Tesi sul tema "Internet of Medical Things (IoMT)"

Epilepsy affects up to 1% of the world's population and approximately 2.5 million people in the United States. A considerable portion (30%) of epilepsy patients are refractory to antiepileptic drugs (AEDs), and surgery can not be an effective candidate if the focus of the seizure is on the eloquent cortex. To overcome the problems with existing solutions, a notable portion of biomedical research is focused on developing an implantable or wearable system for automated seizure detection and control. Seizure detection algorithms based on signal rejection algorithms (SRA), deep neural networks (DNN), and neighborhood component analysis (NCA) have been proposed in the IoMT framework. The algorithms proposed in this work have been validated with both scalp and intracranial electroencephalography (EEG, icEEG), and demonstrate high classification accuracy, sensitivity, and specificity. The occurrence of seizure can be controlled by direct drug injection into the epileptogenic zone, which enhances the efficacy of the AEDs. Piezoelectric and electromagnetic micropumps have been explored for the use of a drug delivery unit, as they provide accurate drug flow and reduce power consumption. The reduction in power consumption as a result of minimal circuitry employed by the drug delivery system is making it suitable for practical biomedical applications. The IoMT inclusion enables remote health activity monitoring, remote data sharing, and access, which advances the current healthcare modality for epilepsy considerably.

L'objectif de ma thèse est d'analyser les caractéristiques des signaux inertiels et physiologiques qui générés par les mouvements inhabituels des patients lorsque la crise survient et de développer un algorithme pour détecter la crise. Notre approche dans le chapitre III commence par dériver la moyenne quadratique pour l'ACM et le Gyro, suivie de la normalisation de signaux entiers dans la même plage puis de l'agrégation en un seul signal. Le contrôle du graphique avec ses limites supérieure et inférieure est défini lors de la phase au repos et utilisé pour détecter les crises anormales et pour déclencher une alarme. La procédure dans le chapitre IV de détection s'exécute dans un dispositif de collecte de données portable et déclenche une alarme. Cet algorithme est basé sur la dérivation des mesures instantanées dans une plage de données glissante contenant des mesures inertielles de 3D (ACM), 3D Gyro et de EMG. La différence entre la puissance estimée et la puissance mesurée est utilisé comme entrée pour l'algorithme de détection basé sur la carte de contrôle de Shewhart. Lorsque la différence entre la puissance prévue et la puissance dérivée dépasse les limites [limite inférieure/supérieure] pour plusieurs créneaux consécutifs, une alarme est déclenchée. L'approche que nous proposons permet une bonne détection avec un FAR de 4\% et une sensibilité de 97\%. Notre modèle dans Le chapitre V commence par réduire la dimension des données collectées grâce à l'utilisation de la moyenne quadratique pour dériver un signal de 3D ACM et un signal du 3D Gyro. Avec les 3 signaux dérivés (ACM, Gyro et EMG), nous appliquons le TVP pour dériver un signal utilisé comme entrée pour le mécanisme de détection d'anomalie. La version robuste du z-score est appliquée sur le signal résultant produit pour détecter les déviations associées aux crises avant de déclencher une alarme. Nos résultats expérimentaux montrent que notre approche proposée est robuste contre les mouvements nocturnes et atteint un haut niveau de précision de détection avec un faible FAR. Ensuite, nous comparons les performances de notre approche avec la méthode des passages à zéro calculées à partir de sEMG. Notre approche montre que la précision de détection à l'aide du VTP surpasse le nombre de passages à zéro sur une plage glissante de chevauchement de 1 seconde. Dans le chapitre VI, Les appareils IoMT sont utilisés pour acquérir ACM, Gyro et EMG et pour transmettre les mesures à LPU pour traitement. Lorsque le LPU détecte des changements anormaux dans les mesures, il déclenche une alarme. Notre approche proposée utilise SVM avec option de rejet pour distinguer les crises des activités normales de la vie quotidienne. Les caractéristiques présentant des changements physiologiques de l'activité musculaire et les données inertielles ont été extraites dans LPU et sont utilisées comme entrée pour l'algorithme de détection. L'option de rejet dans SVM est utilisée pour améliorer la fiabilité du système de surveillance et pour réduire les fausses alarmes, où l'utilisateur est averti et a la possibilité de supprimer l'alarme dans son smartphone en l'absence de saisie. Les expériences menées ont prouvé que notre approche proposée peut atteindre une bonne précision pour distinguer les crises des activités normales avec seulement 4% de taux de FAR. Dans chapitre VII, nous proposons un cadre pour empêcher une MitM de perturber les opérations et interdire le déclenchement d'alarmes par le système de surveillance à distance des soins de santé. Pour réduire la consommation d'énergie lours de la transmission normale des données et préserver la confidentialité des données de santé, notre système transmet une signature de plus petite taille dérivée des données acquises avec un code d'authentification de message, où la clé est dérivée de RSSI. Nos résultats expérimentaux montrent que notre approche peut atteindre une précision de détection élevée avec un faible FAR de 3%<br>The goal of my PhD is to investigate the characteristics of inertial and physiological signals via IoMT systems generated by epileptic seizure and to develop an algorithm to detect the seizure. The focus of the algorithms lies in nocturnal seizures where the risk of SUDEP is high because the patients are unsupervised while sleeping. In chapter III analysis we propose an IoMT platform for seizure detection. The proposed framework approach starts by deriving the RMS for ACM and Gyro, followed by the normalization of whole signals (ACM, Gyro and EMG) in the same range, and aggregate all into one signal. The chart’s control with its upper and lower limits are derived in the training phase and used to detect abnormal seizures and to raise an alarm. In chapter IV Our proposed algorithm is based on deriving instantaneous power measurements in a sliding window containing 3D ACM or 3D Gyro or EMG. The residual between forecasted and measured power is used as input for the detection algorithm based on Shewhart Control Chart (SCC). When the difference between forecasted and derived power exceeds chart limits [lower, upper] for several consecutive slots, an alarm is raised. Our proposed approach provides low FAR (4%) and sensitivity of 97%. In Chapter V our proposed method starts by reducing the dimension of collected data using RMS to derive one signal from 3D ACM and one signal from 3D Gyro. With the derived 3 collected signals (ACM, Gyro and EMG), we apply VTP to derive one signal used as input for anomaly detection mechanism. The robust version of z-score is applied on the resulting product signal to detect deviations associated with seizures before raising an alarm. Our experimental results show that our proposed approach is robust against nocturnal movements and achieves a high level of detection accuracy with low false alarm rate. Afterward, we compare the performance of our approach with the zero-crossings method calculated from sEMG. Our approach shows that the detection accuracy using VTP outperforms zero-crossing count over an overlapping sliding window of 1 second. In chapter VI, we propose an approach using the IoMT devices to acquire EMG, ACM and Gyro data and to transmit the measurements to a LPU for processing. When the LPU detects abnormal changes in the measurements, it raises an alarm for assistant. Our proposed approach uses SVM with reject option to distinguish seizures from normal daily life activity. Features presenting physiological changes of muscular activity and inertial data were extracted in LPU and are used as input for the detection algorithm. The reject option in SVM is used to enhance the reliability of the monitoring system and to reduce FAR, where the user is notified and can discard the alarm in his smartphone in the absence of seizure. The conducted experiments proved that our proposed approach could achieve a good accuracy with only 4% of false alarm rate. Finally, since we are using IoMT sensors, which are susceptible to data security issues. We proposed a solution to prevent Man in the Middle (MitM) attack, which can identify healthcare emergencies of monitored patients and replay normal physiological data to prevent the system from raising an alarm. In this chapter, we propose a framework to prevent a MitM from disrupting the operations and prohibiting the remote healthcare monitoring system. To reduce energy consumption for normal data transmission, and preserve the privacy of health data, our framework transmits a smaller size signature derived from acquired data with message authentication code, where the key is derived from Received Signal Strength Indication (RSSI). Our experimental results for emergency detection show that our approach can achieve a high detection accuracy with a low false alarm rate of 3%

