Статті в журналах з теми "Wearable video devices in police work"

Background: Augmented reality (AR) and artificial intelligence (AI) are highly disruptive technologies that have revolutionised practices in a wide range of domains, including the security sector. Several law enforcement agencies (LEAs) employ AI in their daily operations for forensics and surveillance. AR is also gaining traction in security, particularly with the advent of affordable wearable devices. Equipping police officers with the tools to facilitate an elevated situational awareness (SA) in patrolling and tactical scenarios is expected to improve LEAs’ safety and capacity to deliver crucial blows against terrorist and/or criminal threats. Methods: In this paper we present DARLENE, an ecosystem incorporating novel AI techniques for activity recognition and pose estimation tasks, combined with a wearable AR framework for visualization of the inferenced results via dynamic content adaptation according to the wearer’s stress level and operational context. The concept has been validated with end-users through co-creation workshops, while the decision-making mechanism for enhancing LEAs’ SA has been assessed with experts. Regarding computer vision components, preliminary tests of the instance segmentation method for humans’ and objects’ detection have been conducted on a subset of videos from the RWF-2000 dataset for violence detection, which have also been used to test a human pose estimation method that has so far exhibited impressive results, constituting the basis of further developments in DARLENE. Results: Evaluation results highlight that target users are positive towards the adoption of the proposed solution in field operations, and that the SA decision-making mechanism produces highly acceptable outcomes. Evaluation of the computer vision components yielded promising results and identified opportunities for improvement. Conclusions: This work provides the context of the DARLENE ecosystem and presents the DARLENE architecture, analyses its individual technologies, and demonstrates preliminary results, which are positive both in terms of technological achievements and user acceptance of the proposed solution.

Cameras are ubiquitous and increasingly mobile. While CCTV has captured considerable attention by surveillance researchers, the new visibility of police activities is increasingly produced by incidental sousveillance and wearable on-officer camera systems. This article considers advocacy for policing’s new visibility, contrasting that of police accountability activists who film police with designers and early adopters of on-officer cameras. In both accounts, these devices promise accountability by virtue of their mechanical objectivity. However, to each party, accountability functions rather differently. By attending to the social and legal privileging of police officers’ perspectives, the article provides an explanation for design decisions that produced Taser’s AXON Flex on-officer cameras and for why police are embracing these new technologies. Critics of these cameras cite privacy concerns, officer discretion in operating cameras, and department disclosure of footage. Nonetheless, advocates of police accountability often presume more video documenting police use of force is always helpful. However, the utility of surveillance video is conditioned by point of view. Police agencies in the U.S. are rapidly adopting on-officer camera systems, because they acknowledge ubiquitous surveillance and that these devices aid in nullifying third-party documentation in favor of a perspective that favors officers. As such, these cameras are counter-sousveillance technologies.

The COVID-19 pandemic severely affected many aspects of human life. While most health agencies agree mask wearing and physical distancing reduce viral transmission, efforts to improve the assessment of these behaviors are lacking. This study aimed to develop a direct observation video method [Viral Transmission (VT)-Scan] for assessing COVID-19 transmission behaviors and related factors (e.g., environmental setting). A wearable video device (WVD) was used to obtain videos of outdoor, public areas. The videos were examined to extract relevant information. All outcomes displayed good to excellent intra- and inter-reliability with intra-class correlation coefficients ranging from 0.836 to 0.997. The majority of people had a mask (60.8%) but 22.1% of them wore it improperly, 45.4% were not physical distancing, and 27.6% were simultaneously mask and physical distancing non-compliant. Transmission behaviors varied by demographics with white, obese males least likely to be mask-compliant and white, obese females least likely to physical distance. Certain environments (e.g., crosswalks) were identified as “hot spots” where higher rates of adverse transmission behaviors occurred. This study introduces a reliable method for obtaining objective data on COVID-19 transmission behaviors and related factors which may be useful for agent-based modeling and policy formation.

To propose an idea for implementing wearable IoT devices using the Raspberry Pi, which is equipped with a sound sensor, camera module, GPS, and GSM. When the sound sensor detects screaming, the SVM (support vector machine) algorithm in machine learning eliminates unnecessary noise and evaluates only the victim screaming. After assessing the victim's scream, the gadget promptly activates the camera module, which takes 30 seconds of footage. GPS will track the geographical coordinates and, using the GSM module, will send an alert message and an emergency call to the nearest police station. When the victim activates the switch in the second scenario, the camera module is immediately activated, and a 30-second clip is captured. The GPS will be active, and GSM will send an alert message with the status. The idea's major goal is to present a smart gadget for a woman that is entirely comfy and portable. When compared to other existing safety devices, the first and most crucial difference is the smart band's ability to shrink the size of gadgets.

With the development of modern technology, wearable technology has become more and more popular in the actual college English listening and speaking teaching mode. Wearable devices, as the name suggests, are smart electronic products that can be worn on the human body, such as smart glasses, smart watches, smart rings and smart clothing. Smart watches and ordinary electronic products are very different from wearable devices. Wearable devices give us a more intelligent and technological experience. Wearable technology has brought new changes and challenges to the realistic college English listening and speaking teaching mode. Wearable technology has become a hot topic and frontier in the field of science and technology. It has been widely used in education, medical, and industrial fields. It provides unprecedented convenience for people to learn, work, and live. Augmented reality technology is a kind of technology that skillfully integrates virtual information with the real world. After the simulation of computer-generated text, images, 3D models, music, video, and other virtual information, it is applied to the real world, and the two kinds of information complement each other, thus realizing the “enhancement” of the real world. This paper gives a brief overview of the definition of wearable technology, the classification, and main features of wearable technology and combines it with college English listening and speaking teaching mode to improve the classroom learning effect. Through the questionnaire survey, we know that wearable technology is a teacher’s teaching, and students’ learning provides great convenience. Wearable technology greatly enhances the learning and listening fun of students.

This paper presents an approach to facilitate mobility for the non-ambulant patients using eye movements and wearable health tracking. The patient’s wheelchair movement is controlled using eye ball movements and also some biomedical assistance functionalities are considered to match the current day needs. The proposed work first detects face from input video, then eye portion will be localized, and finally eye ball (pupil) is detected and tracked using computer vision techniques. The direction of movement is assessed and a command is disseminated to the wheelchair control system. The wearable sensors and\or alarms mounted on patients will update current health status indications on to the monitoring panels. The wearable devices have evolved very smartly which are capable enough to take care of the patient health in real time even during assisted mobility.

The privacy of users and information are becoming increasingly important with the growth and pervasive use of mobile devices such as wearables, mobile phones, drones, and Internet of Things (IoT) devices. Today many of these mobile devices are equipped with cameras which enable users to take pictures and record videos anytime they need to do so. In many such cases, bystanders’ privacy is not a concern, and as a result, audio and video of bystanders are often captured without their consent. We present results from a user study in which 21 participants were asked to use a wearable system called FacePET developed to enhance bystanders’ facial privacy by providing a way for bystanders to protect their own privacy rather than relying on external systems for protection. While past works in the literature focused on privacy perceptions of bystanders when photographed in public/shared spaces, there has not been research with a focus on user perceptions of bystander-based wearable devices to enhance privacy. Thus, in this work, we focus on user perceptions of the FacePET device and/or similar wearables to enhance bystanders’ facial privacy. In our study, we found that 16 participants would use FacePET or similar devices to enhance their facial privacy, and 17 participants agreed that if smart glasses had features to conceal users’ identities, it would allow them to become more popular.

The current state of research on the use of the neural networks under martial law to identify offenders committing illegal acts, prevent acts of terrorism, combat sabotage groups in cities, track weapons and control traffic is considered. The methods of detecting illegal actions, weapons, face recognition and traffic violations using video surveillance cameras are analysed. It is proposed to introduce the studied methods into the work of “smart” video surveillance systems in Ukrainian settlements. The most effective means of reducing the number of offences is the inevitability of legal liability for offences, so many efforts in law enforcement are aimed at preventing offences. Along with public order policing by patrol police, video surveillance is an effective way to prevent illegal activities in society. Increasing the coverage area of cameras and their number helps to ensure public safety in the area where they are used. However, an increase in the number of cameras creates another problem which is the large amount of video data that needs to be processed. To solve the problem of video data processing, various methods are used, the most modern of which is the use of artificial intelligence to filter a large amount of data from video cameras and the application of various video processing algorithms. The ability to simultaneously process video data from many CCTV cameras without human intervention not only contributes to public safety, but also improves the work of patrol police. The introduction of smart video surveillance systems allows monitoring the situation in public places around the clock, even if there is no police presence in the area. In the reviewed studies of video surveillance systems, neural networks, in particular MobileNet V2, YOLO, mYOLOv4-tiny, are used to track illegal actions, criminals and weapons, which are trained on large amounts of video and photo data. It has been found that although neural networks used to require a lot of computing power, they can now be used in IoT systems and smartphones, and this contributes to the fact that more video surveillance devices can be used to monitor the situation.

With the development of 5G and the maturity of embedded technology, the Internet of Things has become the most promising technology at present, and human motion recognition and fingerprint feature recognition are hot research topics in the Internet of Things. At the same time, the way of human-computer interaction no longer satisfies the interaction only through screens and our computing devices. We hope to achieve human-computer interaction through simpler and more direct operations. For example, gestures, speech, etc., while the current methods of human recognition are mostly achieved through video or wearable devices, both of which have certain limitations. For example, when using video devices to recognize human bodies, it is necessary to ensure that there are no obstacles on the line of sight (LOS) in the video and sufficient ambient light is available. The Wi-Fi recognition method proposed in this article has the advantages of non-wearable, no light source restriction, and the ability to achieve human recognition using non-line-of-sight paths. Wi-Fi is ubiquitous in modern society, so using Wi-Fi signals for indoor human sensing has important research value. Based on existing Wi-Fi gait recognition work, this paper proposes a Wi-Fi-RSMID system for indoor human recognition. By analyzing the channel state information of Wi-Fi signals during human walking, the Wi-Fi-RSMID system extracts key feature information through PCA principal component analysis of thirty subcarriers of CSI. It collects 155 feature points from five principal components of PAC using a method that combines time-frequency domain information, and achieves human recognition through random subspace method. Experiments show that the system can effectively identify the identities of 15 people in different scenarios, with an average recognition rate of about 75.3% - 85.6%.

The discipline of computer vision is becoming more popular as a research subject. In a surveillance-based computer vision application, item identification and tracking are the core procedures. They consist of segmenting and tracking an object of interest from a sequence of video frames, and they are both performed using computer vision algorithms. In situations when the camera is fixed and the backdrop remains constant, it is possible to detect items in the background using more straightforward methods. Aerial surveillance, on the other hand, is characterized by the fact that the target, as well as the background and video camera, are all constantly moving. It is feasible to recognize targets in the video data captured by an unmanned aerial vehicle (UAV) using the mean shift tracking technique in combination with a deep convolutional neural network (DCNN). It is critical that the target detection algorithm maintains its accuracy even in the presence of changing lighting conditions, dynamic clutter, and changes in the scene environment. Even though there are several approaches for identifying moving objects in the video, background reduction is the one that is most often used. An adaptive background model is used to create a mean shift tracking technique, which is shown and implemented in this work. In this situation, the background model is provided and updated frame-by-frame, and therefore, the problem of occlusion is fully eliminated from the equation. The target tracking algorithm is fed the same video stream that was used for the target identification algorithm to work with. In MATLAB, the works are simulated, and their performance is evaluated using image-based and video-based metrics to establish how well they operate in the real world.

The purpose of this article is to identify ways to improve organizational measures to ensure public security and order during the mass events by the National Police. Methods such as structural-functional, formal-logical, modeling, analysis, and synthesis were used in the writing of the article. The successful implementation of this measure depends largely on organization, relationships between each police authority and unit, rational distribution of forces and resources, early response to the detection of violations and other events, effective coordination, placement of patrol posts and routes. The Department of Organizational Analytical Support and Rapid Response, which ensures within competencies its coordination, planning, control and coordination of actions of all authorities and units involved to ensure public security and order during mass events, plays an important role in the police work in this direction. It was therefore concluded that: a) improvement of decentralization of the management system of police authorities and units, establishment of the mechanism of its coordination with the territorial police bodies; b) equipping of police authorities and units with modern communication means, GPS-navigators, gas analyzers for identifying the state of drunkenness, video cameras, devices of operational identification, computing complexes etc.; c) developing close cooperation with citizens and their associations, with local communities; d) conducting trainings on keeping public order and providing public security, psychological and physical training, analytical work and more.

Abstract Background Although digital maternity records (DMRs) have been evaluated in the past, no previous work investigated usability or acceptance through an observational usability study. Objective The primary objective was to assess the usability and perception of a DMR smartphone app for pregnant women. The secondary objective was to assess personal preferences and habits related to online information searching, wearable data presentation and interpretation, at-home examination, and sharing data for research purposes during pregnancy. Methods A DMR smartphone app was developed. Key features such as wearable device integration, study functionalities (eg, questionnaires), and common pregnancy app functionalities (eg, mood tracker) were included. Women who had previously given birth were invited to participate. Participants completed 10 tasks while asked to think aloud. Sessions were conducted via Zoom. Video, audio, and the shared screen were recorded for analysis. Task completion times, task success, errors, and self-reported (free text) feedback were evaluated. Usability was measured through the System Usability Scale (SUS) and User Experience Questionnaire (UEQ). Semistructured interviews were conducted to explore the secondary objective. Results A total of 11 participants (mean age 34.6, SD 2.2 years) were included in the study. A mean SUS score of 79.09 (SD 18.38) was achieved. The app was rated “above average” in 4 of 6 UEQ categories. Sixteen unique features were requested. We found that 5 of 11 participants would only use wearables during pregnancy if requested to by their physician, while 10 of 11 stated they would share their data for research purposes. Conclusions Pregnant women rely on their medical caregivers for advice, including on the use of mobile and ubiquitous health technology. Clear benefits must be communicated if issuing wearable devices to pregnant women. Participants that experienced pregnancy complications in the past were overall more open toward the use of wearable devices in pregnancy. Pregnant women have different opinions regarding access to, interpretation of, and reactions to alerts based on wearable data. Future work should investigate personalized concepts covering these aspects.

