Journal articles on the topic 'In-app user activity detection'
To see the other types of publications on this topic, follow the link: In-app user activity detection.
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 journal articles for your research on the topic 'In-app user activity detection.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse journal articles on a wide variety of disciplines and organise your bibliography correctly.
1
Pathmaperuma, Madushi H., Yogachandran Rahulamathavan, Safak Dogan, and Ahmet Kondoz. "CNN for User Activity Detection Using Encrypted In-App Mobile Data." Future Internet 14, no. 2 (February 21, 2022): 67. http://dx.doi.org/10.3390/fi14020067.
Full textAbstract:
In this study, a simple yet effective framework is proposed to characterize fine-grained in-app user activities performed on mobile applications using a convolutional neural network (CNN). The proposed framework uses a time window-based approach to split the activity’s encrypted traffic flow into segments, so that in-app activities can be identified just by observing only a part of the activity-related encrypted traffic. In this study, matrices were constructed for each encrypted traffic flow segment. These matrices acted as input into the CNN model, allowing it to learn to differentiate previously trained (known) and previously untrained (unknown) in-app activities as well as the known in-app activity type. The proposed method extracts and selects salient features for encrypted traffic classification. This is the first-known approach proposing to filter unknown traffic with an average accuracy of 88%. Once the unknown traffic is filtered, the classification accuracy of our model would be 92%.
2
Pathmaperuma, Madushi H., Yogachandran Rahulamathavan, Safak Dogan, and Ahmet M. Kondoz. "Deep Learning for Encrypted Traffic Classification and Unknown Data Detection." Sensors 22, no. 19 (October 9, 2022): 7643. http://dx.doi.org/10.3390/s22197643.
Full textAbstract:
Despite the widespread use of encryption techniques to provide confidentiality over Internet communications, mobile device users are still susceptible to privacy and security risks. In this paper, a novel Deep Neural Network (DNN) based on a user activity detection framework is proposed to identify fine-grained user activities performed on mobile applications (known as in-app activities) from a sniffed encrypted Internet traffic stream. One of the challenges is that there are countless applications, and it is practically impossible to collect and train a DNN model using all possible data from them. Therefore, in this work, we exploit the probability distribution of a DNN output layer to filter the data from applications that are not considered during the model training (i.e., unknown data). The proposed framework uses a time window-based approach to divide the traffic flow of activity into segments so that in-app activities can be identified just by observing only a fraction of the activity-related traffic. Our tests have shown that the DNN-based framework has demonstrated an accuracy of 90% or above in identifying previously trained in-app activities and an average accuracy of 79% in identifying previously untrained in-app activity traffic as unknown data when this framework is employed.
3
Zhu, Hao, and Georgios B. Giannakis. "Exploiting Sparse User Activity in Multiuser Detection." IEEE Transactions on Communications 59, no. 2 (February 2011): 454–65. http://dx.doi.org/10.1109/tcomm.2011.121410.090570.
Full text
4
Mitra, U., and H. V. Poor. "Activity detection in a multi-user environment." Wireless Personal Communications 3, no. 1-2 (1996): 149–74. http://dx.doi.org/10.1007/bf00333928.
Full text
5
Kim, Youngho, Tae Oh, and Jeongnyeo Kim. "Analyzing User Awareness of Privacy Data Leak in Mobile Applications." Mobile Information Systems 2015 (2015): 1–12. http://dx.doi.org/10.1155/2015/369489.
Full textAbstract:
To overcome the resource and computing power limitation of mobile devices in Internet of Things (IoT) era, a cloud computing provides an effective platform without human intervention to build a resource-oriented security solution. However, existing malware detection methods are constrained by a vague situation of information leaks. The main goal of this paper is to measure a degree of hiding intention for the mobile application (app) to keep its leaking activity invisible to the user. For real-world application test, we target Android applications, which unleash user privacy data. With the TaintDroid-ported emulator, we make experiments about the timing distance between user events and privacy leaks. Our experiments with Android apps downloaded from the Google Play show that most of leak cases are driven by user explicit events or implicit user involvement which make the user aware of the leakage. Those findings can assist a malware detection system in reducing the rate of false positive by considering malicious intentions. From the experiment, we understand better about app’s internal operations as well. As a case study, we also presents a cloud-based dynamic analysis framework to perform a traffic monitor.
6
Parwez, Md Salik, Danda B. Rawat, and Moses Garuba. "Big Data Analytics for User-Activity Analysis and User-Anomaly Detection in Mobile Wireless Network." IEEE Transactions on Industrial Informatics 13, no. 4 (August 2017): 2058–65. http://dx.doi.org/10.1109/tii.2017.2650206.
Full text
7
Bashir, Sulaimon Adebayo, Andrei Petrovski, and Daniel Doolan. "A framework for unsupervised change detection in activity recognition." International Journal of Pervasive Computing and Communications 13, no. 2 (June 5, 2017): 157–75. http://dx.doi.org/10.1108/ijpcc-03-2017-0027.
Full textAbstract:
Purpose This purpose of this paper is to develop a change detection technique for activity recognition model. The approach aims to detect changes in the initial accuracy of the model after training and when the model is deployed for recognizing new unseen activities without access to the ground truth. The changes between the two sessions may occur because of differences in sensor placement, orientation and user characteristics such as age and gender. However, many of the existing approaches for model adaptation in activity recognition are blind methods because they continuously adapt the recognition model without explicit detection of changes in the model performance. Design/methodology/approach The approach determines the variation between reference activity data belonging to different classes and newly classified unseen data. If there is coherency between the data, it means the model is correctly classifying the instances; otherwise, a significant variation indicates wrong instances are being classified to different classes. Thus, the approach is formulated as a two-level architectural framework comprising of the off-line phase and the online phase. The off-line phase extracts of Shewart Chart change parameters from the training data set. The online phase performs classification of new samples and the detection of the changes in each class of activity present in the data set by using the change parameters computed earlier. Findings The approach is evaluated using a real activity-recognition data set. The results show that there are consistent detections that correlate with the error rate of the model. Originality/value The developed approach does not use ground truth to detect classifier performance degradation. Rather, it uses a data discrimination method and a base classifier to detect the changes by using the parameters computed from the reference data of each class to discriminate outliers in the new data being classified to the same class. The approach is the first, to the best of the authors’ knowledge, that addresses the problem of detecting within-user and cross-user variations that lead to concept drift in activity recognition. The approach is also the first to use statistical process control method for change detection in activity recognition, with a robust integrated framework that seamlessly detects variations in the underlying model performance.
8
Lee, Jemin, and Hyungshin Kim. "QDroid: Mobile Application Quality Analyzer for App Market Curators." Mobile Information Systems 2016 (2016): 1–11. http://dx.doi.org/10.1155/2016/1740129.
Full textAbstract:
Low quality mobile applications have damaged the user experience. However, in light of the number of applications, quality analysis is a daunting task. For that reason, QDroid is proposed, an automated quality analyzer that detects the presence of crashes, excessive resource usage, and compatibility problems, without source codes and human involvement. QDroid was applied to 67 applications for evaluation and discovered 78% more crashes and attained 23% higher Activity coverage than Monkey testing. For detecting excessive resource usage and compatibility problems, QDroid reduced the number of applications that required manual review by up to 96% and 69%, respectively.
9
Zain ul Abideen, Muhammad, Shahzad Saleem, and Madiha Ejaz. "VPN Traffic Detection in SSL-Protected Channel." Security and Communication Networks 2019 (October 29, 2019): 1–17. http://dx.doi.org/10.1155/2019/7924690.