In questa tesi, si partirà con un'introduzione generale all'Internet of Things focalizzando l'attenzione sulla struttura generale dell'architettura ed il suo funzionamento di base in una rete con molti altri dispositivi. Seguirà l'analisi del trend di questa tecnologia e la sua evoluzione nel tempo, con particolare attenzione all'architettura ed al suo successo ai giorni nostri. Verrà discussa l'industrializzazione che ha portato alla creazione delle Industrie 4.0, ovvero l'Internet of Things in ambito sensoristica applicato all'industria, alla robotica, ai Big Data che si occupano dell'archiviazione, all'acquisizione e all'analisi dei dati provenienti dai vari dispositivi, ai sistemi ciberfisici, alla connessione di tutti questi oggetti tra loro per la comunicazione e lo scambio delle informazioni ed infine alla realtà aumentata per il supporto nei vari processi industriali. Questi macroargomenti saranno lo spunto per introdurre il concetto di Internet of Medical Things. Con una breve panoramica sugli ospedali al giorno d'oggi, si vuol proporre una nuova concezione di ospedale dove vengono poste al centro dell'attenzione le esigenze del paziente e del personale medico, trattando nello specifico le tecnologie impiegate, i processi chirurgici, clinici e l’erogazione delle prestazioni sanitarie. Il discorso seguirà focalizzando l'attenzione anche su ambienti della medicina come la chirurgia, introducendo un luogo in cui migliaia di dispositivi connessi alla rete comunicano tra di loro. Si vedranno anche tutte le eventuali criticità e le varie sfide che bisognerà risolvere ed intraprendere per arrivare ad un corretto ed efficiente passaggio agli odierni ospedali concepiti per essere ospedali 4.0. Si concluderà con una riflessione su tutte queste tecnologie e la rivoluzione in ambito medico che promette cambiamenti che porteranno al nuovo concetto di Ospedale 4.0 su un’ottica di Internet of Medical Things.

Epileptic seizure presents a formidable threat to the life of its sufferers, leaving them unconscious within seconds of its onset. Having a mortality rate that is at least twice that of the general population, it is a true cause for concern which has gained ample attention from various research communities. About 800 million people in the world will have at least one seizure experience in their lifespan. Injuries sustained during a seizure crisis are one of the leading causes of death in epilepsy. These can be prevented by an early detection of seizure accompanied by a timely intervention mechanism. The research presented in this dissertation explores Kriging methods to exploit spatial correlations of electroencephalogram (EEG) Signals from the brain, for fast and accurate seizure detection in the Internet of Medical Things (IoMT) using edge computing paradigms, by modeling the brain as a three-dimensional spatial object, similar to a geographical panorama. This dissertation proposes basic, hierarchical and distributed Kriging models, with a deep neural network (DNN) wrapper in some instances. Experimental results from the models are highly promising for real-time seizure detection, with excellent performance in seizure detection latency and training time, as well as accuracy, sensitivity and specificity which compare well with other notable seizure detection research projects.

Ci troviamo in un mondo in costante cambiamento ed evoluzione, in particolar modo nel settore informatico. È proprio in questo continuo processo di evoluzione che spicca l’IoT ovvero Interent Of Things (Internet delle cose). Oggetti, anche di tutti i giorni, collegati ad Internet capaci di scambiarsi messaggi e di comunicare tra loro. Kevin Ashton, pioniere dell’IoT, dice che questa sarà la prossima rivoluzione tecnologica come lo è stato a suo tempo Internet. Tuttavia, come sarà discusso in questa tesi, alcuni ambiti di applicazione dell’IoT come il sistema medico ed ospedaliero non sono ancora del tutto uniformati ma anzi, presentano vari ostacoli nell’ottica di un sistema interoperabile ed intelligente. Per quanto riguarda quest’ultimo caso si parla di Internet of Medical Things(IoMT), Internet of Healthcare Things (IoHT) o ancora Medicina 4.0 (QuartaRivoluzione Industraile in ambito medico). Possiamo pensare ad un ospedale con vari dispositivi capaci di condividere dati ed informazioni tra loro e di mettere adisposizione questi dati in tempo reale al personale sanitario e al paziente anche a distanza.

The Internet of Things (IoT) is a technological paradigm that can be perceived as an evolution of the internet. It is a shift from the traditional way of connecting devices to the internet, both in number and diversity of connected devices. This significant and marked growth in the number and diversity of devices connected to the internet has prompted a rethink of approaches to interconnect devices. The growth in the number of connected devices is driven by emerging applications and business models and supported by falling device costs while the growth in the diversity is driven by the reduction in the cost of manufacturing these devices. This has led to an increase in the number of users (not limited to people) of the internet. According to statistics by the ITU, by the end of 2015, about 3.2 billion people were using the Internet. Significantly, 34% of households in developing countries had Internet access, with more than 80% of households in developed countries. This indicates that it is realistic to leverage the IoT in living spaces. Appreciating this potential, many sectors of society are already positioning themselves to reap the benefits of this great promise. Hence the health sector would do well to adopt this technological paradigm to enhance service delivery. One specific area where the health sector can benefit from the adoption of the IoT is in telemonitoring and the associated early response to medical emergencies. Statistics and research show that there are areas in the medical field, that still need improvement to enhance service delivery. The Nursing Times has summed up these areas into four categories. The first one is a need to have a regular observation of patients and their vital signs. Here, health service providers (SPs) need to adopt creative and non-obtrusive methods that will encourage patients' participation in the monitoring of these vital signs. As much as possible, vital signs readings should be taken at convenient locations and times. Therefore, devices that have consistent internet access and are usually a part of daily life for most patients, such as the mobile phones would prove to be a key enabler of regular observation of vital signs. Furthermore, miniaturization of the vital signs monitoring or sensing devices would be a key step towards realizing this scenario. A lot of work is already being done to miniaturize these devices and make them as much a part of daily life as possible, as evidenced by advancements in the field of fitness and wearables. To map this use to the medical field, a system needs to be created that would allow for the aggregation of these disparate measuring and monitoring devices with medical information management systems. The second potential area of improvement is in the early recognition of deterioration of the patients. With regular observation of patients, it is possible to recognize deterioration at its early stage. Taking cognizance of the different needs of the various stakeholders is important to achieve the intended results. The third potential area of improvement is in the communication among stakeholders. This has to do with identifying the relevant data that must be delivered to the stakeholders during the monitoring and management process. Lastly, effective response to medical concerns is the other potential area of improvement. It is noted that patients do not generally get the right response at the right time because the information does not reach the rightly qualified personnel in good time. The regular and real-time capture of vital signs data coupled with added analytics can enable IoT SPs to design solutions that automate the management and transmission of medical data in a timely manner. This work addresses how the medical sector can adopt IoT-based solutions to improve service delivery, while utilizing existing resources such as smartphones, for the transmission and management of vital signs data, availing it to stakeholders and improve communication among them. It develops a telemonitoring system based on IoT design approaches. The developed system captures readings of vital signs from monitoring devices, processes and manages this data to serve the needs of the various stakeholders. Additionally, intelligence was added to enable the system to interpret the data and make decisions that will help medical practitioners and other stakeholders (patients, caregivers, etc.) to more timely, consistently and reliably provide and receive medical services/assistance. Two end user applications were developed. A cloud-based web application developed using PHP, HTML, and JavaScript and an Android mobile application developed using Java programming language in Android studio. An ETSI standards-compliant M2M middleware is used to aggregate the system using M2M applications developed in Python. This is to leverage the benefits of the standards-compliant middleware while offering flexibility in the design of applications. The developed system was evaluated to assess whether it meets the requirements and expectations of the various stakeholders. Finally, the performance of the proposed telemonitoring system was studied by analyzing the delay on the delivery of messages (local notifications, SMS, and email) to various stakeholders to assess the contribution towards reducing the overall time of the cardiac arrest chain of survival. The results obtained showed a marked improvement (over 28 seconds) on previous work. In addition to improved performance in monitoring and management of vital signs, telemonitoring systems have a potential of decongesting health institutions and saving time for all the stakeholders while bridging most of the gaps discussed above. The captured data can also provide the health researchers and physicians with most of the prerequisite data to effectively execute predictive health thereby improving service delivery in the health sector.