This research provides a study on a smart body area network (SmartBAN) physical layer (PHY), as an of the Internet of medical things (IoMT) technology, for an advanced human monitoring system in industrial use. The SmartBAN provides a new PHY and a medium access control (MAC) layer, improving its performance and providing very low-latency emergency information transmission with low energy consumption compared with other wireless body area network (WBAN) standards. On the other hand, IoMT applications are expected to become more advanced with smarter wearable devices, such as augmented reality-based human monitoring and work support in a factory. Therefore, it is possible to develop more advanced human monitoring systems for industrial use by combining the SmartBAN with multimedia devices. However, the SmartBAN PHY is not designed to transmit multimedia information such as audio and video. To address this issue, multilevel phase shift keying (PSK) modulation is applied to the SmartBAN PHY, and the symbol rate is improved by setting the roll-off rate appropriately to realize the system. The numerical results show that a sufficient link budget, receiver sensitivity and fade margin were obtained even when those approaches were applied to the SmartBAN PHY. The results indicate that these techniques are required for high-quality audio or video transmission, as well as vital sign data transmission, in a SmartBAN.

The purpose of the work is creation of a set of technical means (switches, sensors) for recognition of transport infrastructure facilities, including development of algorithms for autonomous operation of technical facilities under changing environmental factors. In this work, we used methods for determining the volume of a three-dimensional facilities from the data of photo and video recording of the surrounding situation. The algorithm of technical vision was obtained, which is implemented as a program on a mobile device for recognition by means of stereometry of transport infrastructure facilities and their defects and storage of transport infrastructure defects. The novelty of the research is building of decision algorithms based on devices and sensors that recognize changing road conditions, namely, defects in coverage. The data obtained can be used in the planning of road repairs, in the analysis of traffic accidents by road police, road users for processing complaints, etc.

Freezing of gait (FOG) in Parkinson’s disease (PD) is described as a short-term episode of absence or considerable decrease of movement despite the intention of moving forward. FOG is related to risk of falls and low quality of life for individuals with PD. FOG has been studied and analyzed through different techniques, including inertial movement units (IMUs) and motion capture systems (MOCAP), both along with robust algorithms. Still, there is not a standardized methodology to identify nor quantify freezing episodes (FEs). In a previous work from our group, a new methodology was developed to differentiate FEs from normal movement using position data obtained from a motion capture system. The purpose of this study is to determine if this methodology is equally effective identifying FEs when using IMUs. Twenty subjects with PD will perform two different gait-related tasks. Trials will be tracked by IMUs and filmed by a video camera; data from IMUs will be compared to the time occurrence of FEs obtained from the videos. We expect this methodology will successfully detect FEs with IMUs’ data. Results would allow the development of a wearable device able to detect and monitor FOG. It is expected that the use of this type of devices would allow clinicians to better understand FOG and improve patients’ care.

Automation of the technological processes is rapidly improving with the emergence and development of the artificial intelligence. More complex applications and platforms are being developed to better analyze the production process. Artificial intelligence and robotics are becoming efficient and priority tools for removing employees from the hazardous areas, minimizing the influence of the human factor, preventing, and predicting industrial injuries, automating production, improving labor productivity and quality of work. Artificial intelligence tools used in the world practice and wearable protective devices that serve to minimize industrial injuries and increase labor productivity are considered. The analysis of statistical data on injuries to the personnel of JSC «Russian Railways» during maintenance, operation and repair of power supply devices is presented. Further development and implementation of the artificial intelligence, the latest methods, and technical means of protecting railway personnel from electric shock injury is becoming an urgent task. The article considers video surveillance system «DOZOR» used in the RZD holding, which contributes to strengthening labor and technological discipline at production facilities, enhancing occupational safety, improving the quality of work- places preparation, and performing technological operations. It also allows you to assess professional competence and identify gaps in the theoretical and practical knowledge of the employees. It is proposed to introduce a computer vision device into «DOZOR» video surveillance system, which will ensure compliance with the requirements of the occupational safety rules and regulations in real time. It will also make it possible to promptly inform the employee and his managers about all the violations at a particular workplace for taking timely measures on preventing accidents and injury to the personnel.

The recent growth and spread of smart sensor technologies make these connected devices suitable for diagnostic and monitoring in different fields. In particular, these sensors are useful in diagnostics for control of diseases or during rehabilitation. They are also extensively used in the monitoring field, both by non-expert and expert users, to monitor health status and progress during a sports activity. For athletes, these devices could be used to control and enhance their performance. This development has led to the realization of miniaturized sensors that are wearable during different sporting activities without interfering with the movements of the athlete. The use of these sensors, during training or racing, opens new frontiers for the understanding of motions and causes of injuries. This pilot study introduced a motion analysis system to monitor Alpine ski activities during training sessions. Through five inertial measurement units (IMUs), placed on five points of the athletes, it is possible to compute the angle of each joint and evaluate the ski run. Comparing the IMU data, firstly, with a video and then proposing them to an expert coach, it is possible to observe from the data the same mistakes visible in the camera. The aim of this work is to find a tool to support ski coaches during training sessions. Since the evaluation of athletes is now mainly developed with the support of video, we evaluate the use of IMUs to support the evaluation of the coach with more precise data.

Human activity recognition (HAR) was done in various parts of the world in the most recent decade. HAR intends to give data on human actual activity and to recognize activities in a true setting. HAR is individual of the major problems in the system vision field. Distinguishing and recognizing events or behaviors that are performed by an individual is an essential key objective of astute video frameworks. Person activity is utilized in an assortment of uti1ization zones, from person system cooperation to observation, safety, and wellbeing monitor frameworks. Notwithstanding progressing efforts in the field, HAR is as yet a troublesome errand in an unlimited climate and countenances numerous difficulties. The work incorporates various famous strategies for recognizing activity, in wearable gadgets, and cell phone sensors. Understanding the activities of humans through body sensors data collection methods and analyzing them in machine learning techniques is a demanding task in near future. Wearable devices permit catching assorted reach physiological and efficient data for the app in sports, prosperity, and medical services. Movement Recognition has numerous apps on the planet today. HAR can be characterized as distinguishing and recognizing an individual's activities, for example, "standing, sitting, walking, laying down, walk upstairs, walk downstairs, etc." the proposed system method can add to the fast execution of working activity recognition in genuine working fields.

The ability to monitor Sprained Ankle Rehabilitation Exercises (SPAREs) in home environments can help therapists ascertain if exercises have been performed as prescribed. Whilst wearable devices have been shown to provide advantages such as high accuracy and precision during monitoring activities, disadvantages such as limited battery life and users’ inability to remember to charge and wear the devices are often the challenges for their usage. In addition, video cameras, which are notable for high frame rates and granularity, are not privacy-friendly. Therefore, this paper proposes the use and fusion of privacy-friendly and Unobtrusive Sensing Solutions (USSs) for data collection and processing during SPAREs in home environments. The present work aims to monitor SPAREs such as dorsiflexion, plantarflexion, inversion, and eversion using radar and thermal sensors. The main contributions of this paper include (i) privacy-friendly monitoring of SPAREs in a home environment, (ii) fusion of SPAREs data from homogeneous and heterogeneous USSs, and (iii) analysis and comparison of results from single, homogeneous, and heterogeneous USSs. Experimental results indicated the advantages of using heterogeneous USSs and data fusion. Cluster-based analysis of data gleaned from the sensors indicated an average classification accuracy of 96.9% with Neural Network, AdaBoost, and Support Vector Machine, amongst others.

The technical progress in the last decades makes photo and video recording devices omnipresent. This change has a significant impact, among others, on police work. It is no longer unusual that a myriad of digital data accumulates after a criminal act, which must be reviewed by criminal investigators to collect evidence or solve the crime. This paper presents the VICTORIA Interactive 4D Scene Reconstruction and Analysis Framework (“ISRA-4D” 1.0), an approach for the visual consolidation of heterogeneous video and image data in a 3D reconstruction of the corresponding environment. First, by reconstructing the environment in which the materials were created, a shared spatial context of all available materials is established. Second, all footage is spatially and temporally registered within this 3D reconstruction. Third, a visualization of the hereby created 4D reconstruction (3D scene + time) is provided, which can be analyzed interactively. Additional information on video and image content is also extracted and displayed and can be analyzed with supporting visualizations. The presented approach facilitates the process of filtering, annotating, analyzing, and getting an overview of large amounts of multimedia material. The framework is evaluated using four case studies which demonstrate its broad applicability. Furthermore, the framework allows the user to immerse themselves in the analysis by entering the scenario in virtual reality. This feature is qualitatively evaluated by means of interviews of criminal investigators and outlines potential benefits such as improved spatial understanding and the initiation of new fields of application.

Abstract: Modern rehabilitation procedures use devices that provide physical therapists with various types of information to improve assessment of patient progress during reha-bilitation plans. The new trend of these technologies is the development of safe, portable and comfortable wearable devices with extensive applications in various environments (medical clinics or at the patient's home). The present work presents a portable and safe device for hand rehabilitation, consisting of five finger force sensors and a palmar sensor arranged in the ball, capable of capturing pressure signals during the execution of move-ments guided by the physiotherapist or by a video game/virtual reality. A 3-axis accel-erometer was used to spatially monitor the patient's movements. A series of games with different levels of difficulty were created, through which the degree of mobility of the pa-tient can be monitored depending on the game he chooses and at the same time reflected by the score obtained at the end of the game. Also, to be more interactive, the interface was chosen to play with 2 players simultaneously. So that they can choose to play in the team or as competitors. The system allows users to show different routines to guide them in their use and also evaluates pressure signals and response time. Keywords: microcontroller, games interactive, physiokinetotherapist, rehabilitation, health im-provement.

In recent years, much effort has been devoted to the development of applications capable of detecting different types of human activity. In this field, fall detection is particularly relevant, especially for the elderly. On the one hand, some applications use wearable sensors that are integrated into cell phones, necklaces or smart bracelets to detect sudden movements of the person wearing the device. The main drawback of these types of systems is that these devices must be placed on a person’s body. This is a major drawback because they can be uncomfortable, in addition to the fact that these systems cannot be implemented in open spaces and with unfamiliar people. In contrast, other approaches perform activity recognition from video camera images, which have many advantages over the previous ones since the user is not required to wear the sensors. As a result, these applications can be implemented in open spaces and with unknown people. This paper presents a vision-based algorithm for activity recognition. The main contribution of this work is to use human skeleton pose estimation as a feature extraction method for activity detection in video camera images. The use of this method allows the detection of multiple people’s activities in the same scene. The algorithm is also capable of classifying multi-frame activities, precisely for those that need more than one frame to be detected. The method is evaluated with the public UP-FALL dataset and compared to similar algorithms using the same dataset.

The detection and prevention of workers’ body straining postures and other stressing conditions within the work environment, supports establishing occupational safety and promoting well being and sustainability at work. Developed methods towards this aim typically rely on combining highly ergonomic workplaces and expensive monitoring mechanisms including wearable devices. In this work, we demonstrate how the input from low-cost sensors, specifically, passive camera sensors installed in a real manufacturing workplace, and smartwatches used by the workers can provide useful feedback on the workers’ conditions and can yield key indicators for the prevention of work-related musculo-skeletal disorders (WMSD) and physical fatigue. To this end, we study the ability to assess the risk for physical strain of workers online during work activities based on the classification of ergonomically sub-optimal working postures using visual information, the correlation and fusion of these estimations with synchronous worker heart rate data, as well as the prediction of near-future heart rate using deep learning-based techniques. Moreover, a new multi-modal dataset of video and heart rate data captured in a real manufacturing workplace during car door assembly activities is introduced. The experimental results show the efficiency of the proposed approach that exceeds 70% of classification rate based on the F1 score measure using a set of over 300 annotated video clips of real line workers during work activities. In addition a time lagging correlation between the estimated ergonomic risks for physical strain and high heart rate was assessed using a larger dataset of synchronous visual and heart rate data sequences. The statistical analysis revealed that imposing increased strain to body parts will results in an increase to the heart rate after 100–120 s. This finding is used to improve the short term forecasting of worker’s cardiovascular activity for the next 10 to 30 s by fusing the heart rate data with the estimated ergonomic risks for physical strain and ultimately to train better predictive models for worker fatigue.

In recent days, our world has entered the age of advanced digital systems, which means humans has to interact with technology in all scopes of live, this leads too as a result to another main concept, security. There are many security technologies that was developed to keep user information save. for example, there are several technologies used to let just the accurate user to log into devices like fingerprint, face recognition, or any another type of these systems. These technologies are in continuous development and are still suffering from accuracy, so several studies were performed to get the best accuracy for any of these systems. Computer vision was developed to give the devices the ability to see and recognize objects in an image or a video scene. It is a science that aims to build an intelligent application that are able to understand the content inside images as humans can do. To create a system like this, first step is to make Data acquisition, this task is done by cameras which gives us a sequence of frames when we record a video. After that, this data is analyzed and studied to extract important features from it. This feature will allow us to re- construct the description of the outer world in a manner that can understood by computer system. Face recognition systems are used on a wide range in mobile applications, banks, and military sites, police stations to make a recognition of the criminals, even in covid19 situations the face recognition was used too. Our proposed method aims to increase the accuracy a face recognition system using deep learning models, the system proposed is able to work on any platform compiled with python which is the application was used in our study. The model performed gives a high accuracy with a very speed result.