Full textAbstract:
In recent times, secure communication protocols over web such as HTTPS (Hypertext Transfer Protocol Secure) are being widely used instead of plain web communication protocols like HTTP (Hypertext Transfer Protocol). HTTPS provides end-to-end encryption between the user and service. Nowadays, organizations use network firewalls and/or intrusion detection and prevention systems (IDPS) to analyze the network traffic to detect and protect against attacks and vulnerabilities. Depending on the size of organization, these devices may differ in their capabilities. Simple network intrusion detection system (NIDS) and firewalls generally have no feature to inspect HTTPS or encrypted traffic, so they rely on unencrypted traffic to manage the encrypted payload of the network. Recent and powerful next-generation firewalls have Secure Sockets Layer (SSL) inspection feature which are expensive and may not be suitable for every organizations. A virtual private network (VPN) is a service which hides real traffic by creating SSL-protected channel between the user and server. Every Internet activity is then performed under the established SSL tunnel. The user inside the network with malicious intent or to hide his activity from the network security administration of the organization may use VPN services. Any VPN service may be used by users to bypass the filters or signatures applied on network security devices. These services may be the source of new virus or worm injected inside the network or a gateway to facilitate information leakage. In this paper, we have proposed a novel approach to detect VPN activity inside the network. The proposed system analyzes the communication between user and the server to analyze and extract features from network, transport, and application layer which are not encrypted and classify the incoming traffic as malicious, i.e., VPN traffic or standard traffic. Network traffic is analyzed and classified using DNS (Domain Name System) packets and HTTPS- (Hypertext Transfer Protocol Secure-) based traffic. Once traffic is classified, the connection based on the server’s IP, TCP port connected, domain name, and server name inside the HTTPS connection is analyzed. This helps in verifying legitimate connection and flags the VPN-based traffic. We worked on top five freely available VPN services and analyzed their traffic patterns; the results show successful detection of the VPN activity performed by the user. We analyzed the activity of five users, using some sort of VPN service in their Internet activity, inside the network. Out of total 729 connections made by different users, 329 connections were classified as legitimate activity, marking 400 remaining connections as VPN-based connections. The proposed system is lightweight enough to keep minimal overhead, both in network and resource utilization and requires no specialized hardware.
10
Karthikeyan, Dakshinamoorthy, Arun Sivakumar, and Chamundeswari Arumugam. "Android X-Ray - A system for Malware Detection in Android apps using Dynamic Analysis." WSEAS TRANSACTIONS ON INFORMATION SCIENCE AND APPLICATIONS 19 (November 7, 2022): 264–71. http://dx.doi.org/10.37394/23209.2022.19.27.
Full textAbstract:
In recent years, mobile malware takes anywhere between several hours to several days to screen an app for malicious activity. More than 6000 apps are added to the Google Play Store everyday on average. Security analysts face an uphill battle against malware developers as the complexity of malware and code obfuscation techniques are constantly increasing. Currently, most research focuses on the development and application of machine learning techniques for malware detection. However, their success has been limited due to a lack of depth in the data sets available for training models. This paper uses a new method of Dynamic Analysis for Android apps to extract large amounts of information on the behavior of any app which can then be used for training models or to enable security analysts to take an informed decision quickly.
11
He, Qi, Zhi Chen, Tony Q. S. Quek, Jinho Choi, and Shaoqian Li. "Compressive Channel Estimation and User Activity Detection in Distributed-Input Distributed-Output Systems." IEEE Communications Letters 22, no. 9 (September 2018): 1850–53. http://dx.doi.org/10.1109/lcomm.2018.2858241.
Full text
12
Zhang, Jun, Yongping Pan, and Jie Xu. "Compressive Sensing for Joint User Activity and Data Detection in Grant-Free NOMA." IEEE Wireless Communications Letters 8, no. 3 (June 2019): 857–60. http://dx.doi.org/10.1109/lwc.2019.2897552.
Full text
13
Utkovski, Zoran, Osvaldo Simeone, Tamara Dimitrova, and Petar Popovski. "Random Access in C-RAN for User Activity Detection With Limited-Capacity Fronthaul." IEEE Signal Processing Letters 24, no. 1 (January 2017): 17–21. http://dx.doi.org/10.1109/lsp.2016.2633962.
Full text
14
Li, Jing, Yabo Dong, Shengkai Fang, Haowen Zhang, and Duanqing Xu. "User Context Detection for Relay Attack Resistance in Passive Keyless Entry and Start System." Sensors 20, no. 16 (August 9, 2020): 4446. http://dx.doi.org/10.3390/s20164446.
Full textAbstract:
In modern cars, the Passive Keyless Entry and Start system (PKES) has been extensively installed. The PKES enables drivers to unlock and start their cars without user interaction. However, it is vulnerable to relay attacks. In this paper, we propose a secure smartphone-type PKES system model based on user context detection. The proposed system uses the barometer and accelerometer embedded in smartphones to detect user context, including human activity and door closing event. These two types of events detection can be used by the PKES to determine the car owner’s position when the car receives an unlocking or a start command. We evaluated the performance of the proposed method using a dataset collected from user activity and 1526 door closing events. The results reveal that the proposed method can accurately and effectively detect user activities and door closing events. Therefore, smartphone-type PKES can prevent relay attacks. Furthermore, we tested the detection of door closing event under multiple environmental settings to demonstrate the robustness of the proposed method.
15
Zilli, D., O. Parson, G. V. Merrett, and A. Rogers. "A Hidden Markov Model-Based Acoustic Cicada Detector for Crowdsourced Smartphone Biodiversity Monitoring." Journal of Artificial Intelligence Research 51 (December 30, 2014): 805–27. http://dx.doi.org/10.1613/jair.4434.
Full textAbstract:
In recent years, the field of computational sustainability has striven to apply artificial intelligence techniques to solve ecological and environmental problems. In ecology, a key issue for the safeguarding of our planet is the monitoring of biodiversity. Automated acoustic recognition of species aims to provide a cost-effective method for biodiversity monitoring. This is particularly appealing for detecting endangered animals with a distinctive call, such as the New Forest cicada. To this end, we pursue a crowdsourcing approach, whereby the millions of visitors to the New Forest, where this insect was historically found, will help to monitor its presence by means of a smartphone app that can detect its mating call. Existing research in the field of acoustic insect detection has typically focused upon the classification of recordings collected from fixed field microphones. Such approaches segment a lengthy audio recording into individual segments of insect activity, which are independently classified using cepstral coefficients extracted from the recording as features. This paper reports on a contrasting approach, whereby we use crowdsourcing to collect recordings via a smartphone app, and present an immediate feedback to the users as to whether an insect has been found. Our classification approach does not remove silent parts of the recording via segmentation, but instead uses the temporal patterns throughout each recording to classify the insects present. We show that our approach can successfully discriminate between the call of the New Forest cicada and similar insects found in the New Forest, and is robust to common types of environment noise. A large scale trial deployment of our smartphone app collected over 6000 reports of insect activity from over 1000 users. Despite the cicada not having been rediscovered in the New Forest, the effectiveness of this approach was confirmed for both the detection algorithm, which successfully identified the same cicada through the app in countries where the same species is still present, and of the crowdsourcing methodology, which collected a vast number of recordings and involved thousands of contributors.
16
Han, Gang Tao, Ying Qiang Ding, Xiao Min Mu, and Jian Kang Zhang. "A Modified Energy Detection Algorithm Based on Primary User Activity for Cognitive Radio Networks." Applied Mechanics and Materials 548-549 (April 2014): 1351–54. http://dx.doi.org/10.4028/www.scientific.net/amm.548-549.1351.
Full textAbstract:
Spectrum sensing is used to identify the unused frequency bands and as such plays a key role in dynamic spectrum access. In most of the existing spectrum sensing models, the channel state of primary user is assumed unchanged within the spectrum sensing duration, which is not suitable for the channels with high activity, in which the primary user accesses or vacates from the channel frequently. In this paper, a Modified Energy Detection (MED) algorithm is proposed for this scenarios by considering the primary user activity within the spectrum sensing duration. Theory analysis and computer simulation results show that both the probability of detection and false alarm in this scenarios have been improved with our MED.
17
Kim, Park, Kim, Cho, and Kang. "Insider Threat Detection Based on User Behavior Modeling and Anomaly Detection Algorithms." Applied Sciences 9, no. 19 (September 25, 2019): 4018. http://dx.doi.org/10.3390/app9194018.