Human body is a complex system organized at different levels such as cells, tissues and organs, which contributes to 11 important organ systems. The functional efficiency of this complex system is evaluated as health. Traditional healthcare is unable to accommodate everyone's need due to the ever-increasing population and medical costs. With advancements in technology and medical research, traditional healthcare applications are shaping into smart healthcare solutions. Smart healthcare helps in continuously monitoring our body parameters, which helps in keeping people health-aware. It provides the ability for remote assistance, which helps in utilizing the available resources to maximum potential. The backbone of smart healthcare solutions is Internet of Things (IoT) which increases the computing capacity of the real-world components by using cloud-based solutions. The basic elements of these IoT based smart healthcare solutions are called "things." Things are simple sensors or actuators, which have the capacity to wirelessly connect with each other and to the internet. The research for this dissertation aims in developing architectures for these things, focusing on IoT-based smart healthcare solutions. The core for this dissertation is to contribute to the research in smart healthcare by identifying applications which can be monitored remotely. For this, application-specific thing architectures were proposed based on monitoring a specific body parameter; monitoring physical health for family and friends; and optimizing the power budget of IoT body sensor network using human body communications. The experimental results show promising scope towards improving the quality of life, through needle-less and cost-effective smart healthcare solutions.

The medical health industry is entering a new era and technology will play a great role in this area. Equipment in hospitals is in many cases strictly dependent on technology that works. However, technology in the medical health industry will maybe become a bigger part of our private lifestyle. This lifestyle includes digital health apps, wearables and devices that track your daily physical routines with “Internet of things”. These ways of keeping track of your health can be used for private purposes, but also to complement medical studies with clinical results. This thesis will focus on how wearables can complement a medical study where patients with severe heart failure will use the smartwatch Apple Watch. This smartwatch will collect data on patients daily physical activity pattern and thereafter analyze this data in order to find activity patterns. This thesis intends to answer the questions How can wearables such as the Apple Watch benefit medical heart research? and what makes the Apple Watch a suitable wearable for the medical study at Lund’s University Hospital? Interviews were therefore held with medical heart researchers and addressed the purpose of the medical study and their choice of wearable. Thereafter, a examination of the Apple Watch was conducted and it together with the interview indicated that the Apple Watch in fact is a suitable wearable. Finally, an exportation process where data from the Apple Watch was done where the exported data then was decoded in Microsoft Excel. The purpose of this was to examine statements that were revealed in the interview. That being said, the thesis came to the conclusion that the Apple Watch contributes a lot when mixing complementing data from wearables with clinical records. Another conclusion was that this tracking device was suitable for the medical study. In what extension the Apple Watch is suitable, is yet unclear since the medical study is in need of further patients and research where one compares wearables against each other.

The number of Internet of Things (IoT) devices is forecast to grow to over 25 billion by 2030, with the healthcare IoT market projected to grow to 25.9% of IoT devices by 2028 worldwide. However, with new and growing technologies come new types of risks. Current risk assessment and risk management methods haven’t been designed to anticipate or predict these risks. IoT risks relate to openness and lack of standardisation, linking and connectivity between the devices and the lack of skilled support for IoT devices and networks. These factors put medical IoT devices and, by extension, their users at risk from cyber threats. Additionally, the attack surface for the medical IoT has not been fully mapped, nor have the risks been fully assessed. The lack of coverage means increased risk for manufacturers, medical facilities, and potentially, patients. This project evaluates the effectiveness of how new and emerging wireless and connected medical devices can be managed and analysed through a digital forensic framework. An initial analysis of the currently available frameworks showed that they did not address the nuances of implementing a wireless or connected medical device into a healthcare organisation. Digital forensic frameworks that were deemed relevant to wireless medical devices were selected and tested against several currently available wireless medical devices. Four frameworks were tested across four devices each. The outcome was that none of the frameworks was fully able to effectively manage wireless medical devices (at least in terms of the objectives of digital forensics), with each missing elements that would aid an investigator or a hospital organisation in the case of a cyber-related incident. These results led to the synthesis and testing of a framework that addressed the missing elements. The framework emphasises forensic readiness planning and risk management. The synthesised framework was tested against a new device. The results of the test found that the synthesised framework was effective in both the proactive digital forensics approach and reactive approach. The testing found that the framework performed better than the other tested frameworks, containing additional phases and steps that were advantageous in preparing and reacting to incidents involving wireless medical devices.

This thesis describes how a solution can be built to detect human flu-like symptoms. Flu-like symptoms are important to detect to prevent Covid-19 [6]. As people are returning to work there is a need for a simple way of detecting flu-like symptoms to prevent the spread of Covid-19. Other than a solution, this thesis concluded how human flu-like symptoms can be detected, with cameras specifically. This is to know what symptoms are most likely to work for a prototype. The technique of cameras and thermal cameras made this project possible as well as the technique of a single-board computer. The technique of cloud-based services is also an important part of this project. This project has resulted in a novel prototype using a single-board computer, cameras, and various cloud-based services to detect and inform a person if he or she has a human flu-like symptom.