Identification of vehicles violating a certain speed by measuring the speed of vehicles in a nonintrusivemanner with low cost and good results is very important, as it directly contributes to helping thetraffic police instead of using radar, lidar or other expensive devices, the use of video analysis to estimatethe speed of vehicles involved in traffic accidents is becoming increasingly common. In most cases, theestimate is based on in situ reference measurements or data derived using photogrammetry techniques.In this research, the suggested method estimates the average vehicle speed via computing thedistance between consecutive tires using the "Pixel Image Scale Coefficient" and converts the results toaccurate measurements. Using an installed camera or a mobile phone device at video frames per second(fps of 30 frames per second, a mathematical function to identify the speed of a passing vehiclepredicated on its motion pattern vector and transform that speed from measurements of pixels insucceeding frames to realistic measurements is presented. Three steps were used in this work toimplement the technique: In the first stage, a vehicle is distinguished from other objects utilizing artificialintelligence, particularly the Aggregated Channel Features(ACF) vehicle detectors algorithm. In thesecond step, automobiles are monitored by tracking successive video frames and then the third step,which is the working core of this The research, is to calculate the speed of the detected vehicles insuccessive video frames through the proposed mathematical equation that mainly depends on the productof the obtained Euclidean distance, and then convert this result to what is proportional to the realisticmeasurements of speed, which really is km/h.The project work was produced on a 64-bit system with an Intel Core i7 processor using Matlab R2021a. The software was used to analyze a series of locally captured movies that were used as the datasource for a data set used to calculate the average vehicle speed. The proposed program's results werecompared with the established driving velocity in order to verify the findings. A simulation of a vehiclemoving at a known speed was employed. The mistake rate as a result of the vehicle speeds varied from 1to 5 km/h.

In the field of pervasive computing, wearable devices have been widely used for recognizing human activities. One important area in this research is the recognition of activities of daily living where especially inertial sensors and interaction sensors (like RFID tags with scanners) are popular choices as data sources. Using interaction sensors, however, has one drawback: they may not differentiate between proper interaction and simple touching of an object. A positive signal from an interaction sensor is not necessarily caused by a performed activity e.g., when an object is only touched but no interaction occurred afterwards. There are, however, many scenarios like medicine intake that rely heavily on correctly recognized activities. In our work, we aim to address this limitation and present a multimodal egocentric-based activity recognition approach. Our solution relies on object detection that recognizes activity-critical objects in a frame. As it is infeasible to always expect a high quality camera view, we enrich the vision features with inertial sensor data that monitors the users’ arm movement. This way we try to overcome the drawbacks of each respective sensor. We present our results of combining inertial and video features to recognize human activities on different types of scenarios where we achieve an F 1 -measure of up to 79.6%.

As mental health (MH) disorders become increasingly prevalent, their multifaceted symptoms and comorbidities with other conditions introduce complexity to diagnosis, posing a risk of underdiagnosis. While machine learning (ML) has been explored to mitigate these challenges, we hypothesized that multiple data modalities support more comprehensive detection and that non-intrusive collection approaches better capture natural behaviors. To understand the current trends, we systematically reviewed 184 studies to assess feature extraction, feature fusion, and ML methodologies applied to detect MH disorders from passively sensed multimodal data, including audio and video recordings, social media, smartphones, and wearable devices. Our findings revealed varying correlations of modality-specific features in individualized contexts, potentially influenced by demographics and personalities. We also observed the growing adoption of neural network architectures for model-level fusion and as ML algorithms, which have demonstrated promising efficacy in handling high-dimensional features while modeling within and cross-modality relationships. This work provides future researchers with a clear taxonomy of methodological approaches to multimodal detection of MH disorders to inspire future methodological advancements. The comprehensive analysis also guides and supports future researchers in making informed decisions to select an optimal data source that aligns with specific use cases based on the MH disorder of interest.

Recognizing human activity from video sequences and sensor data is one of the major challenges in human-computer interaction and computer vision. Health care is a rapidly developing field of technology and services. The latest development in this field is remote patient monitoring, which has many advantages in a rapidly evolving world. With relatively simple applications for monitoring patients within hospital rooms, technology has advanced to the point where a patient can be allowed to carry out normal daily activities at home while still being monitored using modern communication technologies and sensors. These new technologies can monitor patients based on their disease or condition. The technology varies from sensors attached to the body to peripheral sensors connected to the environment, and innovations show contactless monitoring that only requires the patient to be within a few meters of the sensor. Nowadays, the Internet of Things, wearable devices, mobile technologies, and improved communication and computing capabilities have given rise to innovative mobile health solutions, and several research efforts have recently been made in the field of autism spectrum disorders (ASD). This technology may be particularly useful for some rapidly changing emotional states, especially people with ASD. Children with ASD have some disturbing activities, and usually cannot speak fluently. Instead, they use signs and words to establish rapport, so understanding their needs is one of the most challenging tasks for healthcare providers, but monitoring the disease can make it much easier. We study in this work more than 50 collected articles that have made a significant contribution to the field were selected. Indeed, the current paper reviews the literature to identify current trends, expectations, and potential gaps related to the latest portable, smart, and wearable technologies in the field of ASD. This study also provides a review of recent developments in health care and monitoring of people with autism.

Affective computing through physiological signals monitoring is currently a hot topic in the scientific literature, but also in the industry. Many wearable devices are being developed for health or wellness tracking during daily life or sports activity. Likewise, other applications are being proposed for the early detection of risk situations involving sexual or violent aggressions, with the identification of panic or fear emotions. The use of other sources of information, such as video or audio signals will make multimodal affective computing a more powerful tool for emotion classification, improving the detection capability. There are other biological elements that have not been explored yet and that could provide additional information to better disentangle negative emotions, such as fear or panic. Catecholamines are hormones produced by the adrenal glands, two small glands located above the kidneys. These hormones are released in the body in response to physical or emotional stress. The main catecholamines, namely adrenaline, noradrenaline and dopamine have been analysed, as well as four physiological variables: skin temperature, electrodermal activity, blood volume pulse (to calculate heart rate activity. i.e., beats per minute) and respiration rate. This work presents a comparison of the results provided by the analysis of physiological signals in reference to catecholamine, from an experimental task with 21 female volunteers receiving audiovisual stimuli through an immersive environment in virtual reality. Artificial intelligence algorithms for fear classification with physiological variables and plasma catecholamine concentration levels have been proposed and tested. The best results have been obtained with the features extracted from the physiological variables. Adding catecholamine’s maximum variation during the five minutes after the video clip visualization, as well as adding the five measurements (1-min interval) of these levels, are not providing better performance in the classifiers.

Arm swing during gait has been positively related to gait stability and gait efficiency, particularly in the presence of neurological disorders that affect locomotion. However, most gait studies have focused on lower extremities, while arm swing usually remains ignored. In addition, these studies are mostly based on costly, highly-specialized vision systems or on wearable devices which, despite their popularity among researchers and specialists, are still relatively uncommon for the general population. This work proposes a way of estimating arm swing asymmetry from a single 2D gait video. First, two silhouette-based representations that separately capture motion data from both arms were built. Second, a measure to quantify arm swing energy from such a representation was introduced, producing two side-dependent motion measurements. Third, an arm swing asymmetry index was obtained. The method was validated on two public datasets, one with 68 healthy subjects walking normally and one with 10 healthy subjects simulating different styles of arm swing asymmetry. The validity of the asymmetry index at capturing different arm swing patterns was assessed by two non-parametric tests: the Mann–Whitney U test and the Wilcoxon signed-rank test. The so-called physiological asymmetry was observed on the normal gait sequences of both datasets in a statistically similar way. The asymmetry index was able to fairly characterize the different levels of asymmetry simulated in the second set. Results show that it is possible to estimate the arm swing asymmetry from a single 2D gait video, with enough sensitivity to discriminate anomalous patterns from normality. This opens the door to low-cost easy-to-use mobile applications to assist clinicians in monitoring gait condition in primary care (e.g., in the elderly), when more accurate and specialized technologies are often not available.

Background Multisensor fitness trackers offer the ability to longitudinally estimate sleep quality in a home environment with the potential to outperform traditional actigraphy. To benefit from these new tools for objectively assessing sleep for clinical and research purposes, multisensor wearable devices require careful validation against the gold standard of sleep polysomnography (PSG). Naturalistic studies favor validation. Objective This study aims to validate the Fitbit Charge 2 against portable home PSG in a shift-work population composed of 59 first responder police officers and paramedics undergoing shift work. Methods A reliable comparison between the two measurements was ensured through the data-driven alignment of a PSG and Fitbit time series that was recorded at night. Epoch-by-epoch analyses and Bland-Altman plots were used to assess sensitivity, specificity, accuracy, the Matthews correlation coefficient, bias, and limits of agreement. Results Sleep onset and offset, total sleep time, and the durations of rapid eye movement (REM) sleep and non–rapid-eye movement sleep stages N1+N2 and N3 displayed unbiased estimates with nonnegligible limits of agreement. In contrast, the proprietary Fitbit algorithm overestimated REM sleep latency by 29.4 minutes and wakefulness after sleep onset (WASO) by 37.1 minutes. Epoch-by-epoch analyses indicated better specificity than sensitivity, with higher accuracies for WASO (0.82) and REM sleep (0.86) than those for N1+N2 (0.55) and N3 (0.78) sleep. Fitbit heart rate (HR) displayed a small underestimation of 0.9 beats per minute (bpm) and a limited capability to capture sudden HR changes because of the lower time resolution compared to that of PSG. The underestimation was smaller in N2, N3, and REM sleep (0.6-0.7 bpm) than in N1 sleep (1.2 bpm) and wakefulness (1.9 bpm), indicating a state-specific bias. Finally, Fitbit suggested a distribution of all sleep episode durations that was different from that derived from PSG and showed nonbiological discontinuities, indicating the potential limitations of the staging algorithm. Conclusions We conclude that by following careful data processing processes, the Fitbit Charge 2 can provide reasonably accurate mean values of sleep and HR estimates in shift workers under naturalistic conditions. Nevertheless, the generally wide limits of agreement hamper the precision of quantifying individual sleep episodes. The value of this consumer-grade multisensor wearable in terms of tackling clinical and research questions could be enhanced with open-source algorithms, raw data access, and the ability to blind participants to their own sleep data.

Background Multisensor fitness trackers offer the ability to longitudinally estimate sleep quality in a home environment with the potential to outperform traditional actigraphy. To benefit from these new tools for objectively assessing sleep for clinical and research purposes, multisensor wearable devices require careful validation against the gold standard of sleep polysomnography (PSG). Naturalistic studies favor validation. Objective This study aims to validate the Fitbit Charge 2 against portable home PSG in a shift-work population composed of 59 first responder police officers and paramedics undergoing shift work. Methods A reliable comparison between the two measurements was ensured through the data-driven alignment of a PSG and Fitbit time series that was recorded at night. Epoch-by-epoch analyses and Bland-Altman plots were used to assess sensitivity, specificity, accuracy, the Matthews correlation coefficient, bias, and limits of agreement. Results Sleep onset and offset, total sleep time, and the durations of rapid eye movement (REM) sleep and non–rapid-eye movement sleep stages N1+N2 and N3 displayed unbiased estimates with nonnegligible limits of agreement. In contrast, the proprietary Fitbit algorithm overestimated REM sleep latency by 29.4 minutes and wakefulness after sleep onset (WASO) by 37.1 minutes. Epoch-by-epoch analyses indicated better specificity than sensitivity, with higher accuracies for WASO (0.82) and REM sleep (0.86) than those for N1+N2 (0.55) and N3 (0.78) sleep. Fitbit heart rate (HR) displayed a small underestimation of 0.9 beats per minute (bpm) and a limited capability to capture sudden HR changes because of the lower time resolution compared to that of PSG. The underestimation was smaller in N2, N3, and REM sleep (0.6-0.7 bpm) than in N1 sleep (1.2 bpm) and wakefulness (1.9 bpm), indicating a state-specific bias. Finally, Fitbit suggested a distribution of all sleep episode durations that was different from that derived from PSG and showed nonbiological discontinuities, indicating the potential limitations of the staging algorithm. Conclusions We conclude that by following careful data processing processes, the Fitbit Charge 2 can provide reasonably accurate mean values of sleep and HR estimates in shift workers under naturalistic conditions. Nevertheless, the generally wide limits of agreement hamper the precision of quantifying individual sleep episodes. The value of this consumer-grade multisensor wearable in terms of tackling clinical and research questions could be enhanced with open-source algorithms, raw data access, and the ability to blind participants to their own sleep data.

Augmented reality (AR) is one of the newest learning technologies besides Artificial Intelligent, Virtual Reality, Virtual World, Alternates Reality Games, and Wearable Computing. E-Government is becoming an evolving academic field and transforming to be E-Governance, E-Participation, E-Service, E-Democracy, E-Voting issues. Therefore, some universities have E-Government course in their curriculum. AR can be one of the learning media to learn and teach E-Government effectively and interestingly. This research aims and contributes to develop a novel model of E-Government learning media using AR. Furthermore, this work has three novelties as follows:First, a method to develop e-Government learning media using AR. Second, a novel model of e-government learning media based on augmented reality technology. Third, the material courses are command centre and public service mall materials based in Surabaya, Indonesia. The new model of learning media using AR consists of main components, i.e., user, devices, AR, and course materials. Additionally, this novel model has some sub-components, such as AR object, marker, text, image, audio, video, and 3D animation. The proposed model has some practical and theoretical implications. For the theoretical implication , it adds a model of learning media for e-government course and extends the body of knowledge for e-government and augmented reality fields. For practice, e-Government courses can uilize the augmented reality application.

Affect detection combined with a system that dynamically responds to a person’s emotional state allows an improved user experience with computers, systems, and environments and has a wide range of applications, including entertainment and health care. Previous studies on this topic have used a variety of machine learning algorithms and inputs such as audial, visual, or physiological signals. Recently, a lot of interest has been focused on the last, as speech or video recording is impractical for some applications. Therefore, there is a need to create Human–Computer Interface Systems capable of recognizing emotional states from noninvasive and nonintrusive physiological signals. Typically, the recognition task is carried out from electroencephalogram (EEG) signals, obtaining good accuracy. However, EEGs are difficult to register without interfering with daily activities, and recent studies have shown that it is possible to use electrocardiogram (ECG) signals for this purpose. This work improves the performance of emotion recognition from ECG signals using wavelet transform for signal analysis. Features of the ECG signal are extracted from the AMIGOS database using a wavelet scattering algorithm that allows obtaining features of the signal at different time scales, which are then used as inputs for different classifiers to evaluate their performance. The results show that the proposed algorithm for extracting features and classifying the signals obtains an accuracy of 88.8% in the valence dimension, 90.2% in arousal, and 95.3% in a two-dimensional classification, which is better than the performance reported in previous studies. This algorithm is expected to be useful for classifying emotions using wearable devices.