Full textAbstract:
Insider threats are malicious activities by authorized users, such as theft of intellectual property or security information, fraud, and sabotage. Although the number of insider threats is much lower than external network attacks, insider threats can cause extensive damage. As insiders are very familiar with an organization’s system, it is very difficult to detect their malicious behavior. Traditional insider-threat detection methods focus on rule-based approaches built by domain experts, but they are neither flexible nor robust. In this paper, we propose insider-threat detection methods based on user behavior modeling and anomaly detection algorithms. Based on user log data, we constructed three types of datasets: user’s daily activity summary, e-mail contents topic distribution, and user’s weekly e-mail communication history. Then, we applied four anomaly detection algorithms and their combinations to detect malicious activities. Experimental results indicate that the proposed framework can work well for imbalanced datasets in which there are only a few insider threats and where no domain experts’ knowledge is provided.
18
Huang, Nai-Hsuan, and Tzi-Dar Chiueh. "Sequence Design and User Activity Detection for Uplink Grant-Free NOMA in mMTC Networks." IEEE Open Journal of the Communications Society 2 (2021): 384–95. http://dx.doi.org/10.1109/ojcoms.2021.3056994.
Full text
19
Park, Soojin, Sungyong Park, and Kyeongwook Ma. "An Automatic User Activity Analysis Method for Discovering Latent Requirements: Usability Issue Detection on Mobile Applications." Sensors 18, no. 9 (September 5, 2018): 2963. http://dx.doi.org/10.3390/s18092963.
Full textAbstract:
Starting with the Internet of Things (IoT), new forms of system operation concepts have emerged to provide creative services through collaborations among autonomic devices. Following these paradigmatic changes, the ability of each participating system to automatically diagnose the degree of quality it is providing is inevitable. This paper proposed a method to automatically detect symptoms that hinder certain quality attributes. The method consisted of three steps: (1) extracting information from real usage logs and automatically generating an activity model from the captured information; (2) merging multiple user activity models into a single, representative model; and (3) detecting differences between the representative user activity model, and an expected activity model. The proposed method was implemented in a domain-independent framework, workable on the Android platform. Unlike other related works, we used quantitative evaluation results to show the benefits of applying the proposed method to five Android-based, open-source mobile applications. The evaluation results showed that the average precision rate for the automatic detection of symptoms was 70%, and the success rate for user implementation of usage scenarios demonstrated an improvement of around 21%, when the automatically detected symptoms were resolved.
20
Kim, Myeongchan, Sehyo Yune, Seyun Chang, Yuseob Jung, Soon Ok Sa, and Hyun Wook Han. "The Fever Coach Mobile App for Participatory Influenza Surveillance in Children: Usability Study." JMIR mHealth and uHealth 7, no. 10 (October 17, 2019): e14276. http://dx.doi.org/10.2196/14276.
Full textAbstract:
Background Effective surveillance of influenza requires a broad network of health care providers actively reporting cases of influenza-like illnesses and positive laboratory results. Not only is this traditional surveillance system costly to establish and maintain but there is also a time lag between a change in influenza activity and its detection. A new surveillance system that is both reliable and timely will help public health officials to effectively control an epidemic and mitigate the burden of the disease. Objective This study aimed to evaluate the use of parent-reported data of febrile illnesses in children submitted through the Fever Coach app in real-time surveillance of influenza activities. Methods Fever Coach is a mobile app designed to help parents and caregivers manage fever in young children, currently mainly serviced in South Korea. The app analyzes data entered by a caregiver and provides tailored information for care of the child based on the child’s age, sex, body weight, body temperature, and accompanying symptoms. Using the data submitted to the app during the 2016-2017 influenza season, we built a regression model that monitors influenza incidence for the 2017-2018 season and validated the model by comparing the predictions with the public influenza surveillance data from the Korea Centers for Disease Control and Prevention (KCDC). Results During the 2-year study period, 70,203 diagnosis data, including 7702 influenza reports, were submitted. There was a significant correlation between the influenza activity predicted by Fever Coach and that reported by KCDC (Spearman ρ=0.878; P<.001). Using this model, the influenza epidemic in the 2017-2018 season was detected 10 days before the epidemic alert announced by KCDC. Conclusions The Fever Coach app successfully collected data from 7.73% (207,699/2,686,580) of the target population by providing care instruction for febrile children. These data were used to develop a model that accurately estimated influenza activity measured by the central government agency using reports from sentinel facilities in the national surveillance network.
21
Tsien, Yu Lei, and Rong Li Gai. "User Activity Based Application-Layer DoS/DDoS Attack Defense Algorithm." Applied Mechanics and Materials 742 (March 2015): 693–97. http://dx.doi.org/10.4028/www.scientific.net/amm.742.693.
Full textAbstract:
In application-layer DoS/DDoS attacks, malicious users attack the victim server by sending lots of legitimate requesting packages, which overwhelm the server bottleneck resources. Normal user’s request thus may not be satisfied. The traditional intrusion detection systems for network-layer cannot effectively identify this attack, and recent researches on this kind of attack are mainly for Web servers. This paper proposed a new defense algorithm based on user activity for topic-based Pub/Sub communication servers in mobile push notification systems. Users consuming system bottleneck resources the most can get high scores and thus are considered overactive. With some resource retaken strategy, overactive users’ connections will be dropped according to system performance level. Therefore, the system can get rid of latent threatens. Experiments indicated that this algorithm can identify normal and abnormal users well.
22
Priyatno, Arif Mudi. "SPAMMER DETECTION BASED ON ACCOUNT, TWEET, AND COMMUNITY ACTIVITY ON TWITTER." Jurnal Ilmu Komputer dan Informasi 13, no. 2 (July 1, 2020): 97–107. http://dx.doi.org/10.21609/jiki.v13i2.871.
Full textAbstract:
Spammers are the activities of users who abuse Twitter to spread spam. Spammers imitate legitimate user behavior patterns to avoid being detected by spam detectors. Spammers create lots of fake accounts and collaborate with each other to form communities. The collaboration makes it difficult to detect spammers' accounts. This research proposed the development of feature extraction based on hashtags and community activities for the detection of spammer accounts on Twitter. Hashtags are used by spammers to increase popularity. Community activities are used as features for the detection of spammers so as to give weight to the activities of spammers contained in a community. The experimental result shows that the proposed method got the best performance in accuracy, recall, precision and g-means with are 90.55%, 88.04%, 3.18%, and 16.74%, respectively. The accuracy and g-mean of the proposed method can surpassed previous method with 4.23% and 14.43%. This shows that the proposed method can overcome the problem of detecting spammer on Twitter with better performance compared to state of the art.
23
Truong-Allié, Camille, Alexis Paljic, Alexis Roux, and Martin Herbeth. "User Behavior Adaptive AR Guidance for Wayfinding and Tasks Completion." Multimodal Technologies and Interaction 5, no. 11 (October 20, 2021): 65. http://dx.doi.org/10.3390/mti5110065.
Full textAbstract:
Augmented reality (AR) is widely used to guide users when performing complex tasks, for example, in education or industry. Sometimes, these tasks are a succession of subtasks, possibly distant from each other. This can happen, for instance, in inspection operations, where AR devices can give instructions about subtasks to perform in several rooms. In this case, AR guidance is both needed to indicate where to head to perform the subtasks and to instruct the user about how to perform these subtasks. In this paper, we propose an approach based on user activity detection. An AR device displays the guidance for wayfinding when current user activity suggests it is needed. We designed the first prototype on a head-mounted display using a neural network for user activity detection and compared it with two other guidance temporality strategies, in terms of efficiency and user preferences. Our results show that the most efficient guidance temporality depends on user familiarity with the AR display. While our proposed guidance has not proven to be more efficient than the other two, our experiment hints toward several improvements of our prototype, which is a first step in the direction of efficient guidance for both wayfinding and complex task completion.