The emergency departments in Region Östergötland use pen and paper to a large extent when recording emergency care procedures and measurements. During treatment the patient should be the main focus. Because of this, recording of measurements done could be delayed or in worst case forgotten during stressful situations. The proposal of this project is the development of a prototype that tries to make the administrative work a passive procedure rather than an active one. The system developed uses a Raspberry Pi, along with Node-Red, which connects predefined patient data and medical records, with the clinical staff tending the patient. All these connections are initiated by mainly using RFID technology. The conclusion made with the developed system is that it should unload the staff with the recording of data and that it helps make a data logging a more passive work than today’s used methods. Along with a process that is easier to operate, the time spent on administrative work could be reduced with the proposed system.

The Internet of Medical Things (IoMT) paradigm is becoming mainstream in multiple clinical trials and healthcare procedures. It relies on novel, very accurate and compact sensing devices, network and communication infrastructures, opening previously unmatched possibilities of implementing data collection and continuous patient monitoring. Nevertheless, to fully exploit the potential of IoMT, some steps forward are needed. First, the edge-computing paradigm must be added to the picture. A certain level of near-sensor processing has to be enabled, to improve the scalability, portability, reliability and responsiveness of the IoMT nodes. Second, novel, increasingly accurate data analysis algorithms, such as those based on artificial intelligence and deep learning, must be exploited. To reach these objectives, designers, and programmers of IoMT nodes, have to face challenging optimization tasks, in order to execute fairly complex computing processes on low-power wearable and portable processing systems, with tight power and battery lifetime budgets. In this thesis, the implementation on resource-constrained computing platforms of a cognitive data analysis algorithm based on a convolutional neural network was explored. The treatment of cardiovascular disease and fitness tracking were chosen as use cases within the IoMT context to validate our approach. To minimize power consumption, an adaptivity layer has been added, the latter dynamically manages the hardware and software configuration of the device to adapt it at runtime to the required operating mode. The experimental results show that adapting the node setup to the workload at runtime can save up to 60% power consumption. The optimized and quantized neural network reaches an accuracy value higher than 97% for arrhythmia disorders detection and more than 97% for detecting some specific physical exercises on a wobble board.

L'Internet of Things (IoT) sta cambiando le nostre vite in un modo mai immaginato prima. A differenza del paradigma tradizionale, nel mondo dell'IoT tutte le cose sono considerate come oggetti intelligenti, i quali sono connessi l'uno con l'altro. Spaziando dagli elettrodomestici intelligenti alle città intelligenti, l'IoT ha anche aperto una nuova sfida nel settore sanitario, chiamata Internet of Medical Things (IoMT). Essa gioca un ruolo fondamentale nell'aggiornamento degli ospedali verso il modello di smart hospital. I dispositivi usati nell'IoMT sono generalmente interoperabili e possono essere connessi a un unico sistema scalabile quando appartengono allo stesso venditore. Questa dipendenza, tuttavia, presenta un collo di bottiglia in quasi tutti gli scenari di utilizzo pratico a causa di una vasta gamma di sensori e strumenti medici utilizzati in ambito ospedaliero al giorno d'oggi. Data la sua massima importanza, l'interoperabilità rimane al centro di numerose ricerche recenti. Quindi, partendo da questa criticità, l'obiettivo di questa tesi è di fare una proposta di integrazione efficace per il progetto Tracking for Care (T4C), in collaborazione con AUSL della Romagna e Ospedale Bufalini, e in particolare del dispositivo monitor a parametri vitali.

Метою доповіді є застосування бездротових мереж для пристроїв медичного інтернету речей. Пропонується використання різноманітних «розумних» пристроїв та датчиків для пацієнтів, які можуть на відстані вести моніторинг необхідних параметрів стану здоров’я і сповіщати лікаря про небажані зміни.

The tremendous upsurge in the size of datasets has started gaining momentum a decade ago in science, finance, and every slice of our everyday life. The same scenario of the data volume explosion also arose in medical healthcare, and the elaborate management and exhaustive exploration of these heterogeneous data play important roles in modern medical care services. Traditional healthcare systems have been unable to cope with this complicated situation. After the popularity of digitized medical records and the evolution of the worldwide network interconnection, cloud computing has been proposed and successfully applied in healthcare with its advantages in competitive advantages, information sharing, and dynamic resources. However, along with the growing aspiration of patients, it is inevitable to gradually reform the structure of the healthcare system from the hospital-oriented centralized healthcare system to the patient-oriented distributed mobile healthcare systems (also termed as mHealth). Moreover, IoT (Internet of Things) provides an efficient and structured way to implement distributed patient-oriented mHealth systems, which inevitably leads to the exponential generation of medical data. To better adapt to the requirements (like time and energy consumption) of mHealth, edge computing has emerged as an effective implementation to complement and improve mobile healthcare systems supported by cloud computing. It is a big step to make healthcare systems more sensitive and flexible. Establishing the edge-based smart healthcare system is one of the best methods to alleviate the gigantic press on public medical care. This thesis aims to present the high-credibility edge analytic system for early medical intervention, covering every stage of the entire medical IoT ecosystem, which can be applied to non-specific or general disease treatments. This thesis summarizes the open issues for each stage within the system and further proposes corresponding solutions: from multi-view learning to improve learning performance to the implementation of interpretable results for medical prediction and analysis in conjunction with the outbreak of the COVID-19. And finally, under the consideration of the entire system architecture, security is guaranteed vertically interpretable analysis of edge distributed computing. These works cover almost all stages of the entire medical IoT ecosystem. We have given a variety of practical application scenarios and obtained the corresponding expected results through detailed and feasible experiments.

Computer and Information Science<br>Ph.D.<br>The growing ubiquity of modern wireless and mobile electronic devices has brought our daily lives with more convenience and fun. Today's smartphones are equipped with a variety of sensors and wireless communication technologies, which can support not only the basic functions like phone call and web browsing, but also advanced functions like mobile pay, biometric security, fitness monitoring, etc. Internet-of-Things (IoT) is another category of popular wireless devices that are networked to collect and exchange data. For example, the smart appliances are increasingly deployed to serve in home and office environments, such as smart thermostat, smart bulb, and smart meter. Additionally, implantable medical devices (IMD) is the typical type of modern wireless devices that are implanted within human body for diagnostic, monitoring, and therapeutic purposes. However, these modern wireless and mobile devices are not well protected compared with traditional personal computers (PCs), due to the intrinsic limitations in computation power, battery capacity, etc. In this dissertation, we first present the security and privacy vulnerabilities we discovered. Then, we present our designs to address these issues and enhance the security of smartphones, IoT devices, and IMDs. For smartphone security, we investigate the mobile phishing attacks, mobile clickjacking attacks and mobile camera-based attacks. Phishing attacks aim to steal private information such as credentials. We propose a novel anti-phishing scheme MobiFish, which can detect both phishing webpages and phishing applications (apps). The key idea is to check the consistency between the claimed identity and the actual identity of a webpage/app. The claimed identity can be extracted from the screenshot of login user interface (UI) using the optical character recognition (OCR) technique, while the actual identity is indicated by the secondary-level domain name of the Uniform Resource Locator (URL) to which the credentials are submitted. Clickjacking attacks intend to hijack user inputs and re-route them to other UIs that are not supposed to receive them. To defend such attacks, a lightweight and independent detection service is integrated into the Android operating system. Our solution requires no user or app developer effort, and is compatible with existing commercial apps. Camera-based attacks on smartphone can secretly capture photos or videos without the phone user's knowledge. One advanced attack we discovered records the user's eye movements when entering passwords. We found that it is possible to recover simple passwords from the video containing user eye movements. Next, we propose an out-of-band two-factor authentication scheme for indoor IoT devices (e.g., smart appliances) based on the Blockchain infrastructure. Since smart home environment consists of multiple IoT devices that may share their sensed data to better serve the user, when one IoT device is being accessed, our design utilizes another device to conduct a secondary authentication over an out-of-band channel (light, acoustic, etc.), to detect if the access requestor is a malicious external device. Unlike smartphones and IoT devices, IMDs have the most limited computation and battery resources. We devise a novel smartphone-assisted access control scheme in which the patient's smartphone is used to delegate the heavy computations for authentication and authorization. The communications between the smartphone and the IMD programmer are conducted through an audio cable, which can resist the wireless eavesdropping and other active attacks.<br>Temple University--Theses