Heart rate variability (HRV) is a simple, non-invasive, real-time analyzable, and highly reproducible measurement that captures incidences for assessing a person’s health and physical condition. Public security jobs are characterized by major exposure to risk factors known to influence the cardiovascular response to stimuli, e.g., night shifts, highly physically demanding activity, and acute stress activity. This study aimed to evaluate the HRV parameters in a population of 112 male personnel of the special forces and public order of the Carabinieri, aged 25–59, when engaged in several duty tasks, such as paratroopers, night shift police station officers, night shift patrol, dynamic precision shooting evaluative team, dynamic precision shooting non-evaluative team, and office clerks (used as control group). During the specific task of each participant, the HRV parameters were collected with wearable devices and processed. The HRV parameters in the time and frequency domains collected were average heart rate, standard deviation of all normal RR intervals, root mean square of successive differences in adjacent normal-to-normal (NN) intervals, very-low-frequency power, low-frequency power, high-frequency power, stress index, parasympathetic nervous system activity index, and sympathetic nervous system activity index. Parametric tests for independent series to compare the HRV parameters by subgroups within the study subjects were used. A multivariate linear regression analysis was conducted to evaluate the association between the HRV parameters and some personal and organizational factors. The comparison between different subgroups showed that activities with a high demand for concentration and precision, as is the case with paratroopers and dynamic precision shooters, differ significantly from activities that can be defined as routine, such as office work. Other activities, such as patrolling or remote management from operations centers, although including critical elements, did not deviate significantly from the control group. The study of HRV parameters is therefore a useful tool for occupational physicians, both for addressing work suitability assessments and for better targeting health promotion campaigns, to be considered as being aimed at monitoring the subject’s physiological parameters, and not at the diagnosis of any pathological condition, which should always be carried out by the medical specialist.

Early detection and intervention of gas leaks can reduce industrial risks. Numerous early detection methods have been developed and applied in the industrial field, but they require professional analysis technology, long analysis time, and relatively expensive equipment. Strategies to reduce industrial gas hazards constantly require the development of new, efficient and reliable devices. In the past few decades, various types of gas sensors have been developed based on semiconductors, optical fibers, acoustic waves and other technologies. A significant amount of work has been done in recent years to make sensors smaller, more sensitive, more visually responsive, more manageable, more personal, and more wearable. However, these functions require expensive equipment, complex skills, and large amounts of power. In this regard, colorimetric sensors are of great interest due to their simplicity, ease of manufacture, low cost, visual response, and ease of interpretation without power consumption. However, current colorimetric sensors have some limitations to overcome, such as sensitivity, high cost, early detection and accuracy for use in industrial safety systems. Conventional colorimetric sensor studies use algorithms to compare discoloration with the naked eye, estimate gas concentrations with simple statistical methods, or estimate simple discoloration information using machine learning algorithms to estimate time-series data. Algorithms are trained on measured images or time series data extracted from images. Signal processing focuses on denoising done by scaling time series data. These studies using machine learning and deep learning-based analytics for colorimetric sensor studies did not give sufficient consideration to data coding. Machine learning of time series data is performed using a time series decomposition method that separates time dependencies. I am trying to analyze time-series data through image encoding. In this study, a time series data analysis technique using CNN (Convolutional Neural Network) including multidimensional image encoding was applied to improve the gas concentration estimation accuracy. The estimation accuracy obtained in this study was higher than the estimation accuracy obtained by applying existing statistical methods such as Auto-Regressive Integrated Moving Average (ARIMA) and Exponential Smoothing (ETS) and machine learning techniques such as Multi-layer Perceptron (MLP). We focused on estimating gas concentrations using a time-series-based colorimetric analysis method developed based on colorimetric fabric detection data. Time series data obtained through gas experiments were encoded into images to classify the color value change trend of gas concentration. Image encoding improves the efficiency of specifying gas-exposed sections and estimating gas concentrations within the entire section. Compared to the concentration estimation accuracy of the existing data classification method, MLP was improved by more than 2.5%. In addition, the accuracy was improved by applying a CNN that learned multidimensional processing of sensor data through image encoding. As a result, it was confirmed that the estimation accuracy was improved by 6.1% compared to the basic estimation technique. Although this method has limited data form and application fields, it is effective for subjects such as ours. The proposed technology can be applied to the next-generation smart industrial safety system. Figure 1

This study aims to implement AIoT-based safety module algorithm and platform service technology to build a safety environment in shipyards. To this end, platform service technology is implemented through safety module algorithms and killer content implementation through artificial intelligence learning. In particular, accident prevention and prediction are very important for the continuous ESG management of exporting companies, and safety mode service technology is tested so that managers can quickly evaluate risks through the application of platform service technology and safety modules to prevent serious accidents. The Enforcement Decree of the Act on the Punishment of Serious Disasters, etc., which applies to workplaces with 50 or fewer employees from 2024, suggests the necessity of preparing a minimum safety framework to prevent serious accidents in the establishment and implementation of a safety and health management system. In particular, standardization and algorithm development for risk assessment in accordance with the enactment of notices and guidelines for each field are required. Based on the implementation of these laws, we present decision methods and guidelines for safety diagnosis determination through the implementation of analysis algorithms based on advanced technologies (sensor IoT, network, wearable devices, AI analysis technology, etc.) for major safety accident factors. Until recently, the focus was on the importance of the technical area by focusing on the development, installation, and operation of technology-oriented systems, and if the safety grade was worked on according to the institutional impact on risk diagnosis, the risk factors and harmful factors of the workplace should be identified in advance in accordance with the enforcement of the Serious Disaster Act to estimate and determine the likelihood of injury or disease caused by the factor and the intensity of the disaster, and to establish and implement reduction measures on their own. As Article 36 of the Occupational Safety and Health Act mandates employers to conduct risk assessments on their own, attention to disaster and safety has become commonplace. Accordingly, it is possible to prevent accidents in advance through response solutions based on AIoT technology, and to minimize workers' safety guarantees and accidents through rapid and effective responses. Therefore, by detecting and analyzing risk factors in the field in real time using sensor AIoT technology for small and medium-sized shipyards in poor environments, potential risks can be identified early and serious accidents can be handled quickly. AIoT service technology can warn of the possibility of an accident and the high probability of an accident by establishing a proactive system using big data analysis and prediction models. In addition, virtual space utilization technology based on artificial intelligence can inform field workers of risks in real time and take immediate safety measures through risk factor analysis. Recently, due to the aging society and the MZ generation's avoidance of field work, a large number of foreign workers have flowed in, and the responsibility for accidents at small and medium-sized shipyards due to lack of communication and unskilled workers is increasing. Moreover, from 2024, SMEs in poor environments must respond through safety environment solutions by applying the Major Disaster Act to small and medium-sized workplaces with 50 or fewer employees.

The PreEpiSeizures project was created to better understand epilepsy and seizures through wearable technologies. The motivation was to capture physiological information related to epileptic seizures, besides Electroencephalography (EEG) during video-EEG monitorings. If other physiological signals have reliable information of epileptic seizures, unobtrusive wearable technology could be used to monitor epilepsy in daily life. The development of wearable solutions for epilepsy is limited by the nonexistence of datasets which could validate these solutions. Three different form factors were developed and deployed, and the signal quality was assessed for all acquired biosignals. The wearable data acquisition was performed during the video-EEG of patients with epilepsy. The results achieved so far include 59 patients from 2 hospitals totaling 2,721 h of wearable data and 348 seizures. Besides the wearable data, the Electrocardiogram of the hospital is also useable, totalling 5,838 h of hospital data. The quality ECG signals collected with the proposed wearable is equated with the hospital system, and all other biosignals also achieved state-of-the-art quality. During the data acquisition, 18 challenges were identified, and are presented alongside their possible solutions. Though this is an ongoing work, there were many lessons learned which could help to predict possible problems in wearable data collections and also contribute to the epilepsy community with new physiological information. This work contributes with original wearable data and results relevant to epilepsy research, and discusses relevant challenges that impact wearable health monitoring.

AbstractDrones have been applied to a wide range of security and surveillance applications recently. With drones, Internet of Things are extending to 3D space. An interesting question is: Can we conduct person identification (PID) in a drone view? Traditional PID technologies such as RFID and fingerprint/iris/face recognition have their limitations or require close contact to specific devices. Hence, these traditional technologies can not be easily deployed to drones due to dynamic change of view angle and height. In this work, we demonstrate how to retrieve IoT data from users’ wearables and correctly tag them on the human objects captured by a drone camera to identify and track ground human objects. First, we retrieve human objects from videos and conduct coordination transformation to handle the change of drone positions. Second, a fusion algorithm is applied to measure the correlation of video data and inertial data based on the extracted human motion features. Finally, we can couple human objects with their wearable IoT devices, achieving our goal of tagging wearable device data (such as personal profiles) on human objects in a drone view. Our experimental evaluation shows a recognition rate of 99.5% for varying walking paths, and 98.6% when the drone’s camera angle is within 37°. To the best of our knowledge, this is the first work integrating videos from drone cameras and IoT data from inertial sensors.

AbstractPatients with atopic dermatitis experience increased nocturnal pruritus which leads to scratching and sleep disturbances that significantly contribute to poor quality of life. Objective measurements of nighttime scratching and sleep quantity can help assess the efficacy of an intervention. Wearable sensors can provide novel, objective measures of nighttime scratching and sleep; however, many current approaches were not designed for passive, unsupervised monitoring during daily life. In this work, we present the development and analytical validation of a method that sequentially processes epochs of sample-level accelerometer data from a wrist-worn device to provide continuous digital measures of nighttime scratching and sleep quantity. This approach uses heuristic and machine learning algorithms in a hierarchical paradigm by first determining when the patient intends to sleep, then detecting sleep–wake states along with scratching episodes, and lastly deriving objective measures of both sleep and scratch. Leveraging reference data collected in a sleep laboratory (NCT ID: NCT03490877), results show that sensor-derived measures of total sleep opportunity (TSO; time when patient intends to sleep) and total sleep time (TST) correlate well with reference polysomnography data (TSO: r = 0.72, p < 0.001; TST: r = 0.76, p < 0.001; N = 32). Log transformed sensor derived measures of total scratching duration achieve strong agreement with reference annotated video recordings (r = 0.82, p < 0.001; N = 25). These results support the use of wearable sensors for objective, continuous measurement of nighttime scratching and sleep during daily life.

Introduction: Wearable assistive devices for the visually impaired whose technology is based on video camera devices represent a challenge in rapid evolution, where one of the main problems is to find computer vision algorithms that can be implemented in low-cost embedded devices.Objectives and Methods: This work presents a Tiny You Only Look Once architecture for pedestrian detection, which can be implemented in low-cost wearable devices as an alternative for the development of assistive technologies for the visually impaired.Results: The recall results of the proposed refined model represent an improvement of 71% working with four anchor boxes and 66% with six anchor boxes compared to the original model. The accuracy achieved on the same data set shows an increase of 14% and 25%, respectively. The F1 calculation shows a refinement of 57% and 55%. The average accuracy of the models achieved an improvement of 87% and 99%. The number of correctly detected objects was 3098 and 2892 for four and six anchor boxes, respectively, whose performance is better by 77% and 65% compared to the original, which correctly detected 1743 objects.Discussion: Finally, the model was optimized for the Jetson Nano embedded system, a case study for low-power embedded devices, and in a desktop computer. In both cases, the graphics processing unit (GPU) and central processing unit were tested, and a documented comparison of solutions aimed at serving visually impaired people was performed.Conclusion: We performed the desktop tests with a RTX 2070S graphics card, and the image processing took about 2.8 ms. The Jetson Nano board could process an image in about 110 ms, offering the opportunity to generate alert notification procedures in support of visually impaired mobility.

Abstract Purpose Wearable ultrasound devices can be used to continuously monitor muscle activity. One possible application is to provide real-time feedback during physiotherapy, to show a patient whether an exercise is performed correctly. Algorithms which automatically analyze the data can be of importance to overcome the need for manual assessment and annotations and speed up evaluations especially when considering real-time video sequences. They even could be used to present feedback in an understandable manner to patients in a home-use scenario. The following work investigates three deep learning based segmentation approaches for abdominal muscles in ultrasound videos during a segmental stabilizing exercise. The segmentations are used to automatically classify the contraction state of the muscles. Methods The first approach employs a simple 2D network, while the remaining two integrate the time information from the videos either via additional tracking or directly into the network architecture. The contraction state is determined by comparing measures such as muscle thickness and center of mass between rest and exercise. A retrospective analysis is conducted but also a real-time scenario is simulated, where classification is performed during exercise. Results Using the proposed segmentation algorithms, 71% of the muscle states are classified correctly in the retrospective analysis in comparison to 90% accuracy with manual reference segmentation. For the real-time approach the majority of given feedback during exercise is correct when the retrospective analysis had come to the correct result, too. Conclusion Both retrospective and real-time analysis prove to be feasible. While no substantial differences between the algorithms were observed regarding classification, the networks incorporating the time information showed temporally more consistent segmentations. Limitations of the approaches as well as reasons for failing cases in segmentation, classification and real-time assessment are discussed and requirements regarding image quality and hardware design are derived.