24
Bhoge, Rutuja K., Snehal A. Nagare, Swapanali P. Mahajan, and Prajakta S. Kor. "Depression Detection by Analyzing Social Media Post of User." International Journal for Research in Applied Science and Engineering Technology 10, no. 4 (April 30, 2022): 2720–24. http://dx.doi.org/10.22214/ijraset.2022.41874.
Full textAbstract:
Abstract: Nowadays the problem of early depression detection is one of the most important in the field of psychology .Mental health issues are widely accepted as one of the most prominent health challenges in the world, with over 300 million people currently suffering from depression alone. With massive volumes of user-generated data on social networking platforms, researchers are increasingly using machine learning to determine whether this content can be used to detect mental health problems in users. Depression as a disorder has been an excellent concern in our society and has been continuously a hot topic for researchers in the world. Despite the massive quantity of analysis on understanding individual moods together with depression, anxiety, and stress supported activity logs collected by pervasive computing devices like smartphones, foretelling depressed moods continues to be an open question. Social networks analysis is widely applied to address this problem. In this paper, we have proposed a depression analysis and suicidal ideation detection system, for predicting the suicidal acts supported the extent of depression. The present study aims to exploit machine learning techniques for detecting a probable depressed Social Media user his/her Posts. For this purpose, we trained and tested classifiers to differentiate whether a user is depressed or not using features extracted from his/her activities within the posts. classification machine algorithms are used to train and classify it in Different stages of depression on scale of 0-100%. Also, data was collected in the form of posts and were classified into whether the one that tweeted is in depression or not using classification algorithms of Machine Learning In this way Predictive approach for early detection of depression or other mental illnesses. This study’s main contribution is that the exploration a neighborhood of the features and its impact on detecting Depression level. This study aims to develop a deep learning model to classify users with depression via multiple instance learning, which can learn from user-level labels to identify post-level labels. By combining every possibility of posts label category, it can generate temporal posting profiles which can then be used to classify users with depression. This paper shows that there are clear differences in posting patterns between users with depression and non-depression, which is represented through the combined likelihood of posts label category. In this research, machine learning is used to process the scrapped data collected from social media users posts. Natural Language Processing (NLP), classified using BERT algorithm to detect depression potentially in amore convenient and efficient way. Keywords: Machine Learning, NLP, BERT Algorithm, Classification, Social Media Post
25
Mishra, Varun, Florian Künzler, Jan-Niklas Kramer, Elgar Fleisch, Tobias Kowatsch, and David Kotz. "Detecting Receptivity for mHealth Interventions in the Natural Environment." Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies 5, no. 2 (June 23, 2021): 1–24. http://dx.doi.org/10.1145/3463492.
Full textAbstract:
Just-In-Time Adaptive Intervention (JITAI) is an emerging technique with great potential to support health behavior by providing the right type and amount of support at the right time. A crucial aspect of JITAIs is properly timing the delivery of interventions, to ensure that a user is receptive and ready to process and use the support provided. Some prior works have explored the association of context and some user-specific traits on receptivity, and have built post-study machine-learning models to detect receptivity. For effective intervention delivery, however, a JITAI system needs to make in-the-moment decisions about a user's receptivity. To this end, we conducted a study in which we deployed machine-learning models to detect receptivity in the natural environment, i.e., in free-living conditions. We leveraged prior work regarding receptivity to JITAIs and deployed a chatbot-based digital coach - Ally - that provided physical-activity interventions and motivated participants to achieve their step goals. We extended the original Ally app to include two types of machine-learning model that used contextual information about a person to predict when a person is receptive: a static model that was built before the study started and remained constant for all participants and an adaptive model that continuously learned the receptivity of individual participants and updated itself as the study progressed. For comparison, we included a control model that sent intervention messages at random times. The app randomly selected a delivery model for each intervention message. We observed that the machine-learning models led up to a 40% improvement in receptivity as compared to the control model. Further, we evaluated the temporal dynamics of the different models and observed that receptivity to messages from the adaptive model increased over the course of the study.
26
Rivera, Bryan, Consuelo Cano, Israel Luis, and Dante A. Elias. "A 3D-Printed Knee Wearable Goniometer with a Mobile-App Interface for Measuring Range of Motion and Monitoring Activities." Sensors 22, no. 3 (January 20, 2022): 763. http://dx.doi.org/10.3390/s22030763.
Full textAbstract:
Wearable technology has been developed in recent years to monitor biomechanical variables in less restricted environments and in a more affordable way than optical motion capture systems. This paper proposes the development of a 3D printed knee wearable goniometer that uses a Hall-effect sensor to measure the knee flexion angle, which works with a mobile app that shows the angle in real-time as well as the activity the user is performing (standing, sitting, or walking). Detection of the activity is done through an algorithm that uses the knee angle and angular speeds as inputs. The measurements of the wearable are compared with a commercial goniometer, and, with the Aktos-t system, a commercial motion capture system based on inertial sensors, at three speeds of gait (4.0 km/h, 4.5 km/h, and 5.0 km/h) in nine participants. Specifically, the four differences between maximum and minimum peaks in the gait cycle, starting with heel-strike, were compared by using the mean absolute error, which was between 2.46 and 12.49 on average. In addition, the algorithm was able to predict the three activities during online testing in one participant and detected on average 94.66% of the gait cycles performed by the participants during offline testing.
27
Gnanasekar, A. "Detecting Spam Bots on Social Network." Revista Gestão Inovação e Tecnologias 11, no. 2 (June 5, 2021): 850–60. http://dx.doi.org/10.47059/revistageintec.v11i2.1719.
Full textAbstract:
Bots have made an appearance on social media in a variety of ways. Twitter, for instance, has been particularly hard hit, with bots accounting for a shockingly large number of its users. These bots are used for nefarious purposes such as disseminating false information about politicians and inflating celebrity expectations. Furthermore, these bots have the potential to skew the results of conventional social media research. With the multiple increases in the size, speed, and style of user knowledge in online social networks, new methods of grouping and evaluating such massive knowledge are being explored. Getting rid of malicious social bots from a social media site is crucial. The most widely used methods for identifying fraudulent social bots focus on the quantitative measures of their actions. Social bots simply mimic these choices, leading to a low level of study accuracy. Transformation clickstream sequences and semi-supervised clustering were used to develop a new technique for detecting malicious social bots. This method considers not only the probability of user activity clickstreams being moved, but also the behavior's time characteristic. The detection accuracy for various kinds of malware social bots by the detection technique assisted transfer probability of user activity clickstreams will increase by a mean of 12.8 percent, as per results from our research on real online social network sites, compared to the detection method funded estimate of user behaviour.
28
Esmaeili Kelishomi, Aghil, A. H. S. Garmabaki, Mahdi Bahaghighat, and Jianmin Dong. "Mobile User Indoor-Outdoor Detection Through Physical Daily Activities." Sensors 19, no. 3 (January 26, 2019): 511. http://dx.doi.org/10.3390/s19030511.
Full textAbstract:
An automatic, fast, and accurate switching method between Global Positioning System and indoor positioning systems is crucial to achieve current user positioning, which is essential information for a variety of services installed on smart devices, e.g., location-based services (LBS), healthcare monitoring components, and seamless indoor/outdoor navigation and localization (SNAL). In this study, we proposed an approach to accurately detect the indoor/outdoor environment according to six different daily activities of users including walk, skip, jog, stay, climbing stairs up and down. We select a number of features for each activity and then apply ensemble learning methods such as Random Forest, and AdaBoost to classify the environment types. Extensive model evaluations and feature analysis indicate that the system can achieve a high detection rate with good adaptation for environment recognition. Empirical evaluation of the proposed method has been verified on the HASC-2016 public dataset, and results show 99% accuracy to detect environment types. The proposed method relies only on the daily life activities data and does not need any external facilities such as the signal cell tower or Wi-Fi access points. This implies the applicability of the proposed method for the upper layer applications.