Every year, one out of three adults over the age of 65 falls, and about 30% of the falls result in moderate to severe injuries. The high rate of fall-related hospitalizations and the fact that falls are a major source of morbidity and mortality in older adults have motivated extensive interdisciplinary clinical and engineering research with a focus on fall prevention. This research is aimed at developing a medical Cyber Physical System (CPS) composed of a human supervised mobile robot and ambient intelligence sensors to provide continuous evaluation of environmental risks in the home. As a preventive measure to avoid falls, we propose use of mobile robots to detect possible fall risks inside a house. As a step-up to that, we also define a control framework for intelligent, networked mobile robots to semi-autonomously perform assistive and preventive tasks. This framework is integrated in a smart home that provides monitoring and control capabilities of environmental conditions such as objects blocking pathways or uneven surfaces. The main outcome of this work is the realization of this system at Worcester Polytechnic Institute's (WPI) @Home testbed.

Thesis: S.M. in Engineering and Management, Massachusetts Institute of Technology, System Design and Management Program, 2018.<br>Cataloged from PDF version of thesis.<br>Includes bibliographical references (pages 64-66).<br>The Healthcare industry, just like any industry, is constantly racing to stay abreast with pace of technological innovations, especially at such a time where the industry is experiencing a strain on the global healthcare infrastructure. Specifically, the evolution of record management systems in the healthcare system has taken a slow and gradual transformation with each stage of transformation carrying over certain aspects and functions of previous stages. A survey of record management practices reveals that record management begun with paper-based records that have since partially been replaced with centralized Electronic Health Records (EHR). With the advent of Electronic Health Records enabled by distributed ledgers, we continue to see the inclusion of traditional paper-based functions beyond centralized EHR functions. Electronic data sharing in the healthcare ecosystem is constrained by interoperability challenges with different providers choosing to implement systems that respond to increasing their productivity. Prioritizing a patient-focused strategy during implementation of EHRs forces providers to implement systems that are more interoperable. A system engineering approach was adopted to guide the development and valuation of candidate architectures from Stakeholder analysis to concept generation and enumeration. Nine (9) key design decisions were selected with their combinations yielding 512 feasible hybrid architectures. In this paper, we proposed a hybrid EHR solution combining distributed ledger technologies and Internet of Medical Things, which contributes towards providing value-based healthcare. Leveraging properties of distributed ledgers and IoMT, the hybrid solution interconnects various data sources for health records to provide real-time record creation and monitoring whilst enabling data sharing and management in a secure manner.<br>by Paula Ingabire.<br>S.M. in Engineering and Management

In the late 1990's, when sophisticated personal computers and electronic devices with miniaturized sensors were being mass produced, the concept of ambient intelligence (AmI) emerged. An environment that has AmI is a space containing objects which includes technologies that are not visible to users, and which generates intelligent responses when appropriate. When people interact with an AmI environment, they intuitively use technologies according to their own needs and gain more awareness of their actions, thereby improving their quality of life, comfort, and empowerment. Currently, healthcare professionals work inside a complex adaptive system in which the clinical environment and the health status of patients vary dynamically, and resources are limited. This can generate an increasing number of adverse events as well as medical errors and consequently patients are more exposed to potential harm during a hospital stay. Many researchers are creating new AmI tools to overcome these challenges. This is especially important in intensive care units (ICUs), where there are seriously ill patients who need advanced infrastructure and equipment to receive continuous clinical monitoring and treatment in as safe a way as possible. Three out of every ten patients in an ICU suffer some type of clinical safety issue, which puts their lives at risk. In this context, the main aim of the work I present in this thesis is to develop an AmI environment for improving the efficiency of processes related to patient safety in ICUs. I have written this thesis with the collaboration of the clinical and engineering team of the Smart ICU at the Hospital Cl(n ic in Barcelona (HCB). That AmI environment is equipped mainly with technologies related to the Internet of Things (IoT) that provide an adaptive and dynamic distribution of clinical information based on the role and location of each professional as well as the clinical health status of patients. I divided the development of this thesis into three phases. Firstly, I designed, built, and tested a prototype to simulate the AmI environment in a laboratory setting, considering the main patient safety issues which arise in ICUs. I considered 5 patient safety issues: a code blue, a code red, a code pink, control of nosocomial infections and drug-related errors. Secondly, that prototype was adapted and implemented in a Smart ICU at HCB. Thirdly, I collected and analysed data generated by the AmI. It is important to highlight that part of the data collection and analysis related to the AmI environment took place during the SARS-CoV-2 epidemic (Covid- 19). To summarize, my thesis evaluates the efficiency of the use of new technologies to improve patient safety processes in critical care. It improves clinical and educational standards in terms of patient safety processes at the unit concerned. Moreover, it enables quantification of events related to patient safety as well as heightening awareness of them.<br>A finales de la década de 1990, cuando las computadoras personales y los dispositivos electrónicos se producían en masa, el concepto de inteligencia en el entorno (AmI – Ambient Intelligence en inglés) surgió. Un entorno que contiene AmI es un espacio con objetos que incluyen tecnologías, invisibles para los usuarios, y que les generan respuestas inteligentes cuando sea necesario. Actualmente, los profesionales sanitarios están trabajando dentro de un sistema complejo adaptativo en el que el entorno clínico y el estado de salud del paciente varían dinámicamente. Esto es especialmente importante en las Unidades de Cuidados Intensivos (UCIs), donde hay pacientes gravemente enfermos que necesitan infraestructuras y equipos avanzados para recibir monitorización de la forma más segura posible. En este contexto, el objetivo principal del trabajo que presento en esta tesis es desarrollar un entorno AmI para mejorar la eficiencia en los procesos relacionados con la seguridad del paciente en las UCIs. He elaborado esta tesis con la colaboración del equipo de la UCI inteligente del Hospital Clínic de Barcelona (HCB). El desarrollo de esta tesis se ha dividido en tres fases. En primer lugar, he diseñado, construido y probado un prototipo para simular el entorno AmI en un escenario de laboratorio considerando los principales problemas de seguridad clínica que ocurren en las UCIs. En segundo lugar, este prototipo ha sido adaptado e implementado en una UCI inteligente del HCB. En tercer lugar, he recogido y analizado los datos generados por el entorno inteligente. En conclusión, mi tesis evalúa la eficiencia del uso de nuevas tecnologías para mejorar los procesos de seguridad clínica en cuidados críticos, mejora los estándares clínicos y educativos sobre los procesos de seguridad del paciente en esta unidad y, finalmente, permite cuantificar los eventos relacionados con la seguridad clínica, así como ganar más conciencia sobre ellos.