Abstract Introduction Penile erection is well understood and has been extensively studied. The Erectile Hardness Score is a commonly used tool to quantify the strength of an erection. Few such measurement tools exists for women. This study builds on the work done by Mechelmans et al exploring Clitoral Pulse Amplitude (CPA) as a marker for physical arousal in women. CPA has been shown to be related to clitoral blood volume, erection, and engorgement of the clitoris. The erection in the clitoris is homologous to penile erection. Objective To test a new, wearable, clitoral pulse sensor designed for at-home use for correlation with subjective arousal for proof of concept. To test the comfort and usability of such a device configured with an internal (vaginal) portion and a clitoral portion. Methods 20 healthy female participants were shipped the device and completed the study from their home with an online module which guided them through the study material. Participants wore the device while watching a control (non-arousing) video and during progressively more sexually arousing activities. They were allowed to choose their own materials to watch, read, or listen to for arousal. A masturbation phase was included for additional information. Participants also reported their subjective arousal after each phase. After the test, participants were also surveyed about the comfort and usability of the device. Results The pulse sensor successfully detected CPA. Results show that most participants had increasing levels of subjective arousal correlating with increasing CPA. Statistical correlation between CPA and arousal was positive but low, which could be attributed to differences of sensor calibration and/or device placement by participants. Overall, this positive relationship indicates that a commercially available pulse sensor could be integrated into a future device to measure physical arousal in women, a metric which was previously not widely available. Participants reported high satisfaction with the comfort and usability of the device. These insights validate that this device shape will be comfortable and usable in further iterations, with the ultimate goal of producing a device which would give clitoris-owners greater insight into their sexual health and provide valuable information to their healthcare providers. Conclusions This study showed a positive relationship between Clitoral Pulse Amplitude and subjective sexual arousal using an at-home wearable device, opening possibilities for future measurement devices. Participants felt the device was very comfortable and easy to use, suggesting this form factor with vaginal (internal) and clitoral (external) portions is a viable configuration for further development. We anticipate improving both the pulse sensing system and device usability as the device is further commercialized. Disclosure Yes, this is sponsored by industry/sponsor: FirmTech. Clarification: Industry initiated, executed and funded study. Any of the authors act as a consultant, employee or shareholder of an industry for: FirmTech.

Abstract Introduction Penile erection is well understood and has been extensively studied. The Erectile Hardness Score is a commonly used tool to quantify the strength of an erection. Few such measurement tools exists for women. This study builds on the work done by Mechelmans et al exploring Clitoral Pulse Amplitude (CPA) as a marker for physical arousal in women. CPA has been shown to be related to clitoral blood volume, erection, and engorgement of the clitoris. The erection in the clitoris is homologous to penile erection. Objective To test a new, wearable, clitoral pulse sensor designed for at-home use for correlation with subjective arousal for proof of concept. To test the comfort and usability of such a device configured with an internal (vaginal) portion and a clitoral portion. Methods 20 healthy female participants were shipped the device and completed the study from their home with an online module which guided them through the study material. Participants wore the device while watching a control (non-arousing) video and during progressively more sexually arousing activities. They were allowed to choose their own materials to watch, read, or listen to for arousal. A masturbation phase was included for additional information. Participants also reported their subjective arousal after each phase. After the test, participants were also surveyed about the comfort and usability of the device. Results The pulse sensor successfully detected CPA. Results show that most participants had increasing levels of subjective arousal correlating with increasing CPA. Statistical correlation between CPA and arousal was positive but low, which could be attributed to differences of sensor calibration and/or device placement by participants. Overall, this positive relationship indicates that a commercially available pulse sensor could be integrated into a future device to measure physical arousal in women, a metric which was previously not widely available. Participants reported high satisfaction with the comfort and usability of the device. These insights validate that this device shape will be comfortable and usable in further iterations, with the ultimate goal of producing a device which would give clitoris-owners greater insight into their sexual health and provide valuable information to their healthcare providers. Conclusions This study showed a positive relationship between Clitoral Pulse Amplitude and subjective sexual arousal using an at-home wearable device, opening possibilities for future measurement devices. Participants felt the device was very comfortable and easy to use, suggesting this form factor with vaginal (internal) and clitoral (external) portions is a viable configuration for further development. We anticipate improving both the pulse sensing system and device usability as the device is further commercialized. Disclosure Yes, this is sponsored by industry/sponsor: FirmTech. Clarification: Industry initiated, executed and funded study. Any of the authors act as a consultant, employee or shareholder of an industry for: FirmTech.

Assessment of mental workload is crucial for applications that require sustained attention and where conditions such as mental fatigue and drowsiness must be avoided. Previous work that attempted to devise objective methods to model mental workload were mainly based on neurological or physiological data collected when the participants performed tasks that did not involve physical activity. While such models may be useful for scenarios that involve static operators, they may not apply in real-world situations where operators are performing tasks under varying levels of physical activity, such as those faced by first responders, firefighters, and police officers. Here, we describe WAUC, a multimodal database of mental Workload Assessment Under physical aCtivity. The study involved 48 participants who performed the NASA Revised Multi-Attribute Task Battery II under three different activity level conditions. Physical activity was manipulated by changing the speed of a stationary bike or a treadmill. During data collection, six neural and physiological modalities were recorded, namely: electroencephalography, electrocardiography, breathing rate, skin temperature, galvanic skin response, and blood volume pulse, in addition to 3-axis accelerometry. Moreover, participants were asked to answer the NASA Task Load Index questionnaire after each experimental section, as well as rate their physical fatigue level on the Borg fatigue scale. In order to bring our experimental setup closer to real-world situations, all signals were monitored using wearable, off-the-shelf devices. In this paper, we describe the adopted experimental protocol, as well as validate the subjective, neural, and physiological data collected. The WAUC database, including the raw data and features, subjective ratings, and scripts to reproduce the experiments reported herein will be made available at: http://musaelab.ca/resources/.

AbstractThis work investigates the estimation biases of remote photoplethysmography (rPPG) methods for pulse rate measurement across diverse demographics. Advances in photoplethysmography (PPG) and rPPG methods have enabled the development of contact and noncontact approaches for continuous monitoring and collection of patient health data. The contagious nature of viruses such as COVID-19 warrants noncontact methods for physiological signal estimation. However, these approaches are subject to estimation biases due to variations in environmental conditions and subject demographics. The performance of contact-based wearable sensors has been evaluated, using off-the-shelf devices across demographics. However, the measurement uncertainty of rPPG methods that estimate pulse rate has not been sufficiently tested across diverse demographic populations or environments. Quantifying the efficacy of rPPG methods in real-world conditions is critical in determining their potential viability as health monitoring solutions. Currently, publicly available face datasets accompanied by physiological measurements are typically captured in controlled laboratory settings, lacking diversity in subject skin tones, age, and cultural artifacts (e.g, bindi worn by Indian women). In this study, we collect pulse rate and facial video data from human subjects in India and Sierra Leone, in order to quantify the uncertainty in noncontact pulse rate estimation methods. The video data are used to estimate pulse rate using state-of-the-art rPPG camera-based methods, and compared against ground truth measurements captured using an FDA-approved contact-based pulse rate measurement device. Our study reveals that rPPG methods exhibit similar biases when compared with a contact-based device across demographic groups and environmental conditions. The mean difference between pulse rates measured by rPPG methods and the ground truth is found to be ~2% (1 beats per minute (b.p.m.)), signifying agreement of rPPG methods with the ground truth. We also find that rPPG methods show pulse rate variability of ~15% (11 b.p.m.), as compared to the ground truth. We investigate factors impacting rPPG methods and discuss solutions aimed at mitigating variance.

Introduction: Mental disorders are a leading cause of disability worldwide. Depression has a significant impact in the field of occupational health because it is particularly prevalent during working age. On the other hand, there are a growing number of studies on the relationship between “well-being” and employee productivity. To promote healthy and productive workplaces, this study aims to develop a technique to quantify stress and well-being in a way that does not disturb the workplace.Methods and analysis: This is a single-arm prospective observational study. The target population is adult (&gt;20 years old) workers at companies that often engage in desk work; specifically, a person who sits in front of a computer for at least half their work hours. The following data will be collected: (a) participants' background characteristics; (b) participants' biological data during the 4-week observation period using sensing devices such as a camera built into the computer (pulse wave data extracted from the facial video images), a microphone built into their work computer (voice data), and a wristband-type wearable device (electrodermal activity data, body motion data, and body temperature); (c) stress, well-being, and depression rating scale assessment data. The analysis workflow is as follows: (1) primary analysis, comprised of using software to digitalize participants' vital information; (2) secondary analysis, comprised of examining the relationship between the quantified vital data from (1), stress, well-being, and depression; (3) tertiary analysis, comprised of generating machine learning algorithms to estimate stress, well-being, and degree of depression in relation to each set of vital data as well as multimodal vital data.Discussion: This study will evaluate digital phenotype regarding stress and well-being of white-collar workers over a 4-week period using persistently obtainable biomarkers such as heart rate, acoustic characteristics, body motion, and electrodermal activity. Eventually, this study will lead to the development of a machine learning algorithm to determine people's optimal levels of stress and well-being.Ethics and dissemination: Collected data and study results will be disseminated widely through conference presentations, journal publications, and/or mass media. The summarized results of our overall analysis will be supplied to participants.Registration: UMIN000036814