29
Steed, Robert J., Amaya Fuenzalida, Rémy Bossu, István Bondár, Andres Heinloo, Aurelien Dupont, Joachim Saul, and Angelo Strollo. "Crowdsourcing triggers rapid, reliable earthquake locations." Science Advances 5, no. 4 (April 2019): eaau9824. http://dx.doi.org/10.1126/sciadv.aau9824.
Full textAbstract:
In many cases, it takes several minutes after an earthquake to publish online a seismic location with confidence. Via monitoring for specific types of increased website, app, or Twitter usage, crowdsourced detection of seismic activity can be used to “seed” the search in the seismic data for an earthquake and reduce the risk of false detections, thereby accelerating the publication of locations for felt earthquakes. We demonstrate that this low-cost approach can work at the global scale to produce reliable and rapid results. The system was retroactively tested on a set of real crowdsourced detections of earthquakes made during 2016 and 2017, with 50% of successful locations found within 103 s, 76 s faster than GEOFON and 271 s faster than the European-Mediterranean Seismological Centre’s publication times, and 90% of successful locations found within 54 km of the final accepted epicenter.
30
Nikonowicz, Jakub, Aamir Mahmood, and Mikael Gidlund. "A Blind Signal Samples Detection Algorithm for Accurate Primary User Traffic Estimation." Sensors 20, no. 15 (July 25, 2020): 4136. http://dx.doi.org/10.3390/s20154136.
Full textAbstract:
The energy detection process for enabling opportunistic spectrum access in dynamic primary user (PU) scenarios, where PU changes state from active to inactive at random time instances, requires the estimation of several parameters ranging from noise variance and signal-to-noise ratio (SNR) to instantaneous and average PU activity. A prerequisite to parameter estimation is an accurate extraction of the signal and noise samples in a received signal time frame. In this paper, we propose a low-complexity and accurate signal samples detection algorithm as compared to well-known methods, which is also blind to the PU activity distribution. The proposed algorithm is analyzed in a semi-experimental simulation setup for its accuracy and time complexity in recognizing signal and noise samples, and its use in channel occupancy estimation, under varying occupancy and SNR of the PU signal. The results confirm its suitability for acquiring the necessary information on the dynamic behavior of PU, which is otherwise assumed to be known in the literature.
31
S, Shalini. "Behavioral Based Credit Card Fraud Detection." International Journal for Research in Applied Science and Engineering Technology 9, no. VII (July 31, 2021): 3556–61. http://dx.doi.org/10.22214/ijraset.2021.37134.
Full textAbstract:
Credit card fraud is a significant threat in the BFSI sector. This credit card fraud detection system analyzes user behavioral patterns and their location to identify any unusual patterns. This consists of user characteristics, which includes user spending styles as well as standard user geographic places to verify his identity. One of the user behavior patterns includes spending habits, usage patterns, etc. This system deals with user credit card data for various characteristics, which includes user country, usual spending procedures. Based upon previous transactions information of that person, the system recognizes unusual patterns in the payment method. The fraud detection system contains the past transaction data of each user. Based on this data, it identifies the standard user behavior patterns for individual users, and any deviation from those normal user patterns becomes a trigger for the detection system. If it detects any unusual patterns, then user will be required to undergo the security verification, which identifies the original user using QR code recognition system. In case of any unusual activity, the system not only raises alerts but it will block the user after three invalid attempts.
32
Chiossi, Francesco, Robin Welsch, Steeven Villa, Lewis Chuang, and Sven Mayer. "Virtual Reality Adaptation Using Electrodermal Activity to Support the User Experience." Big Data and Cognitive Computing 6, no. 2 (May 13, 2022): 55. http://dx.doi.org/10.3390/bdcc6020055.
Full textAbstract:
Virtual reality is increasingly used for tasks such as work and education. Thus, rendering scenarios that do not interfere with such goals and deplete user experience are becoming progressively more relevant. We present a physiologically adaptive system that optimizes the virtual environment based on physiological arousal, i.e., electrodermal activity. We investigated the usability of the adaptive system in a simulated social virtual reality scenario. Participants completed an n-back task (primary) and a visual detection (secondary) task. Here, we adapted the visual complexity of the secondary task in the form of the number of non-player characters of the secondary task to accomplish the primary task. We show that an adaptive virtual reality can improve users’ comfort by adapting to physiological arousal regarding the task complexity. Our findings suggest that physiologically adaptive virtual reality systems can improve users’ experience in a wide range of scenarios.
33
Sack, Jordan, Todd Reid, Eric Schlossberg, and Nikroo Hashemi. "A Smartphone App for Patients With End-Stage Liver Disease Can Detect Behavioral Changes That Predict Liver-Related Events." Iproceedings 5, no. 1 (October 2, 2019): e15229. http://dx.doi.org/10.2196/15229.
Full textAbstract:
Background Patients with end-stage liver disease have significant morbidity and mortality. The 90-day readmission rate for these patients is up to 53% at a cost of $4.45 billion annually. Healthcare delivery for these patients is often fragmented and inadequate. Smartphone-based remote health monitoring may reduce hospitalizations by earlier detection of premonitory warning signs associated with liver-related complications. Hepatic encephalopathy which is a common cause of hospitalization and sleep disturbance and subtle/sub-clinical behavioral changes are early warning signs. Objective In this pilot study of patients with end-stage liver disease, we assessed the feasibility of our smartphone app to detect physiologic and behavioral changes during the 7 days prior to liver-related hospitalizations or urgent visits. Methods This is a prospective multicenter pilot study of patients with end-stage liver disease who were enrolled at three academic centers to receive our smartphone app for a 180-day period. English speaking patients age ≥18 years who receive liver care at one of the study sites, do not actively use alcohol or drugs, have had a liver-related complication in the previous 3 months (ascites, hepatic encephalopathy, variceal bleeding, bacterial peritonitis), and own an Android smartphone with internet connectivity were eligible. The smartphone app solicits emotions daily and collects passive data on activity, sleep, and social interactions. Patients received monthly in-app questions about how many liver-related events they had over the preceding month. Surveys on sociodemographic characteristics and health status were collected at baseline, 90 days, and 180 days. Clinical data on liver-related hospitalizations or urgent visits (“events”) were collected prospectively through chart review. Smartphone data on activity, sleep, social interactions, and emotions were analyzed during the 7-day period preceding a liver event and compared to the average over the study period. Statistical analyses were performed with Mann-Whitney U test. Results An interim analysis of the 40 enrolled patients who met all eligibility criteria found that 15 patients had 27 liver-related events during the study period. These patients were predominantly men with a median age of 56 years. 61% of these patients responded to the monthly in-app question about hospitalizations and did so with 100% accuracy. In the 7-day period prior to the event, these patients had more sleep disturbances and changes in activity score (P=.04; P=.04). There was no statistically significant difference in social scores during the 7-day period prior to the event. Emoji selection among this group was too small for analysis. Conclusions The interim analysis of this pilot study suggests that passive data collected from our smartphone app can detect behavioral changes that could be used to predict liver-related events. Specifically, significant changes in smartphone activity and sleep disturbances were identified during the 7-day period prior to a liver-related event. Smartphone-based remote health monitoring appears to be feasible in this patient population and has the potential to reduce hospitalizations through early detection of early warning signs.
34
Natadimadja, Muhammad Rayhan, Maman Abdurohman, and Hilal Hudan Nuha. "A Survey on Phishing Website Detection Using Hadoop." Jurnal Informatika Universitas Pamulang 5, no. 3 (September 30, 2020): 237. http://dx.doi.org/10.32493/informatika.v5i3.6672.
Full textAbstract:
Phishing is an activity carried out by phishers with the aim of stealing personal data of internet users such as user IDs, password, and banking account, that data will be used for their personal interests. Average internet user will be easily trapped by phishers due to the similarity of the websites they visit to the original websites. Because there are several attributes that must be considered, most of internet user finds it difficult to distinguish between an authentic website or not. There are many ways to detecting a phishing website, but the existing phishing website detection system is too time-consuming and very dependent on the database it has. In this research, the focus of Hadoop MapReduce is to quickly retrieve some of the attributes of a phishing website that has an important role in identifying a phishing website, and then informing to users whether the website is a phishing website or not.