L'internet des objets (IoT) et l'intelligence artificielle (IA) sont deux domaines technologiques en progression utilisant les capacités d'exécution de tâches mains libres et d'analyse intelligente des données. Ces technologies présentent un potentiel prometteur pour améliorer les interactions homme-machine dans le flux de travail, créer une meilleure prise de décision et améliorer l'accessibilité aux données. Les progrès rapides et les nouvelles possibilités d'application de l'IoT et de l'IA en sont aux phases initiales. Par conséquent, les travaux de recherche de cette thèse ont pour objectifs d'identifier et d'étudier le potentiel, les défis et les possibilités d'utiliser l'IoT et l'IA pour évaluer les paramètres cliniques. Plusieurs organisations affirment qu'une attention accrue devrait être accordée à l'utilisation efficace des ressources de santé. L'augmentation de l'espérance de vie et de la taille de la population au niveau international s'accompagne d'une augmentation du nombre d'hospitalisations de courte durée, et donc de la capacité limitée des lits. Le rapport international sur la santé mondiale publié par l'Organisation Mondiale de la Santé « OMS » montre que 20 à 40 % de l'ensemble des ressources de soins de santé ne sont pas suffisamment utilisées. Ainsi, les outils qui favorisent un système de soins de santé efficace sont d'une grande importance pour la société actuelle. L'objectif de cette thèse est d'étendre les méthodes dans le domaine de l'IoT et de l'IA ainsi que la modélisation et l'optimisation au flux de patients dans les hôpitaux pour fournir à la direction et aux planificateurs une gamme d'outils de décision afin d'améliorer l'utilisation des ressources hospitalières. Nous élaborons plusieurs problèmes d'optimisation hospitalière pertinents qui concernent la prise de décision au niveau stratégique, tactique et opérationnel. En outre, nous nous concentrons sur différents types de flux de patients, des admissions de patients hospitalisés aux admissions de patients externes, ce qui a donné lieu à de nombreuses études de recherche différentes. Sur le plan méthodologique, nous nous concentrons principalement sur l'évaluation des différentes instances du flux de patients, mais plus particulièrement sur les patients atteints de maladies cardiovasculaires, dont nous appuyant sur la modélisation de la chaîne de Markov. L'accent a été mis plus particulièrement sur la séparation du séjour du patient à l'hôpital en trois phases principales. Chaque phase est interdépendante, variable dans le temps et dépend de l'autre phase. Le cœur de la contribution est d'évaluer et de donner à chaque étape du processus d'admission, de traitement et de sortie des patients des solutions qui peuvent aider les médecins à prendre des décisions temps minimum, mais aussi à les prendre efficacement. Dans notre cas, l'IoT a été de grande utilité afin de collecter les signaux d'électrocardiogrammes (ECG) de patients atteints de différentes pathologies cardiovasculaires, et de transférer ces données dans une plateforme pour le traitement et le stockage. L'IA est utilisée pour classer automatiquement ces signaux avec trois ensembles de données du MIT, afin de décider automatiquement des patients sont atteints de maladies cardiovasculaires. L'IA a ensuite été utilisée pour prédire efficacement quels patients doivent sortir de l'hôpital en fonction de leurs signaux et caractéristiques épidémiologiques et physiologiques, mais aussi en fonction de leur durée de séjour et de leur historique d'admission et de transfert. Enfin, vient le rôle de l'utilisation de l'optimisation métaheuristique. Ce dernier tient compte de l'admission, de la trajectoire de traitement et de la première analyse de survie de ces patients pour décider quels patients seront affectés à un lit dans quel service, principalement dans l'unité de soins intensifs<br>Internet of Things (IoT) and Artificial Intelligence (AI)are two advancing technological areas utilizing the capabilities of performing hands free tasks and intelligent data analysis. These technologies are showing promising potentials of improving the Human-to-Machine interactions in clinical workflow, create a better foundation of clinical decision-making, and improve the accessibility of clinical data. The novel aspect, rapid advancement, and new application possibilities of IoT and AI are in the initial phases. Hence, the thesis research has the objectives of identifying and investigating the potential, challenges, and possibilities of using IoT and AI to assess clinical settings.From the other hand, Various organizations claim that increasing attention should be put on an efficient use of healthcare resources. The internationally rising life expectancy and population size is accompanied by hospitals that are relying more on short admissions, and thus on limited bed capacity. The international World Health Report published by the World Health Organization shows that 20-40% of all healthcare resources are not being sufficiently utilized. Thus, tools that benefit an efficient healthcare system is greatly relevant to the present society. The goal of this thesis is to expand methods in the field of IoT and AI and modeling and optimization to hospital patient flow with a view to provide management and planners with a range of decision tools for improving the utilization of hospital resources. We elaborate on several relevant hospital optimization problems which relate to decision making on both the strategic, tactical and operational level. In addition, we focus on various types of patient flow, from inpatient to outpatient admissions, which has led to many different research studies. Methodologically we mainly focus on evaluating the different instances of patient flow but specifically on patients with cardiovascular diseases (CVD) based on Markov chain modeling.Mainly, the focus was on separating the patient stay in the hospital into three main phases. Each phase in an interdependent, time varying and function of the other phase. The core of the contribution is to assess and give every step of the process of admitting, treating, and discharging patients with solutions that can help physicians take decisions in short time but also take them efficiently. These techniques used IoT in order to collect electrocardiogram signals (ECG) from patients with different CVD pathologies and to transfer these data into a platform that can preprocess it and store it. AI that is used to automatically classify these signals along with three MIT dataset and decide which patients have cardiovascular diseases with no physician intervention. Then AI was used to efficiently predict which patients need to be discharged based on their epidemiological, physiological signals and characteristics and also based on their Length of Stay (LOS) and on their admission and transfer history. Finally, comes the role of using metaheuristic optimization. This last one, into account the admission, treatment trajectory and first survival analysis of these patients to decide which patients will be allocated to a bed in which ward mainly in the Intensive Care Unit (ICU).The proposed system for studying and optimizing the patients flow in a health care facility show high performance based on the different performance metrics we are using in this research project