Introduction This article is a study in anxiety with regard to social online spaces (SOS) conceived of as dark. There are two possible ways to define ‘dark’ in this context. The first is that communication is dark because it either has limited distribution, is not open to all users (closed groups are a case example) or hidden. The second definition, linked as a result of the first, is the way that communication via these means is interpreted and understood. Dark social spaces disrupt the accepted top-down flow by the ‘gazing elite’ (data aggregators including social media), but anxious users might need to strain to notice what is out there, and this in turn destabilises one’s reception of the scene. In an environment where surveillance technologies are proliferating, this article examines contemporary, dark, interconnected, and interactive communications for the entangled affordances that might be brought to bear. A provocation is that resistance through counterveillance or “sousveillance” is one possibility. An alternative (or addition) is retreating to or building ‘dark’ spaces that are less surveilled and (perhaps counterintuitively) less fearful. This article considers critically the notion of dark social online spaces via four broad socio-technical concerns connected to the big social media services that have helped increase a tendency for fearful anxiety produced by surveillance and the perceived implications for personal privacy. It also shines light on the aspect of darkness where some users are spurred to actively seek alternative, dark social online spaces. Since the 1970s, public-key cryptosystems typically preserved security for websites, emails, and sensitive health, government, and military data, but this is now reduced (Williams). We have seen such systems exploited via cyberattacks and misappropriated data acquired by affiliations such as Facebook-Cambridge Analytica for targeted political advertising during the 2016 US elections. Via the notion of “parasitic strategies”, such events can be described as news/information hacks “whose attack vectors target a system’s weak points with the help of specific strategies” (von Nordheim and Kleinen-von Königslöw, 88). In accord with Wilson and Serisier’s arguments (178), emerging technologies facilitate rapid data sharing, collection, storage, and processing wherein subsequent “outcomes are unpredictable”. This would also include the effect of acquiescence. In regard to our digital devices, for some, being watched overtly—through cameras encased in toys, computers, and closed-circuit television (CCTV) to digital street ads that determine the resonance of human emotions in public places including bus stops, malls, and train stations—is becoming normalised (McStay, Emotional AI). It might appear that consumers immersed within this Internet of Things (IoT) are themselves comfortable interacting with devices that record sound and capture images for easy analysis and distribution across the communications networks. A counter-claim is that mainstream social media corporations have cultivated a sense of digital resignation “produced when people desire to control the information digital entities have about them but feel unable to do so” (Draper and Turow, 1824). Careful consumers’ trust in mainstream media is waning, with readers observing a strong presence of big media players in the industry and are carefully picking their publications and public intellectuals to follow (Mahmood, 6). A number now also avoid the mainstream internet in favour of alternate dark sites. This is done by users with “varying backgrounds, motivations and participation behaviours that may be idiosyncratic (as they are rooted in the respective person’s biography and circumstance)” (Quandt, 42). By way of connection with dark internet studies via Biddle et al. (1; see also Lasica), the “darknet” is a collection of networks and technologies used to share digital content … not a separate physical network but an application and protocol layer riding on existing networks. Examples of darknets are peer-to-peer file sharing, CD and DVD copying, and key or password sharing on email and newsgroups. As we note from the quote above, the “dark web” uses existing public and private networks that facilitate communication via the Internet. Gehl (1220; see also Gehl and McKelvey) has detailed that this includes “hidden sites that end in ‘.onion’ or ‘.i2p’ or other Top-Level Domain names only available through modified browsers or special software. Accessing I2P sites requires a special routing program ... . Accessing .onion sites requires Tor [The Onion Router]”. For some, this gives rise to social anxiety, read here as stemming from that which is not known, and an exaggerated sense of danger, which makes fight or flight seem the only options. This is often justified or exacerbated by the changing media and communication landscape and depicted in popular documentaries such as The Social Dilemma or The Great Hack, which affect public opinion on the unknown aspects of internet spaces and the uses of personal data. The question for this article remains whether the fear of the dark is justified. Consider that most often one will choose to make one’s intimate bedroom space dark in order to have a good night’s rest. We might pleasurably escape into a cinema’s darkness for the stories told therein, or walk along a beach at night enjoying unseen breezes. Most do not avoid these experiences, choosing to actively seek them out. Drawing this thread, then, is the case made here that agency can also be found in the dark by resisting socio-political structural harms. 1. Digital Futures and Anxiety of the Dark Fear of the darkI have a constant fear that something's always nearFear of the darkFear of the darkI have a phobia that someone's always there In the lyrics to the song “Fear of the Dark” (1992) by British heavy metal group Iron Maiden is a sense that that which is unknown and unseen causes fear and anxiety. Holding a fear of the dark is not unusual and varies in degree for adults as it does for children (Fellous and Arbib). Such anxiety connected to the dark does not always concern darkness itself. It can also be a concern for the possible or imagined dangers that are concealed by the darkness itself as a result of cognitive-emotional interactions (McDonald, 16). Extending this claim is this article’s non-binary assertion that while for some technology and what it can do is frequently misunderstood and shunned as a result, for others who embrace the possibilities and actively take it on it is learning by attentively partaking. Mistakes, solecism, and frustrations are part of the process. Such conceptual theorising falls along a continuum of thinking. Global interconnectivity of communications networks has certainly led to consequent concerns (Turkle Alone Together). Much focus for anxiety has been on the impact upon social and individual inner lives, levels of media concentration, and power over and commercialisation of the internet. Of specific note is that increasing commercial media influence—such as Facebook and its acquisition of WhatsApp, Oculus VR, Instagram, CRTL-labs (translating movements and neural impulses into digital signals), LiveRail (video advertising technology), Chainspace (Blockchain)—regularly changes the overall dynamics of the online environment (Turow and Kavanaugh). This provocation was born out recently when Facebook disrupted the delivery of news to Australian audiences via its service. Mainstream social online spaces (SOS) are platforms which provide more than the delivery of media alone and have been conceptualised predominantly in a binary light. On the one hand, they can be depicted as tools for the common good of society through notional widespread access and as places for civic participation and discussion, identity expression, education, and community formation (Turkle; Bruns; Cinque and Brown; Jenkins). This end of the continuum of thinking about SOS seems set hard against the view that SOS are operating as businesses with strategies that manipulate consumers to generate revenue through advertising, data, venture capital for advanced research and development, and company profit, on the other hand. In between the two polar ends of this continuum are the range of other possibilities, the shades of grey, that add contemporary nuance to understanding SOS in regard to what they facilitate, what the various implications might be, and for whom. By way of a brief summary, anxiety of the dark is steeped in the practices of privacy-invasive social media giants such as Facebook and its ancillary companies. Second are the advertising technology companies, surveillance contractors, and intelligence agencies that collect and monitor our actions and related data; as well as the increased ease of use and interoperability brought about by Web 2.0 that has seen a disconnection between technological infrastructure and social connection that acts to limit user permissions and online affordances. Third are concerns for the negative effects associated with depressed mental health and wellbeing caused by “psychologically damaging social networks”, through sleep loss, anxiety, poor body image, real world relationships, and the fear of missing out (FOMO; Royal Society for Public Health (UK) and the Young Health Movement). Here the harms are both individual and societal. Fourth is the intended acceleration toward post-quantum IoT (Fernández-Caramés), as quantum computing’s digital components are continually being miniaturised. This is coupled with advances in electrical battery capacity and interconnected telecommunications infrastructures. The result of such is that the ontogenetic capacity of the powerfully advanced network/s affords supralevel surveillance. What this means is that through devices and the services that they provide, individuals’ data is commodified (Neff and Nafus; Nissenbaum and Patterson). Personal data is enmeshed in ‘things’ requiring that the decisions that are both overt, subtle, and/or hidden (dark) are scrutinised for the various ways they shape social norms and create consequences for public discourse, cultural production, and the fabric of society (Gillespie). Data and personal information are retrievable from devices, sharable in SOS, and potentially exposed across networks. For these reasons, some have chosen to go dark by being “off the grid”, judiciously selecting their means of communications and their ‘friends’ carefully. 2. Is There Room for Privacy Any More When Everyone in SOS Is Watching? An interesting turn comes through counterarguments against overarching institutional surveillance that underscore the uses of technologies to watch the watchers. This involves a practice of counter-surveillance whereby technologies are tools of resistance to go ‘dark’ and are used by political activists in protest situations for both communication and avoiding surveillance. This is not new and has long existed in an increasingly dispersed media landscape (Cinque, Changing Media Landscapes). For example, counter-surveillance video footage has been accessed and made available via live-streaming channels, with commentary in SOS augmenting networking possibilities for niche interest groups or micropublics (Wilson and Serisier, 178). A further example is the Wordpress site Fitwatch, appealing for an end to what the site claims are issues associated with police surveillance (fitwatch.org.uk and endpolicesurveillance.wordpress.com). Users of these sites are called to post police officers’ identity numbers and photographs in an attempt to identify “cops” that might act to “misuse” UK Anti-terrorism legislation against activists during legitimate protests. Others that might be interested in doing their own “monitoring” are invited to reach out to identified personal email addresses or other private (dark) messaging software and application services such as Telegram (freeware and cross-platform). In their work on surveillance, Mann and Ferenbok (18) propose that there is an increase in “complex constructs between power and the practices of seeing, looking, and watching/sensing in a networked culture mediated by mobile/portable/wearable computing devices and technologies”. By way of critical definition, Mann and Ferenbok (25) clarify that “where the viewer is in a position of power over the subject, this is considered surveillance, but where the viewer is in a lower position of power, this is considered sousveillance”. It is the aspect of sousveillance that is empowering to those using dark SOS. One might consider that not all surveillance is “bad” nor institutionalised. It is neither overtly nor formally regulated—as yet. Like most technologies, many of the surveillant technologies are value-neutral until applied towards specific uses, according to Mann and Ferenbok (18). But this is part of the ‘grey area’ for understanding the impact of dark SOS in regard to which actors or what nations are developing tools for surveillance, where access and control lies, and with what effects into the future. 3. Big Brother Watches, So What Are the Alternatives: Whither the Gazing Elite in Dark SOS? By way of conceptual genealogy, consideration of contemporary perceptions of surveillance in a visually networked society (Cinque, Changing Media Landscapes) might be usefully explored through a revisitation of Jeremy Bentham’s panopticon, applied here as a metaphor for contemporary surveillance. Arguably, this is a foundational theoretical model for integrated methods of social control (Foucault, Surveiller et Punir, 192-211), realised in the “panopticon” (prison) in 1787 by Jeremy Bentham (Bentham and Božovič, 29-95) during a period of social reformation aimed at the improvement of the individual. Like the power for social control over the incarcerated in a panopticon, police power, in order that it be effectively exercised, “had to be given the instrument of permanent, exhaustive, omnipresent surveillance, capable of making all visible … like a faceless gaze that transformed the whole social body into a field of perception” (Foucault, Surveiller et Punir, 213–4). In grappling with the impact of SOS for the individual and the collective in post-digital times, we can trace out these early ruminations on the complex documentary organisation through state-controlled apparatuses (such as inspectors and paid observers including “secret agents”) via Foucault (Surveiller et Punir, 214; Subject and Power, 326-7) for comparison to commercial operators like Facebook. Today, artificial intelligence (AI), facial recognition technology (FRT), and closed-circuit television (CCTV) for video surveillance are used for social control of appropriate behaviours. Exemplified by governments and the private sector is the use of combined technologies to maintain social order, from ensuring citizens cross the street only on green lights, to putting rubbish in the correct recycling bin or be publicly shamed, to making cashless payments in stores. The actions see advantages for individual and collective safety, sustainability, and convenience, but also register forms of behaviour and attitudes with predictive capacities. This gives rise to suspicions about a permanent account of individuals’ behaviour over time. Returning to Foucault (Surveiller et Punir, 135), the impact of this finds a dissociation of power from the individual, whereby they become unwittingly impelled into pre-existing social structures, leading to a ‘normalisation’ and acceptance of such systems. If we are talking about the dark, anxiety is key for a Ministry of SOS. Following Foucault again (Subject and Power, 326-7), there is the potential for a crawling, creeping governance that was once distinct but is itself increasingly hidden and growing. A blanket call for some form of ongoing scrutiny of such proliferating powers might be warranted, but with it comes regulation that, while offering certain rights and protections, is not without consequences. For their part, a number of SOS platforms had little to no moderation for explicit content prior to December 2018, and in terms of power, notwithstanding important anxiety connected to arguments that children and the vulnerable need protections from those that would seek to take advantage, this was a crucial aspect of community building and self-expression that resulted in this freedom of expression. In unearthing the extent that individuals are empowered arising from the capacity to post sexual self-images, Tiidenberg ("Bringing Sexy Back") considered that through dark SOS (read here as unregulated) some users could work in opposition to the mainstream consumer culture that provides select and limited representations of bodies and their sexualities. This links directly to Mondin’s exploration of the abundance of queer and feminist pornography on dark SOS as a “counterpolitics of visibility” (288). This work resulted in a reasoned claim that the technological structure of dark SOS created a highly political and affective social space that users valued. What also needs to be underscored is that many users also believed that such a space could not be replicated on other mainstream SOS because of the differences in architecture and social norms. Cho (47) worked with this theory to claim that dark SOS are modern-day examples in a history of queer individuals having to rely on “underground economies of expression and relation”. Discussions such as these complicate what dark SOS might now become in the face of ‘adult’ content moderation and emerging tracking technologies to close sites or locate individuals that transgress social norms. Further, broader questions are raised about how content moderation fits in with the public space conceptualisations of SOS more generally. Increasingly, “there is an app for that” where being able to identify the poster of an image or an author of an unknown text is seen as crucial. While there is presently no standard approach, models for combining instance-based and profile-based features such as SVM for determining authorship attribution are in development, with the result that potentially far less content will remain hidden in the future (Bacciu et al.). 4. There’s Nothing New under the Sun (Ecclesiastes 1:9) For some, “[the] high hopes regarding the positive impact of the Internet and digital participation in civic society have faded” (Schwarzenegger, 99). My participant observation over some years in various SOS, however, finds that critical concern has always existed. Views move along the spectrum of thinking from deep scepticisms (Stoll, Silicon Snake Oil) to wondrous techo-utopian promises (Negroponte, Being Digital). Indeed, concerns about the (then) new technologies of wireless broadcasting can be compared with today’s anxiety over the possible effects of the internet and SOS. Inglis (7) recalls, here, too, were fears that humanity was tampering with some dangerous force; might wireless wave be causing thunderstorms, droughts, floods? Sterility or strokes? Such anxieties soon evaporated; but a sense of mystery might stay longer with evangelists for broadcasting than with a laity who soon took wireless for granted and settled down to enjoy the products of a process they need not understand. As the analogy above makes clear, just as audiences came to use ‘the wireless’ and later the internet regularly, it is reasonable to argue that dark SOS will also gain widespread understanding and find greater acceptance. Dark social spaces are simply the recent development of internet connectivity and communication more broadly. The dark SOS afford choice to be connected beyond mainstream offerings, which some users avoid for their perceived manipulation of content and user both. As part of the wider array of dark web services, the resilience of dark social spaces is reinforced by the proliferation of users as opposed to decentralised replication. Virtual Private Networks (VPNs) can be used for anonymity in parallel to TOR access, but they guarantee only anonymity to the client. A VPN cannot guarantee anonymity to the server or the internet service provider (ISP). While users may use pseudonyms rather than actual names as seen on Facebook and other SOS, users continue to take to the virtual spaces they inhabit their off-line, ‘real’ foibles, problems, and idiosyncrasies (Chenault). To varying degrees, however, people also take their best intentions to their interactions in the dark. The hyper-efficient tools now deployed can intensify this, which is the great advantage attracting some users. In balance, however, in regard to online information access and dissemination, critical examination of what is in the public’s interest, and whether content should be regulated or controlled versus allowing a free flow of information where users self-regulate their online behaviour, is fraught. O’Loughlin (604) was one of the first to claim that there will be voluntary loss through negative liberty or freedom from (freedom from unwanted information or influence) and an increase in positive liberty or freedom to (freedom to read or say anything); hence, freedom from surveillance and interference is a kind of negative liberty, consistent with both libertarianism and liberalism. Conclusion The early adopters of initial iterations of SOS were hopeful and liberal (utopian) in their beliefs about universality and ‘free’ spaces of open communication between like-minded others. This was a way of virtual networking using a visual motivation (led by images, text, and sounds) for consequent interaction with others (Cinque, Visual Networking). The structural transformation of the public sphere in a Habermasian sense—and now found in SOS and their darker, hidden or closed social spaces that might ensure a counterbalance to the power of those with influence—towards all having equal access to platforms for presenting their views, and doing so respectfully, is as ever problematised. Broadly, this is no more so, however, than for mainstream SOS or for communicating in the world. References Bacciu, Andrea, Massimo La Morgia, Alessandro Mei, Eugenio Nerio Nemmi, Valerio Neri, and Julinda Stefa. “Cross-Domain Authorship Attribution Combining Instance Based and Profile-Based Features.” CLEF (Working Notes). Lugano, Switzerland, 9-12 Sep. 2019. Bentham, Jeremy, and Miran Božovič. The Panopticon Writings. London: Verso Trade, 1995. Biddle, Peter, et al. “The Darknet and the Future of Content Distribution.” Proceedings of the 2002 ACM Workshop on Digital Rights Management. Vol. 6. Washington DC, 2002. Bruns, Axel. Blogs, Wikipedia, Second Life, and Beyond: From Production to Produsage. New York: Peter Lang, 2008. Chenault, Brittney G. “Developing Personal and Emotional Relationships via Computer-Mediated Communication.” CMC Magazine 5.5 (1998). 1 May 2020 <http://www.december.com/cmc/mag/1998/may/chenault.html>. Cho, Alexander. “Queer Reverb: Tumblr, Affect, Time.” Networked Affect. Eds. K. Hillis, S. Paasonen, and M. Petit. Cambridge, Mass.: MIT Press, 2015: 43-58. Cinque, Toija. Changing Media Landscapes: Visual Networking. London: Oxford UP, 2015. ———. “Visual Networking: Australia's Media Landscape.” Global Media Journal: Australian Edition 6.1 (2012): 1-8. Cinque, Toija, and Adam Brown. “Educating Generation Next: Screen Media Use, Digital Competencies, and Tertiary Education.” Digital Culture & Education 7.1 (2015). Draper, Nora A., and Joseph Turow. “The Corporate Cultivation of Digital Resignation.” New Media & Society 21.8 (2019): 1824-1839. Fellous, Jean-Marc, and Michael A. Arbib, eds. Who Needs Emotions? The Brain Meets the Robot. New York: Oxford UP, 2005. Fernández-Caramés, Tiago M. “From Pre-Quantum to Post-Quantum IoT Security: A Survey on Quantum-Resistant Cryptosystems for the Internet of Things.” IEEE Internet of Things Journal 7.7 (2019): 6457-6480. Foucault, Michel. Surveiller et Punir: Naissance de la Prison [Discipline and Punish—The Birth of The Prison]. Trans. Alan Sheridan. New York: Random House, 1977. Foucault, Michel. “The Subject and Power.” Michel Foucault: Power, the Essential Works of Michel Foucault 1954–1984. Vol. 3. Trans. R. Hurley and others. Ed. J.D. Faubion. London: Penguin, 2001. Gehl, Robert W. Weaving the Dark Web: Legitimacy on Freenet, Tor, and I2P. Cambridge, Massachusetts: MIT Press, 2018. Gehl, Robert, and Fenwick McKelvey. “Bugging Out: Darknets as Parasites of Large-Scale Media Objects.” Media, Culture & Society 41.2 (2019): 219-235. Gillespie, Tarleton. Custodians of the Internet: Platforms, Content Moderation, and the Hidden Decisions That Shape Social Media. London: Yale UP, 2018. Habermas, Jürgen. The Structural Transformation of the Public Sphere: An Inquiry into a Category of Bourgeois Society. Trans. Thomas Burger with the assistance of Frederick Lawrence. Cambridge, Mass.: MIT Press, 1989. Inglis, Ken S. This Is the ABC: The Australian Broadcasting Commission 1932–1983. Melbourne: Melbourne UP, 1983. Iron Maiden. “Fear of the Dark.” London: EMI, 1992. Jenkins, Henry. Convergence Culture: Where Old and New Media Collide. New York: New York UP, 2006. Lasica, J. D. Darknet: Hollywood’s War against the Digital Generation. New York: John Wiley and Sons, 2005. Mahmood, Mimrah. “Australia's Evolving Media Landscape.” 13 Apr. 2021 <https://www.meltwater.com/en/resources/australias-evolving-media-landscape>. Mann, Steve, and Joseph Ferenbok. “New Media and the Power Politics of Sousveillance in a Surveillance-Dominated World.” Surveillance & Society 11.1/2 (2013): 18-34. McDonald, Alexander J. “Cortical Pathways to the Mammalian Amygdala.” Progress in Neurobiology 55.3 (1998): 257-332. McStay, Andrew. Emotional AI: The Rise of Empathic Media. London: Sage, 2018. Mondin, Alessandra. “‘Tumblr Mostly, Great Empowering Images’: Blogging, Reblogging and Scrolling Feminist, Queer and BDSM Desires.” Journal of Gender Studies 26.3 (2017): 282-292. Neff, Gina, and Dawn Nafus. Self-Tracking. Cambridge, Mass.: MIT Press, 2016. Negroponte, Nicholas. Being Digital. New York: Alfred A. Knopf, 1995. Nissenbaum, Helen, and Heather Patterson. “Biosensing in Context: Health Privacy in a Connected World.” Quantified: Biosensing Technologies in Everyday Life. Ed. Dawn Nafus. 2016. 68-79. O’Loughlin, Ben. “The Political Implications of Digital Innovations.” Information, Communication and Society 4.4 (2001): 595–614. Quandt, Thorsten. “Dark Participation.” Media and Communication 6.4 (2018): 36-48. Royal Society for Public Health (UK) and the Young Health Movement. “#Statusofmind.” 2017. 2 Apr. 2021 <https://www.rsph.org.uk/our-work/campaigns/status-of-mind.html>. Statista. “Number of IoT devices 2015-2025.” 27 Nov. 2020 <https://www.statista.com/statistics/471264/iot-number-of-connected-devices-worldwide/>. Schwarzenegger, Christian. “Communities of Darkness? Users and Uses of Anti-System Alternative Media between Audience and Community.” Media and Communication 9.1 (2021): 99-109. Stoll, Clifford. Silicon Snake Oil: Second Thoughts on the Information Highway. Anchor, 1995. Tiidenberg, Katrin. “Bringing Sexy Back: Reclaiming the Body Aesthetic via Self-Shooting.” Cyberpsychology: Journal of Psychosocial Research on Cyberspace 8.1 (2014). The Great Hack. Dirs. Karim Amer, Jehane Noujaim. Netflix, 2019. The Social Dilemma. Dir. Jeff Orlowski. Netflix, 2020. Turkle, Sherry. The Second Self: Computers and the Human Spirit. Cambridge, Mass.: MIT Press, 2005. Turkle, Sherry. Alone Together: Why We Expect More from Technology and Less from Each Other. UK: Hachette, 2017. Turow, Joseph, and Andrea L. Kavanaugh, eds. The Wired Homestead: An MIT Press Sourcebook on the Internet and the Family. Cambridge, Mass.: MIT Press, 2003. Von Nordheim, Gerret, and Katharina Kleinen-von Königslöw. “Uninvited Dinner Guests: A Theoretical Perspective on the Antagonists of Journalism Based on Serres’ Parasite.” Media and Communication 9.1 (2021): 88-98. Williams, Chris K. “Configuring Enterprise Public Key Infrastructures to Permit Integrated Deployment of Signature, Encryption and Access Control Systems.” MILCOM 2005-2005 IEEE Military Communications Conference. IEEE, 2005. Wilson, Dean, and Tanya Serisier. “Video Activism and the Ambiguities of Counter-Surveillance.” Surveillance & Society 8.2 (2010): 166-180.