35
Trisno, Syahrul Nugraha, Achmad Ubaidillah, and Kunto Aji Wibisono. "SMART TROLLY DESIGN BASED ON MARKER DETECTION." MULTITEK INDONESIA 15, no. 1 (October 4, 2021): 43–53. http://dx.doi.org/10.24269/mtkind.v15i1.2429.
Full textAbstract:
In this modern era, robots are very instrumental in helping the human work and even replace their work. From the various human works, humans will need a trolley to carry goods. As in supermarkets, people will need a trolley to make it easier to carry groceries and other luggage. But with a trolley that is commonly used, users must encourage the trolley to move so that it reduces hand activity to do other activities. Therefore, we need a trolley that can move to follow the user automatically, so the user no longer needs to push the trolley, and the user's hand can be more free to do other activities. This research discusses about trolley robot using marker detection. With the application of this method will help the robot determine the object so as to facilitate the movement of the robot to follow the user. In the testing process carried out in the study, the system accuracy in detecting markers on objects was 70%.
36
Yakovyna, Vitalii, and Bohdan Uhrynovskyi. "User-perceived Response Metrics in Android OS for Software Aging Detection." Vìsnik Nacìonalʹnogo unìversitetu "Lʹvìvsʹka polìtehnìka". Serìâ Ìnformacìjnì sistemi ta merežì 9 (June 10, 2021): 32–43. http://dx.doi.org/10.23939/sisn2021.09.032.
Full textAbstract:
Mobile systems and devices including Android are vulnerable to the effects of software aging which are manifested in performance degradation during long run-time. It is important to identify efficient system and user interface metrics for detecting and counteracting the software aging effects. The aging metrics used in researches of the Android operating system do not take into account the aging processes in user applications. Therefore, this paper discusses two new graphical user interface metrics that allow to track performance degradation and user applications response time: Frame Draw Time and Janky Frames (dropped or delayed frames). Test framework was implemented to perform stress testing of mobile applications in the Android operating system, to collect system state data during stress test performing and to map obtained raw data into time series. Calculated time series are used for further analysis and study of system and graphical user interface metrics. The considered metrics have been compared to the previously used Android Activity Launch Time metric and RAM usage metrics. Practical results have shown that Frame Draw Time and Janks Frames metrics provide data, which can be useful in most scenarios of mobile application using. Therefore, it is proposed to use the two new metrics in combination with other previously used metrics to detect aging trends in the system state and to study the phenomenon of software aging in general. It is noted that the Frame Draw Time metric value can be mapped to states with determined thresholds for transition between these states. These states and thresholds provide the possibility of developing mathematical models based on Markov chains or forecasting the time to aging-failure using regression methods. The need of further study of the correlations between Frame Draw Time metric, Janky Frames metric and metrics of memory usage by different system processes has been identified. Thus, the expediency of using the proposed metrics in future studies of the aging phenomenon in the Android operating system is substantiated, in particular, the effectiveness of the proposed metrics could be checked for different mobile use cases and for different types of mobile applications.
37
Chen, Shuo, Haojie Li, Lanjie Zhang, Mingyu Zhou, and Xuehua Li. "Block Sparse Bayesian Learning Based Joint User Activity Detection and Channel Estimation in Grant-Free MIMO-NOMA." Drones 7, no. 1 (December 31, 2022): 27. http://dx.doi.org/10.3390/drones7010027.
Full textAbstract:
In the massive machine type of communication (mMTC), grant-free non-orthogonal multiple access (NOMA) is receiving more and more attention because it can skip the complex grant process to allocate non-orthogonal resources to serve more users. To address the limited wireless resources and substantial connection challenges, combining grant-free NOMA and multiple-input multiple-output (MIMO) is crucial to further improve the system’s capacity. In the grant-free MIMO-NOMA system, the base station should obtain the relevant information of the user before data detection. Thus, user activity detection (UAD) and channel estimation (CE) are two problems that should be solved urgently. In this paper, we fully consider the sparse characteristics of signals and the spatial correlation between multiple antennas in the grant-free MIMO-NOMA system. Then, we propose a spatial correlation block sparse Bayesian learning (SC-BSBL) algorithm to address the joint UAD and CE problems. First, by fully mining the block sparsity of signals in the grant-free MIMO-NOMA system, we model the joint UAD and CE problem as a three-dimensional block sparse signal recovery problem. Second, we derive the cost function based on the hierarchical Bayesian theory and spatial correlation. Finally, to estimate the channel and the set of active users, we optimize the cost function with fast marginal likelihood maximization. The simulation results indicate that, compared with the existing algorithms, SC-BSBL can always fully use the signal sparsity and spatial correlation to accurately complete UAD and CE under various user activation probabilities, SNRs, and the number of antennas. The normalized mean square error of CE can be reduced to 0.01, and the UAD error rate can be less than 10−5.
38
Kamble, Kunal, Pranit Jadhav, Atharva Shanware, and Pallavi Chitte. "Smart Surveillance System for Anomaly Recognition." ITM Web of Conferences 44 (2022): 02003. http://dx.doi.org/10.1051/itmconf/20224402003.
Full textAbstract:
Situation awareness is the key to security. Surveillance systems are installed in all places where security is very important. Manually observing all the surveillance footage captured is a monotonous and time consuming task. Security can be defined in different terms in different conditions like violence detection, theft identification, detecting harmful activities etc. In crowded public places the term security covers almost all type of unusual events. To eliminate the tedious manual surveillance we have developed a smart surveillance which will detect an anomaly and alert the user and authority without any human interference. It is a very critical issue in a smart surveillance system to instantly detect an anomalous behaviour in video surveillance system. In this project, a unified framework based on deep neural network framework is proposed to detect anomalous activities. This neural network framework consists of (a) an object detection module, (b) an object discriminator and tracking module, (c) an anomalous activity detection module based on recurrent neural network. The system is a web application where user can apply for three different security services namely motion detection, fall detection and anomaly detection which is applicable for monitoring different environment like homes, roads, offices, schools, shops, etc. On detection of anomalous activity the system will notify the user and responsible authority regarding the anomaly through mail with an anomaly detected frame attachment.
39
Et.al, D. Priyadarshini. "A Novel Technique for IDS in Distributed Data Environment Using Merkel Based Security Mechanism for Secure User Allocation." Turkish Journal of Computer and Mathematics Education (TURCOMAT) 12, no. 3 (April 11, 2021): 4284–97. http://dx.doi.org/10.17762/turcomat.v12i3.1720.
Full textAbstract:
Multiple corporations and people frequently launching their data in the cloud environment. With the huge growth of data mining and the cloud storage paradigm without checking protection policies and procedures that can pose a great risk to their sector. The data backup in the cloud storage would not only be problematic for the cloud user but also the Cloud Service Provider (CSP). The unencrypted handling of confidential data is likely to make access simpler for unauthorized individuals and also by the CSP. Normal encryption algorithms need more primitive computing, space and costs for storage. It is also of utmost importance to secure cloud data with limited measurement and storage capacity. Till now, different methods and frameworks to maintain a degree of protection that meets the requirements of modern life have been created. Within those systems, Intrusion Detection Systems (IDS) appear to find suspicious actions or events which are vulnerable to a system's proper activity. Today, because of the intermittent rise in network traffic, the IDS face problems for detecting attacks in broad streams of links. In existing the Two-Stage Ensemble Classifier for IDS (TSE-IDS) had been implemented. For detecting trends on big data, the irrelevant data characteristics appear to decrease both the velocity of attack detection and accuracy. The computing resource available for training and testing of the IDS models is also increased. We have put forward a novel strategy in this research paper to the above issues to improve the balance of the server load effectively with protected user allocation to a server, and thereby minimize resource complexity on the cloud data storage device, by integrating the Authentication based User-Allocation with Merkle based Hashing-Tree (AUA-MHT) technique. Through this, the authentication attack and flood attack are detected and restrict unauthorized users. By this proposed model the cloud server verifies, by resolving such attacks, that only approved users are accessing the cloud info. The proposed framework AUA-MHT performs better than the existing model TSE-IDS for parameters such as User Allocation Rate, Intrusion Detection Rate and Space Complexity
40
Akhriana, Asmah, and Andi Irmayana. "WEB APP PENDETEKSI JENIS SERANGAN JARINGAN KOMPUTER DENGAN MEMANFAATKAN SNORT DAN LOG HONEYPOT." CCIT Journal 12, no. 1 (February 6, 2019): 85–96. http://dx.doi.org/10.33050/ccit.v12i1.604.