碩士<br>國立交通大學<br>資訊管理研究所<br>106<br>Since 1982, the elderly population of Taiwan has accounted more than 7% of the total population and has started to move in an aging society. Impact of decreasing birthrate, at the end of February 2017, the registered elderly population (over 65 years old) are more than the younger population (0-14 years old). According to the survey, about 70% of the elderly want to live with their children or spouses. But the family structure is slowly changing, and the care of the elderly people at home are going to be challenging. With the development of information and communications technology (ICT), several healthcare care systems and tools can be employed for the care of the elderly people at home. For example, Internet of things (IoT) such as wearable devices or sensors can be applied to sense basic physiological signals and upload these directly to the cloud platform. When there is an emergency situation, it can send out warning signals to the family to warn about the physiological condition. It can also be connected with the hospital or the care organization, which allows physicians and caregivers to monitor instantly and provide better care employing the remote care system. There are four purposes of the current study. First, explore the common needs required for elderly care. Understand the different needs of healthcare, psychological adjustment, economy, life care, and housing. Then a detailed discussion on health care and life care was employed. Second, explore the development of the IoT, including its operational model and basic structure. Third, understand the application of the IoT in medical care and explore how IoT can be applied in fields such as medical care or hospitals, and how it can be employed to improve the quality of medical care. The last item is to propose a comprehensive medical network for the elderly care service model. Integrate the care needs of the elderly at home, and connect the various services through the technology of the IoT to provide comprehensive care services for the elderly people. 　　The literature review from 2010 to 2017 was employed to collect data. We include doctoral thesis, government research projects, publication of foreign journals and academic papers published in seminars are included for current study. A total of 199 published academic papers on the elderly care population related with IoT were finally included for the current study. All these studies are classified into six categories: health monitoring, using drugs, environmental safety, activities and sports, location monitoring and help, and rehabilitation. Discuss the several contents to understand how the Internet of Medical Things (IoMT) can solve the needs of elderly care. At the end of the study, a medical network structure was proposed for the home care service model of the elderly population. First, wearable devices and sensors are placed on the user to monitor their physical condition. Sensors and monitors are also built in a way which can work in the homely environment. Then, upload the relevant data to the cloud for storage and analysis. Finally, it is used to provide services such as health management, disease monitoring, diet, exercise, and rehabilitation to meet several medical care and daily needs. It can be used to provide preventive care and prevent disability or help to detect the disease in early stage and provide corresponding medical care services. It can be employed as self-health care management for healthy elderly people. Elderly people suffering from chronic diseases and have long-term care for disability can use it to monitor their physical condition instantly. However, it can be employed to reduce the burden on home caregivers, indirectly reduce the medical care costs, and improve the quality of care. The limitation of this study is that the data was collected only from published academic articles. Thus, there are lacks the opinions of experts. Therefore, future research should use questionnaires, interviews, and the opinions of relevant personnel to make the study findings more comprehensive. In addition, the service model proposed in this study is only a concept and has not been actually implemented. In the future research, it is expected to develop a system that can be used in practice, and discuss the system functions in the more precise way. Finally, security protection and transmission of users’ information are reinforced to protect the privacy of users.

碩士<br>淡江大學<br>管理科學學系企業經營碩士在職專班<br>101<br>In view of Taiwan&apos;&apos;s population is aging rapidly, causing that need to be taken care of the elderly population continues to grow, on the contrary the structure of double-income families to take care of human caused reduced, so the need for the development of long-term care is more and more important. Current home care, the majority of family members or to hire only licensed non-nursing home care as a non-professional caregivers are often unable to provide professional medical care. As a result, new types of remote health care services have emerged, using remote monitoring of care mode is the future trend of an aging society.In this study, we apply IoT (Internet of Things, IoT) structure model and cloud services to traditional long-term care system, to analyze advantages by data flow diagrams (Data Flow Diagram, DFD). In this cases study, a chronic diabetic patients using long-term care systems with IoT structure, to analysis of actual usage, verify that the actual results.Verify that the actual results, we found by using the Internet of Things structure Telecare system is a viable option.

碩士<br>國立中正大學<br>會計與資訊科技研究所<br>104<br>With the advancement of Internet, cloud computing and Wearable Technology, Internet of Things(IOTs) are the third wave of innovation reform for the global information technology industry. The IoTs will change people’s life and business models. New technology is accompanied by a new issue. Therefore, the studies related to IoT primarily focus on technology development and analysis of IoTs industry. Few researches put their accent on IS problems of IoT. As the proportion of elderly in society continues to rise, Technologies Applied to Health Care is most popularize in the IoTs applications. This study conducts an empirical study to construct the maturity model of information security in IoT environment for the medical industry. Finally, this study conducts the case study from a hospital which is willing to cooperate with this study. It is expected that aforementioned measurement scale can really work in the medical industry. It is expected that that the research findings can be beneficial for information security decision-making IT managers of medical industry to do the right decisions under the environment of IoTs.

Dissertação de Mestrado em Engenharia Informática apresentada à Faculdade de Ciências e Tecnologia<br>Com o crescimento em tamanho, complexidade e funcionalidade, os sistemas informáticos estão cada vez mais inteligentes e interconectados. Em linha com essa tendência, a Internet das Coisas é usada de forma mais eficiente para oferecer suporte a novos tipos de sistemas. O desenvolvimento de sistemas "Humanos em Ciclo" (tradução livre para "Human-in-the-Loop") em ambientes de Internet das Coisas ainda é relativamente recente e, como tal são poucos os trabalhos e teses realizados sobre o tema. Por meio de investigação de ponta e uma visão geral detalhada de modelos “Humanos em Ciclo” em ambientes de Internet das Coisas, esta tese é um esforço para estender o conhecimento do campo com a implementação de dois sistemas "Humanos em Ciclo" em ambientes IoT aplicados à área médica. O primeiro projeto (Vitoria) foi concebido para coletar métricas e criar técnicas de previsão para os padrões de comportamento das pessoas durante e após uma pandemia. O segundo projeto (POC) teve como objetivo permitir a investigação da correlação, sobreposição e distinção entre o transtorno do espectro do autismo e o transtorno obsessivo-compulsivo, por meio de recolha passiva e ativa de dados. Ambos os projetos seguem um processo de desenvolvimento característico de projetos informáticos que é detalhadamente especificado nesta tese, e ambos passam pelo desenvolvimento de sistemas para plataformas moveis, embora por processos de desenvolvimento diferentes. O sistema do primeiro projeto é baseado na plataforma Android e o sistema do segundo projeto é baseado na plataforma Xamarin. Esta tese também inclui uma biblioteca de software com o objetivo de permitir a qualquer programador implementar as principais funcionalidades de um sistema Humanos em Ciclo em qualquer aplicação de software baseada na plataforma Xamarin.<br>Along with the growth in size, complexity and functionality, informatic systems are becoming increasingly more intelligent and interconnected. In line with this trend, the Internet of Things is being used more efficiently to support new types of systems. The development of "Human-in-the-Loop" systems in Internet of Things environments is still relatively recent and, as such, there are few works, and theses carried out on the subject. Through state-of-the-art research and detailed overview of Human-in-the-Loop models in Internet of Things Environments, this thesis is an effort to extend the field’s knowledge with the implementation of two Human-in-the-Loop systems in IoT environments applied to medical situations. The first project (Vitoria) was meant to collect metrics and predictive techniques for people’s behaviour patterns during and after a pandemic. The second project (POC) had the objective to allow the investigation of the correlation, overlapping, and distinction between autism spectrum disorder and obsessive-compulsion disorder, through passive and active data collection. Both projects follow a development process characteristic of Informatic projects that is specified in detail in this thesis, and both go through the development of systems for mobile platforms, although through different development processes. The system of the first project is based on Android platform and the system of second project is based on Xamarin platform. This thesis also includes a software library with the objective to allow any developer to implement the main features of a Human-in-the-Loop application in any software application based on Xamarin platform.<br>Outro - The research presented in this thesis was supported by the EEA Grants Portugal 2014- 2021 - Bilateral Initiative number 63 "PrivacyCoLab" and by the Project - "iFriend – Supervisión inteligente del estado de salud en personas mayores con insuficiencia renal mediante dispositivos inalámbricos" of Fundación CSIC, Interreg Portugal-Espanha.