Introduction Children are not only born digital, they are fashioned toward a lifestyle that needs them to be digital all the time (Palfrey and Gasser). They click, tap, save, circulate, download, and upload the texts of their lives, their friends’ lives, and the anonymous lives of the people that surround them. They are socialised as Internet consumers ready to participate in digital services targeted to them as they age such as Snapchat, Instagram, and YouTube. But they are also fashioned as producers, whereby their lives are sold as content on these same markets. As commodities, the minutiae of their lives become the fodder for online circulation. Paradoxically, we also celebrate these digital behaviours as a means to express identity. Personal profile-building for adults is considered agency-building (Beer and Burrows), and as a consequence, we praise children for mimicking these acts of adult lifestyle. This article reflects on the Kids, Creative Storyworlds, and Wearables project, which involved an ethnographic study with five young children (ages 4-7), who were asked to share their autobiographical stories, creative self-narrations, and predictions about their future mediated lives (Atkins et al.). For this case study, we focus on commercialised forms of children’s automedia, and we compare discussions we had with 6-year old Cayden, a child we met in the study who expresses the desire to make himself famous online, with videos of Jacob, a child vlogger on YouTube’s Kinder Playtime, who clearly influences children like Cayden. We argue that child social influencers need consideration both as autobiographical agents and as child subjects requiring a sheltered approach to their online lives.Automedia Automedia is an emergent genre of autobiography (Smith and Watson Reading 190; “Virtually Me” 78). Broadcasting one’s life online takes many forms (Kennedy “Vulnerability”). Ümit Kennedy argues “Vlogging on YouTube is a contemporary form of autobiography in which individuals engage in a process of documenting their life on a daily or weekly basis and, in doing so, construct[ing] their identity online” (“Exploring”). Sidonie Smith and Julia Watson write that “visual and digital modes are projecting and circulating not just new subjects but new notions of subjectivity through the effects of automediality” with the result that “the archive of the self in time, in space and in relation expands and is fundamentally reorganized” (Reading 190). Emma Maguire addresses what online texts “tell us about cultural understandings of selfhood and what it means to communicate ‘real’ life through media” naming one tool, “automedia”. Further, Julie Rak calls on scholars “to rethink ‘life’ and ‘writing’ as automedia” to further “characterize the enactment of a personal life story in a new media environment.” We define automedia as a genre that involves the practices of creating, performing, sharing, circulating, and (at times) preserving one’s digital life narrative meant for multiple publics. Automedia revises identity formation, embodiment, or corporealities in acts of self-creation (Brophy and Hladki 4). Automedia also emphasizes circulation. As shared digital life texts now circulate through the behaviours of other human subjects, and automatically via algorithms in data assemblages, we contend that automediality currently involves a measure of relinquishing control over perpetually evolving mediatised environments. One cannot control how a shared life narrative will meet a public in the future, which is a revised way of thinking about autobiography. For the sake of this paper, we argue that children’s automedia ought to be considered a creative, autobiographical act, in order to afford child authors who create them the consideration they deserve as agents, now and in the future. Automedial practices often begin when children receive access to a device. The need for a distraction activity is often the reason parents hand a young child a smartphone, iPad, or even a wearable camera (Nansen). Mirroring the lives of parents, children aspire to share representations of their own personal lives in pursuit of social capital. They are often encouraged to use technologies and apps as adults do–to track aspects of self, broadcast life stories and eventually “live share” them—effectively creating, performing, sharing, and at times, seeking to preserve a public life narrative. With this practice, society inculcates children into spheres of device ubiquity, “socializing them to a future digital lifestyle that will involve always carrying a computer in some form” (Atkins et al. 49). Consequently, their representations become inculcated in larger media assemblages. Writing about toddlers, Nansen describes how the “archiving, circulation and reception of these images speaks to larger assemblages of media in which software protocols and algorithms are increasingly embedded in and help to configure everyday life (e.g. Chun; Gillespie), including young children’s media lives (Ito)” (Nansen). Children, like adult citizens, are increasingly faced with choices “not structured by their own preferences but by the economic imperatives of the private corporations that have recently come to dominate the internet” (Andrejevic). Recent studies have shown that for children and youth in the digital age, Internet fame, often characterized by brand endorsements, is a major aspiration (Uhls and Greenfield, 2). However, despite the ambition to participate as celebrity digital selves, children are also mired in the calls to shield them from exposure to screens through institutions that label these activities detrimental. In many countries, digital “protections” are outlined by privacy commissioners and federal or provincial/state statutes, (e.g. Office of the Privacy Commissioner of Canada). Consequently, children are often caught in a paradox that defines them either as literate digital agents able to compose or participate with their online selves, or as subjectified wards caught up in commercial practices that exploit their lives for commercial gain.Kids, Creative Storyworlds and Wearables ProjectBoth academic and popular cultural critics continually discuss the future but rarely directly engage the people who will be empowered (or subjugated) by it as young adults in twenty years. To address children’s lack of agency in these discussions, we launched the Kids, Creative Storyworlds and Wearables project to bring children into a dialogue about their own digital futures. Much has been written on childhood agency and participation in culture and mediated culture from the discipline of sociology (James and James; Jenks; Jenkins). In previous work, we addressed the perspective of child autobiographical feature filmmakers to explore issues of creative agency and consent when adult gatekeepers facilitate children in film production (Pedersen and Aspevig “My Eyes”; Pedersen and Aspevig “Swept”). Drawing on that previous work, this project concentrates on children’s automediated lives and the many unique concerns that materialize with digital identity-building. Children are categorised as a vulnerable demographic group necessitating special policy and legislation, but the lives they project as children will eventually become subsumed in their own adult lives, which will almost certainly be treated and mediated in a much different manner in the future. We focused on this landscape, and sought to query the children on their futures, also considering the issues that arise when adult gatekeepers get involved with child social media influencers. In the Storyworlds ethnographic study, children were given a wearable toy, a Vtech smartwatch called Kidizoom, to use over a month’s timeframe to serve as a focal point for ethnographic conversations. The Kidizoom watch enables children to take photos and videos, which are uploaded to a web interface. Before we gave them the tech, we asked them questions about their lives, including What are machines going to be like in the future? Can you imagine yourself wearing a certain kind of computer? Can you tell/draw a story about that? If you could wear a computer that gave you a super power, what would it be? Can you use your imagination to think of a person in a story who would use technology? In answering, many of them drew autobiographical drawings of technical inventions, and cast themselves in the images. We were particularly struck by the comments made by one participant, Cayden (pseudonym), a 6-year-old boy, and the stories he told us about himself and his aspirations. He expressed the desire to host a YouTube channel about his life, his activities, and the wearable technologies his family already owned (e.g. a GroPro camera) and the one we gave him, the Kidizoom smartwatch. He talked about how he would be proud to publically broadcast his own videos on YouTube, and about the role he had been allowed to play in the making of videos about his life (that were not broadcast). To contextualize Cayden’s commentary and his automedial aspirations, we extended our study to explore child social media influencers who broadcast components of their personal lives for the deliberate purpose of popularity and the financial gain of their parents.We selected the videos of Jacob, a child vlogger because we judged them to be representative of the kinds that Cayden watched. Jacob reviews toys through “unboxing videos,” a genre in which a child tells an online audience her or his personal experiences using new toys in regular, short videos on a social media site. Jacob appears on a YouTube channel called Kinder Playtime, which appears to be a parent-run channel that states that, “We enjoy doing these things while playing with our kids: Jacob, Emily, and Chloe” (see Figure 1). In one particular video, Jacob reviews the Kidizoom watch, serving as a child influencer for the product. By understanding Jacob’s performance as agent-driven automedia, as well as being a commercialised, mediatised form of advertising, we get a clearer picture of how the children in the study are coming to terms with their own digital selfhood and the realisation that circulated, life-exposing videos are the expectation in this context.Children are implicated in a range of ways through “family” influencer and toy unboxing videos, which are emergent entertainment industries (Abidin 1; Nansen and Nicoll; Craig and Cunningham 77). In particular, unboxing videos do impact child viewers, especially when children host them. Jackie Marsh emphasizes the digital literacy practices at play here that co-construct viewers as “cyberflâneur[s]” and she states that “this mode of cultural transmission is a growing feature of online practices for this age group” (369). Her stress, however, is on how the child viewer enjoys “the vicarious pleasure he or she may get from viewing the playing of another child with the toy” (376). Marsh writes that her study subject, a child called “Gareth”, “was not interested in being made visible to EvanHD [a child celebrity social media influencer] or other online peers, but was content to consume” the unboxing videos. The concept of the cyberflâneur, then, is fitting as a mediatising co-constituting process of identity-building within discourses of consumerism. However, in our study, the children, and especially Cayden, also expressed the desire to create, host, and circulate their own videos that broadcast their lives, also demonstrating awareness that videos are valorised in their social circles. Child viewers watch famous children perform consumer-identities to create an aura of influence, but viewers simultaneously aspire to become influencers using automedial performances, in essence, becoming products, themselves. Jacob, Automedial Subjects and Social Media InfluencersJacob is a vlogger on YouTube whose videos can garner millions of views, suggesting that he is also an influencer. In one video, he appears to be around the age of six as he proudly sits with folded hands, bright eyes, and a beaming, but partly toothless smile (see Figure 2). He says, “Welcome to Kinder Playtime! Today we have the Kidi Zoom Smartwatch DX. It’s from VTech” (Kinder Playtime). We see the Kidi Zoom unboxed and then depicted in stylized animations amid snippets of Jacob’s smiling face. The voice and hands of a faceless parent guide Jacob as he uses his new wearable toy. We listen to both parent and child describe numerous features for recording and enhancing the wearer’s daily habits (e.g. calculator, calendar, fitness games), and his dad tells him it has a pedometer “which tracks your steps” (Kinder Playtime). But the watch is also used by Jacob to mediate himself and his world. We see that Jacob takes pictures of himself on the tiny watch screen as he acts silly for the camera. He also uses the watch to take personal videos of his mother and sister in his home. The video ends with his father mentioning bedtime, which prompts a “thank you” to VTech for giving him the watch, and a cheerful “Bye!” from Jacob (Kinder Playtime). Figure 1: Screenshot of Kinder Playtime YouTube channel, About page Figure 2: Screenshot of “Jacob,” a child vlogger at Kinder Playtime We chose Jacob for three reasons. First, he is the same age as the children in the Storyworlds study. Second, he reviews the smart watch artifact that we gave to the study children, so there was a common use of automedia technology. Third, Jacob’s parents were involved with his broadcasts, and we wanted to work within the boundaries of parent-sanctioned practices. However, we also felt that his playful approach was a good example of how social media influence overlaps with automediality. Jacob is a labourer trading his public self-representations in exchange for free products and revenue earned through the monetisation of his content on YouTube. It appears that much of what Jacob says is scripted, particularly the promotional statements, like, “Today we have the Kidizoom Smartwatch DX. It’s from VTech. It’s the smartest watch for kids” (Kinder Playtime). Importantly, as an automedial subject Jacob reveals aspects of his self and his identity, in the manner of many child vloggers on public social media sites. His product reviews are contextualised within a commoditised space that provides him a means for the public performance of his self, which, via YouTube, has the potential to reach an enormous audience. YouTube claims to have “over a billion users—almost one-third of all people on the Internet—and every day people watch hundreds of millions of hours on YouTube and generate billions of views” (YouTube). Significantly, he is not only filmed by others, Jacob is also a creative practitioner, as Cayden aspired to become. Jacob uses high-tech toys, in this case, a new wearable technology for self-compositions (the smart watch), to record himself, friends, family or simply the goings-on around him. Strapped to his wrist, the watch toy lets him play at being watched, at being quantified and at recording the life stories of others, or constructing automediated creations for himself, which he may upload to numerous social media sites. This is the start of his online automediated life, which will be increasingly under his ownership as he ages. To greater or lesser degrees, he will later be able to curate, add to, and remediate his body of automedia, including his digital past. Kennedy points out that “people are using YouTube as a transformative tool, and mirror, to document, construct, and present their identity online” (“Exploring”). Her focus is on adult vloggers who consent to their activities. Jacob’s automedia is constructed collaboratively with his parents, and it is unclear how much awareness he has of himself as an automedia creator. However, if we don’t afford Jacob the same consideration as we afford adult autobiographers, that the depiction of his life is his own, we will reduce his identity performance to pure artifice or advertisement. The questions Jacob’s videos raise around agency, consent, and creativity are important here. Sidonie Smith asks “Can there be a free, agentic space; and if so, where in the world can it be found?” (Manifesto 188). How much agency does Jacob have? Is there a liberating aspect in the act of putting personal technology into the hands of a child who can record his life, himself? And finally, how would an adult Jacob feel about his childhood self advertising these products online? Is this really automediality if Jacob does not fully understand what it means to publicly tell a mediated life story?These queries lead to concerns over child social media influence with regard to legal protection, marketing ethics, and user consent. The rise of “fan marketing” presents a nexus of stealth marketing to children by other children. Stealth marketing involves participants, in this case, fans, who do not know they are involved in an advertising scheme. For instance, the popular Minecon Minecraft conference event sessions have pushed their audience to develop the skills to become advocates and advertisers of their products, for example by showing audiences how to build a YouTube channel and sharing tips for growing a community. Targeting children in marketing ploys seems insidious. Marketing analyst Sandy Fleisher describes the value of outsourcing marketing to fan labourers:while Grand Theft Auto spent $120 million on marketing its latest release, Minecraft fans are being taught how to create and market promotional content themselves. One [example] is Minecraft YouTuber, SkydoesMinecraft. His nearly 7 million strong YouTube army, almost as big as Justin Bieber’s, means his daily videos enjoy a lot of views; 1,419,734,267 to be precise. While concerns about meaningful consent that practices like this raise have led some government bodies, and consumer and child protection groups to advocate restrictions for children, other critics have questioned the limits placed on children’s free expression by such restrictions. Tech commentator Larry Magid has written that, “In the interest of protecting children, we sometimes deny them the right to access material and express themselves.” Meghan M. Sweeney notes that “the surge in collaborative web models and the emphasis on interactivity—frequently termed Web 2.0—has meant that children are not merely targets of global media organizations” but have “multiple opportunities to be active, critical, and resistant producers”...and ”may be active agents in the production and dissemination of information” (68). Nevertheless, writes Sweeney, “corporate entities can have restrictive effects on consumers” (68), by for example, limiting imaginative play to the choices offered on a Disney website, or limiting imaginative topics to commercial products (toys, video games etc), as in YouTube review videos. Automedia is an important site from which to consider young children’s online practices in public spheres. Jacob’s performance is indeed meant to influence the choice to buy a toy, but it is also meant to influence others in knowing Jacob as an identity. He means to share and circulate his self. Julie Rak recalls Paul John Eakin’s claims about life-writing that the “process does not even occur at the level of writing, but at the level of living, so that identity formation is the result of narrative-building.” We view Jacob’s performance along these lines. Kinder Playtime offers him a constrained, parent-sanctioned (albeit commercialised) space for role-playing, a practice bound up with identity-formation in the life of most children. To think through the legality of recognising Jacob’s automedial content as his life, Rak is also useful: “In Eakin’s work in particular, we can see evidence of John Locke’s contention that identity is the expression of consciousness which is continuous over time, but that identity is also a product, one’s own property which is a legal entity”. We have argued that children are often caught in the paradox that defines them either as literate digital creators composing and circulating their online selves or as subjectified personas caught up in commercial advertising practices that use their lives for commercial gain. However, through close observation of individual children, one who we met and questioned in our study, Cayden, the other who we met through his mediated, commercialized, and circulated online persona, Jacob, we argue that child social influencers need consideration as autobiographical agents expressing themselves through automediality. As children create, edit, and grow digital traces of their lives and selves, how these texts are framed becomes increasingly important, in part because their future adult selves have such a stake in the matter: they are being formed through automedia. Moreover, these children’s coming of age may bring legal questions about the ownership of their automedial products such as YouTube videos, an enduring legacy they are leaving behind for their adult selves. Crucially, if we reduce identity performances such as unboxing, toy review videos, and other forms of children’s fan marketing to pure advertisement, we cannot afford Jacob and other child influencers the agency that their self representation is legally and artistically their own.ReferencesAbidin, Crystal. “#familygoals: Family Influencers, Calibrated Amateurism, and Justifying Young Digital Labor.” Social Media + Society 3.2 (2017): 1-15.Andrejevic, Mark. “Privacy, Exploitation, and the Digital Enclosure.” Amsterdam Law Forum 1.4 (2009). <http://amsterdamlawforum.org/article/view/94/168>.Atkins, Bridgette, Isabel Pedersen, Shirley Van Nuland, and Samantha Reid. “A Glimpse into the Kids, Creative Storyworlds and Wearables Project: A Work-in-Progress.” ICET 60th World Assembly: Teachers for a Better World: Creating Conditions for Quality Education – Pedagogy, Policy and Professionalism. 2017. 49-60.Beer, David, and Roger Burrows. “Popular Culture, Digital Archives and the New Social Life of Data.” Theory, Culture & Society 30.4 (2013): 47–71.Brophy, Sarah, and Janice Hladki. Introduction. Pedagogy, Image Practices, and Contested Corporealities. Eds. Sarah Brophy and Janice Hladki. New York, NY: Routledge, 2014. 1-6.Craig, David, and Stuart Cunningham. “Toy Unboxing: Living in a(n Unregulated) Material World.” Media International Australia 163.1 (2017): 77-86.Fleischer, Sandy. “Watch Out for That Creeper: What Minecraft Teaches Us about Marketing.” Digital Marketing Magazine. 30 May 2014. <http://digitalmarketingmagazine.co.uk/articles/watch-out-for-that-creeper-what-minecraft-teaches-us-about-marketing>.James, Allison, and Adrian James. Key Concepts in Childhood Studies. London: Sage, 2012.Jenkins, Henry. The Childhood Reader. New York: NYU P, 1998.Jenks, Chris. Childhood. 2nd ed. London: Routledge, 2015.Kennedy, Ümit. "Exploring YouTube as a Transformative Tool in the 'The Power of MAKEUP!' Movement." M/C Journal 19.4 (2016). <http://journal.media-culture.org.au/index.php/mcjournal/article/view/1127>.———. “The Vulnerability of Contemporary Digital Autobiography” a/b: Auto/Biography Studies 32.2 (2017): 409-411.Kinder Playtime. “VTech Kidizoom Smart Watch DX Review by Kinder Playtime.” YouTube, 4 Nov. 2015. <https://www.youtube.com/watch?v=JaxCSjwZjcA&t=28s>.Magid, Larry. “Protecting Children Online Needs to Allow for Their Right to Free Speech.” ConnectSafely 29 Aug. 2014. <http://www.connectsafely.org/protecting-children-online-needs-to-allow-for-their-right-to-free-speech/>.Maguire, Emma. “Home, About, Shop, Contact: Constructing an Authorial Persona via the Author Website.” M/C Journal 17.3 (2014). <http://journal.media-culture.org.au/index.php/mcjournal/article/view/821>.Marsh, Jackie. “‘Unboxing’ Videos: Co-construction of the Child as Cyberflâneur.” Discourse: Studies in the Cultural Politics of Education 37.3 (2016): 369-380.Nansen, Bjorn. “Accidental, Assisted, Automated: An Emerging Repertoire of Infant Mobile Media Techniques.” M/C Journal 18.5 (2015). <http://journal.media-culture.org.au/index.php/mcjournal/article/view/1026>.———, and Benjamin Nicoll. “Toy Unboxing Videos and the Mimetic Production of Play.” Paper presented at the 18th Annual Conference of Internet Researchers (AoIR), Tartu, Estonia. 2017.Palfrey, John, and Urs Gasser. Born Digital: How Children Grow Up in a Digital Age. New York: Basic Books, 2016.Pedersen, Isabel, and Kristen Aspevig. “‘My Eyes Ended Up at My Fingertips, My Ears, My Nose, My Mouth’: Antoine, Autobiographical Documentary, and the Cinematic Depiction of a Blind Child Subject.” Biography: An Interdisciplinary Quarterly 34.4 (2011).Pedersen, Isabel, and Kristen Aspevig. “‘Swept to the Sidelines and Forgotten’: Cultural Exclusion, Blind Persons’ Participation, and International Film Festivals.” Canadian Journal of Disability Studies 3.3 (2014): 29-52.Rak, Julie. “First Person? Life Writing versus Automedia.” International Association for Biography and Autobiography Europe (IABA Europe). Vienna, Austria. 30 Oct. – 3 Nov. 2013.Smith, Sidonie. “The Autobiographical Manifesto.” Ed. Shirely Neuman. Autobiography and Questions of Gender. London: Frank Cass, 1991.———, and Julia Watson. Reading Autobiography. Minneapolis: U of Minnesota P, 2010.———. “Virtually Me: A Toolbox about Online Self-Presentation.” Identity Technologies: Constructing the Self Online. Eds. Anna Poletti and Julie Rak. Madison: U of Wisconsin P, 2014. 70-95.Sweeney, Meghan. “‘Where Happily Ever After Happens Every Day’: Disney's Official Princess Website and the Commodification of Play.” Jeunesse: Young People, Texts, Cultures 3.2 (2011): 66-87.Uhls, Yalda, and Particia Greenfield. “The Value of Fame: Preadolescent Perceptions of Popular Media and Their Relationship to Future Aspirations.” Developmental Psychology 48.2 (2012): 315-326.YouTube. “YouTube for Press.” 2017. <https://www.youtube.com/yt/about/press/>.