Full textAbstract:
Along with the current development of Information Technology is always changing to make the security of an information is very important, especially on a network connected to the internet. But what is unfortunate is that the imbalance between each development of a technology is not accompanied by developments in the security system itself, so that there are quite a lot of systems that are still weak and have to be increased by the security wall. This study aims to design a Web-based App interface to facilitate users or administrators in securing network computers from various types of attacks. The Instrusion detection system (IDS) method is used to detect suspicious activity in a system or network using snort and honeypot. Honeypot is built on a computer along with Apache, MySQL, and Snort. Honeypot will act as a target to attract attackers and log information from the attacker and snort to apply the rules made from the web. The functional system will then be tested using the black box testing method. The results of this study concluded that Web App-based interfaces that are created can be used to help users and administrators in maintaining data and information on server computers from various types of attacks on computer networks
41
Bouali, Chaima, Olivier Habert, and Abderrahim Tahiri. "In Situ Abnormal Behaviours Detection." Modelling, Measurement and Control C 81, no. 1-4 (December 31, 2020): 1–6. http://dx.doi.org/10.18280/mmc_c.811-401.
Full textAbstract:
This work describes a ‘detection of abnormal activities and health-related changes’ system for an elderly person at her/his home. The analysis is based on the data collected by a domotic box of the market. The box was initially designed to continuously recognize the owner’s daily activities in order to anticipate anomalies and consequently prevent health complications and enhance the rate of disease prevention. The box uses non-intrusive home automation sensors to detect the activity level of the occupants. It is equipped also with other technologies, including humidity sensors, bed and chair sensors to name a few. In order to build a system capable of intercepting warning signs for early intervention, we adopt a Hidden Markov Model based approach that we will initialize beforehand with the activity sequences of the user within a given period. The outcomes of the model paves the way for deducting the final judgement and reporting a relevant context-aware alert to healthcare service experts. Other statistical processes might complete this behavioural analysis later on to enhance the alerts accuracy.
42
Shelke, Sagar, and Baris Aksanli. "Static and Dynamic Activity Detection with Ambient Sensors in Smart Spaces." Sensors 19, no. 4 (February 16, 2019): 804. http://dx.doi.org/10.3390/s19040804.
Full textAbstract:
Convergence of Machine Learning, Internet of Things, and computationally powerful single-board computers has boosted research and implementation of smart spaces. Smart spaces make predictions based on historical data to enhance user experience. In this paper, we present a low-cost, low-energy smart space implementation to detect static and dynamic human activities that require simple motions. We use low-resolution (4 × 16) and non-intrusive thermal sensors to collect data. We train six machine learning algorithms, namely logistic regression, naive Bayes, support vector machine, decision tree, random forest and artificial neural network (vanilla feed-forward) on the dataset collected in our lab. Our experiments reveal a very high static activity detection rate with all algorithms, where the feed-forward neural network method gives the best accuracy of 99.96%. We also show how data collection methods and sensor placement plays an important role in the resulting accuracy of different machine learning algorithms. To detect dynamic activities in real time, we use cross-correlation and connected components of thermal images. Our smart space implementation, with its real-time properties, can be used in various domains and applications, such as conference room automation, elderly health-care, etc.
43
Ahmed, Arshed, Muhammad Sajjad Khan, Noor Gul, Irfan Uddin, Su Min Kim, and Junsu Kim. "A Comparative Analysis of Different Outlier Detection Techniques in Cognitive Radio Networks with Malicious Users." Wireless Communications and Mobile Computing 2020 (December 9, 2020): 1–18. http://dx.doi.org/10.1155/2020/8832191.
Full textAbstract:
In a cognitive radio (CR), opportunistic secondary users (SUs) periodically sense the primary user’s (PU’s) existence in the network. Spectrum sensing of a single SU is not precise due to wireless channels and hidden terminal issues. One promising solution is cooperative spectrum sensing (CSS) that allows multiple SUs’ cooperation to sense the PU’s activity. In CSS, the misdetection of the PU signal by the SU causes system inefficiency that increases the interference to the system. This paper introduces a new category of a malicious user (MU), i.e., a lazy malicious user (LMU) with two operating modes such as an awakened mode and sleeping mode. In the awakened mode, the LMU reports accurately the PU activity like other normal cooperative users, while in the sleeping mode, it randomly reports abnormal sensing data similar to an always yes malicious user (AYMU) or always no malicious user (ANMU). In this paper, statistical analysis is carried out to detect the behavior of different abnormal users and mitigate their harmful effects. Results are collected for the different hard combination schemes in the presence of the LMU and opposite categories of malicious users (OMUs). Simulation results collected for the error probability, detection probability, and false alarm at different levels of the signal-to-noise ratios (SNRs) and various contributions of the LMUs and OMUs confirmed that out of the many outlier detection tests, the median test performs better in MU detection by producing minimum error probability results in the CSS. The results are further compared by keeping minimum SNR values with the mean test, quartile test, Grubbs test, and generalized extreme studentized deviate (GESD) test. Similarly, performance gain of the median test is examined further separately in the AND, OR, and voting schemes that show minimum error probability results of the proposed test as compared with all other outlier detection tests in discarding abnormal sensing reports.
44
Dvoynikova, Anastasiya, Ildar Kagirov, and Alexey Karpov. "Analytical review of methods for automatic detection of user engagement in virtual communication." Information and Control Systems, no. 5 (October 28, 2022): 12–22. http://dx.doi.org/10.31799/1684-8853-2022-5-12-22.
Full textAbstract:
Introduction: The solution of the task of the recognition and assessment of user engagement in the acts of human-machine interaction or telecommunication, achieved through the use of automatic means, is highly important in computer recognition of human psycho-emotional states. This is necessary for e-learning, business and entertainment applications design. Purpose: To conduct a comparative analysis of the current information support in the field of automatic recognition and assessment of user involvement in human-machine interaction or virtual communication, as well as to establish a methodology for building a data body based on the idea of multimodal communication. Results: The conducted analysis of research papers has shown that in most existing databases there is a substantial lack of data for natural online communication. Moreover, not all databases contain different modalities in “human-machine-human” communication system. Text and audio modalities turn out to be important for a multilevel engagement classification task, aimed at the determination of engagement intensity. It is also promising to take into account “body language” features, such as facial expressions, movements of the body and the head, gestures. For the correct assessment of involvement, an engagement database must contain meta-data on the psycho-emotional states of communicants. Neural network-based approaches to the automatic detection of user engagement show the best performance. Practical relevance: Based on the obtained analytical conclusions, the authors of the paper are going to elaborate an original software system for automatic recognition of user engagement, and to collect a data set for machine learning purposes. The presented review formulates basic requirements for such systems and contributes to the solution of the problem of automatic recognition of psycho-emotional states. Discussion: The survey leads to the conclusion that the notion of engagement as understood in studies on automatic emotion recognition differs from that used in psychology. User (or communicant) engagement in terms of info- and communicative sphere implies the manifestation of a person's mental activity level (emotional, cognitive, and behavioral components) changing dynamically while interacting with another person or computer system.
45
Ando, Bruno, Salvatore Baglio, Salvatore Castorina, Ruben Crispino, and Vincenzo Marletta. "An Assistive Technology Solution for User Activity Monitoring Exploiting Passive RFID." Sensors 20, no. 17 (September 1, 2020): 4954. http://dx.doi.org/10.3390/s20174954.