The human activity monitoring system helps to differentiate a person's physical actions such as walking, clapping, shaking hands etc. Activity awareness is the foundation for the development of many potential applications for health, wellness and sports. HAR has a variety of uses because of its impact on health. Helps users improve quality of life in areas such as aged care, daily logging, personal fitness software. Personal Performance Recognition is a field for identifying basic human activity and is currently being used in various fields where important information about an individual's ability to work and lifestyle. As the famous saying goes "Exercise not only changes our body it changes our mind, our mood, and our attitude". Fitness is a practice today. Everyone wants to be fit, to be beautiful, and to be healthy. But during this epidemic, not everyone can hire a coach or go to the gym. Another option is wearable devices that not everyone can afford. This paper proposed an AI trainer model. The proposed model used by anyone regardless of age and health status. The AI model uses Personal Status Evaluation. It is a popular method and determines the location and posture of the human body. This technique creates important points in the human body and is based on the fact that it creates a virtual skeletal structure in the 2D dimension. Featured is a live video taken from a person's webcam and the output captures location marks or key points in the human body. The AI trainer specifies the calculation and timing of the settings that a person must perform. It also specifies errors and feedback if any. This paper provides a way to use the stop rate that works on the CPU to get the correct points. Based on points touch and other curls (biceps) are calculated. This paper proposes a method that uses OpenCV to use a stand-alone model.