Full textAbstract:
Population ageing is having a direct influence on serious health issues, including hampered mobility and physical decline. Good habits in performing physical activities, in addition to eating and drinking, are essential to improve the life quality of the elderly population. Technological solutions, aiming at increasing awareness or providing reminders to eat/drink regularly, can have a significant impact in this scenario. These solutions enable the possibility to constantly monitor deviations from users’ normal behavior, thus allowing reminders to be provided to users/caregivers. In this context, this paper presents a radio-frequency identification (RFID) system to monitor user’s habits, such as the use of food, beverages, and/or drugs. The device was optimized to fulfill specifications imposed by the addressed application. The approach could be extended for the monitoring of home appliances, environment exploitation, and activity rate. Advantages of the approach compared to other solutions, e.g., based on cameras, are related to the low level of invasiveness and flexibility of the adopted technology. A major contribution of this paper is related to the wide investigation of system behavior, which is aimed to define the optimal working conditions of the system, with regards to the power budget, user (antenna)-tag reading range, and the optimal inter-tag distance. To investigate the performance of the system in tag detection, experiments were performed in a scenario replicating a home environment. To achieve this aim, specificity and sensitivity indexes were computed to provide an objective evaluation of the system performance. For the case considered, if proper conditions are meet, a specificity value of 0.9 and a sensitivity value of 1 were estimated.
46
Zheng, Panpan, Shuhan Yuan, and Xintao Wu. "SAFE: A Neural Survival Analysis Model for Fraud Early Detection." Proceedings of the AAAI Conference on Artificial Intelligence 33 (July 17, 2019): 1278–85. http://dx.doi.org/10.1609/aaai.v33i01.33011278.
Full textAbstract:
Many online platforms have deployed anti-fraud systems to detect and prevent fraudulent activities. However, there is usually a gap between the time that a user commits a fraudulent action and the time that the user is suspended by the platform. How to detect fraudsters in time is a challenging problem. Most of the existing approaches adopt classifiers to predict fraudsters given their activity sequences along time. The main drawback of classification models is that the prediction results between consecutive timestamps are often inconsistent. In this paper, we propose a survival analysis based fraud early detection model, SAFE, which maps dynamic user activities to survival probabilities that are guaranteed to be monotonically decreasing along time. SAFE adopts recurrent neural network (RNN) to handle user activity sequences and directly outputs hazard values at each timestamp, and then, survival probability derived from hazard values is deployed to achieve consistent predictions. Because we only observe the user suspended time instead of the fraudulent activity time in the training data, we revise the loss function of the regular survival model to achieve fraud early detection. Experimental results on two real world datasets demonstrate that SAFE outperforms both the survival analysis model and recurrent neural network model alone as well as state-of-theart fraud early detection approaches.
47
Sara, Meghshanth. "Stress Detection Smartwatch." International Journal for Research in Applied Science and Engineering Technology 10, no. 7 (July 31, 2022): 3796–802. http://dx.doi.org/10.22214/ijraset.2022.45865.
Full textAbstract:
Abstract: When a person is unable to handle their circumstances, responsibilities, and workload, stress is a natural emotion that is produced. A person's physical and mental health may suffer when the body is triggered, which can be deadly. The physical impacts of stress on a person's body can include an increase in blood pressure, a rapid heartbeat, increased muscle tension, headaches, a decrease in bodily immunity functions, and a decrease in sleepiness, among other things. The latest technology, known as smartwatches, provides the user with easy access to mobile features. Users can employ the stress-detecting capabilities of high-end smartwatches. Although they can be used to understand things better, these stress applications for smartwatches are not precise in how they operate. Heart rate variability, or HRV, is used by smartwatches and involves the intervals between each heartbeat that the sensor records. A person who has a low HRV is likely under stress. Although stress applications may not be as precise as medical equipment, they are dependable when necessary because there is a good likelihood that the data is accurate. An Electro Dermal Activity (EDA) sensor, found in some smartwatches, monitors tension by electrically altering the amount of sweat on our skin. You must spend two minutes with your palm on the watch dial to achieve the same. As an increase in heart rate is a direct outcome of stress, stress is recognized in the project utilizing heart rate. Since it is also an immediate outcome of stress, heart rate is used in the implementation. In this sector, mobile applications give users a way to explore this data graphically or in greater detail. The user of mobile applications might utilize them for medical purposes and to understand the data
48
Zhang, Zhaoji, Ying Li, Chongwen Huang, Qinghua Guo, Lei Liu, Chau Yuen, and Yong Liang Guan. "User Activity Detection and Channel Estimation for Grant-Free Random Access in LEO Satellite-Enabled Internet of Things." IEEE Internet of Things Journal 7, no. 9 (September 2020): 8811–25. http://dx.doi.org/10.1109/jiot.2020.2997336.
Full text
49
Damkliang, Kasikrit, Jarutas Andritsch, Krittamate Khamkom, and Nanida Thongthep. "A System for Sleepwalking Accident Prevention Utilizing the Remote Sensor of Wearable Device." ECTI Transactions on Computer and Information Technology (ECTI-CIT) 13, no. 2 (March 14, 2020): 160–69. http://dx.doi.org/10.37936/ecti-cit.2019132.184442.
Full textAbstract:
Sleepwalking is a type of sleep disorder which originates during deep sleep and results in walking state and performing series of complex behaviors or actions while sleeping. In some cases, sleepwalking patients can injure themselves from their actions such as driving a car or climbing out of a window. In addition, to wake up the sleepwalkers can be difficult. The suddenly waking up and can cause them to be confused or even attack the person who wakes them. Therefore, detecting the sleepwalking incident in an early state can help the caretaker or family members to stop the patients before they harm themselves from any strange, inappropriate, or violent behaviors. In this research, we present a prototype system of sleepwalking detection algorithm and notification system using smart device which work coordinating with wearable device. There are two main groups of users; patients and caretakers. User Activity Sensor (UAS) in the wearable device is utilized for detecting User Activity Data (UAD) which is unusual activities of inducing a sleepwalking patient provided by the Remote Sensor SDK. The system returns the patient UAD states consisting of standing, walking, and running. The smart device accepts the UAD states from the wearable device, performs sleepwalking detection algorithms then, alarms caretakers when the sleepwalking state has already invoked. The system is implemented, built, tested and deployed. The threefold experimental measurement of physical user activites have been performed to validate our proposed sleepwalking detection algorithms. The system correctly detects the sleepwalking states and notifies the caretaker.
50
Yang, Taehun, Sang-Hoon Lee, and Soochang Park. "AI-Aided Individual Emergency Detection System in Edge-Internet of Things Environments." Electronics 10, no. 19 (September 28, 2021): 2374. http://dx.doi.org/10.3390/electronics10192374.
Full textAbstract:
Recently, many disasters have occurred in indoor places. In order to rescue or detect victims within disaster scenes, vital information regarding their existence and location is needed. To provide such information, some studies simply employ indoor positioning systems to identify each mobile device of victims. However, their schemes may be unreliable, since people sometimes drop their mobile devices or put them on a desk. In other words, their methods may find a mobile device, not a victim. To solve this problem, this paper proposes a novel individual monitoring system based on edge intelligence. The proposed system monitors coexisting states with a user and a smart mobile device through a user state detection mechanism, which could allow tracking through the monitoring of continuous user state switching. Then, a fine-grained localization scheme is employed to perceive the precise location of a user who is with a mobile device. Hence, the proposed system is developed as a proof-of-concept relying on off-the-shelf WiFi devices and reusing pervasive signals. The smart mobile devices of users interact with hierarchical edge computing resources to quickly and safely collect and manage sensing data of user behaviors with encryption by cipher-block chaining, and user behaviors are analyzed via the ensemble paradigm of three machine learning technologies. The proposed system shows 98.82% prevision for user activity recognition, and 96.5% accuracy for user localization accuracy is achieved.