碩士<br>國立臺灣科技大學<br>醫學工程研究所<br>106<br>The elders and patients with physical disabilities have difficulty in mobility, and electric wheelchairs and scooters would be possible mobility aids in their daily life. Severe disability patient with long-term illness in bed situation may use active pressure bedsore to change the body posture to prevent pressure ulcer. To provide the abovementioned patients having better quality of life through the uses of up-to-date technologies is the aim of this research. Therefore, this thesis mainly aims at developing the wearable devices with Internet of Things (IoT) techniques to provide a feasible human-machine-interface for disabled patient in terms of scenario design, solution implementation and validation. This thesis mainly discusses the applications of IoT in the development of wireless medical device control interface. In order to achieve the above goals, the technologies of MQTT (Message Queuing Telemetry Transport) and Bluetooth were employed. For the hardware aspects, the inertial measurement unit (IMU) and HM-10 Bluetooth modules were used. For the software aspects, the mobile tablet APP was realized with APP inventor. An ATmega2560 microcontroller was used to connect the APP and wearable sensors modules and the physical medical devices. Finally, the proposed interfaces were validated in terms of modifying the commercial available facilities of an electric wheelchair, an electric baby car and an active pressure bedsore.

碩士<br>臺北城市科技大學<br>機電整合研究所<br>106<br>ABSTRACT With the development of science and technology, the convenient wearable devices has been a success in the market. Nowadays, various health sensors are developed and used to monitor personal health condition such as sphygmomanometers, and blood oxygen gauge, etc. The Wearable technology is often touted as one of the greatest applications of the Internet of Things, with good reasons. The health condition data are transmitted to the server over Internet, and monitored by specialists or program to achieve the purpose of remote healthcare. In this paper, the AD8232 module is used as the sensor of Electrocardiography(ECG). Arduino Yun development board is chosen as the controller of our wearable device. The ECG data are sent to the remote server by wireless LAN and can be monitored by web browser. The specialists can be aware of the irregular data early by surfing our webpage.

博士<br>國立陽明大學<br>生物醫學工程學系<br>107<br>Cardiovascular disease (CVD) is the leading cause of the death all over the world, and this health issues also bring about abundant economic burdens. The global popular technology, Internet of Things (IoT), can integrate the hardware system of health monitoring, diagnostics and treatment, and making it more personalized, timely, and convenient in a lower cost. Wearable IoT may monitor vital signs and physical activities and promote a health program to maintain an active lifestyle, develop healthy habits for reducing the morbidity of CVD. However, the existing wearable devices still confront big challenges of insufficient function and poor strategy of big data acquisition for bio-data analysis. Therefore, this study proposed a wearable Hardware/Software (HW/SW) co-design wrist-type PPG device for IoT healthcare system, which incorporate with 24-hours vital sign AI-monitoring. To verify the clinical requirement, this study conducted a long-term clinical trial to validate different function including heart rate variability, blood pressure trend, atrial fibrillation, blood oxygen level, sleep cycle. Artificial intelligence and machine learning techniques are used to increase the measuring accuracy. The results shown that our lab-developed wrist-type PPG device was verified to acquire the sufficient and reliable bio-data. The AI-platform was also successfully established to provide specialists and users helpful information, such as timely noticing the abnormal vital signs or long-term healthy trend shown on the terminal device interface. By these means, we expecting the quality of healthy life would be raised up.

碩士<br>國立聯合大學<br>資訊管理學系碩士班<br>105<br>With the rapid development of Internet of Things technology and the popularity of wearable equipment, mobile care will become the mainstream care way in the future. For integrating IoT technology and wearable devices into mobile medical care to improve the efficiency and quality of future care environments, this study proposes an integrated system based on wearable devices those are extensible to construct an IoT of medical care. This system collects and monitors the patient's physiological signals through sensors within wearable devices. In addition to find out the patient's abnormal physiological signals and then give patients warning earlier, this system integrate the patient's physiological information to make a long-term health observation. The proposed middleware can filter and integrate the physiological information from sensers, and then deliver the integrated physiological information to Cloud System according to the pre-designed packet format. In addition, the mapping of virtual and physical resources is carried out so that the system can independently identify the type of collected information. The sensor with a unique identification can sense physiologic signal and can be used by many patients repeatedly in different period. No matter what sensors a patient uses, the collected physiologic signal is belong to this patient. Simultaneously this system provide location tracking service to patients for ensuring patients’ safty in the hospital. Through the instant collection of physical information, patients can understand their immediate condition and then get relative care services. In the environment where extremely lacks medical care resources today, the quality of care can be improved by reducing the burden of care workers.

This thesis examines users’ perception of trust within the context of security and privacy of Wearable Internet of Medical Things (WIoMT). WIoMT is a collective term for all medical devices connected to internet to facilitate collection and sharing of health-related data such as blood pressure, heart rate, oxygen level and more. Common wearable devices include smart watches and fitness bands. WIoMT, a phenomenon due to Internet of Things (IoT) has become prevalent in managing the day-to-day activities and health of individuals. This increased growth and adoption poses severe security and privacy concerns. Similar to IoT, there is a need to analyse WIoMT security risks as they are used by individuals and organisations on regular basis, risking personal and confidential information. Additionally, for better implementation, performance, adoption, and secured wearable medical devices, it is crucial to observe users’ perception. Users’ perspectives towards trust are critical for adopting WIoMT. This research aimed to understand users’ perception of trust in the adoption of WIoMT, while also exploring the security risks associated with adopting wearable IoMT. Employing a quantitative method approach, 189 participants from Western Sydney University completed an online survey. The results of the study and research model indicated more than half of the variance (R2 = 0.553) in the Intention to Use WIoMT devices, which was determined by the significant predictors (95% Confidence Interval; p < 0.05), Perceived Usefulness, Perceived Ease of Use and Perceived Security and Privacy. Among these two, the domain Perceived Security and Privacy was found to have significant outcomes. Hence, this study reinforced that a WIoMT user intends to use the device only if he/she trusts the device; trust here has been defined in terms of its usefulness, easy to use and security and privacy features. This finding will be a steppingstone for equipment vendors and manufacturers to have a good grasp on the health industry, since the proper utilisation of WIoMT devices results in the effective and efficient management of health and wellbeing of users. The expected outcome from this research also aims to identify how users’ security and perception matters while adopting WIoMT, which in future can benefit security professionals to examine trust factors when implementing new and advanced WIoMT devices. Moreover, the expected result will help consumers as well as different healthcare industry to create a device which can be easily adopted and used securely by consumers.

碩士<br>國立勤益科技大學<br>電機工程系<br>107<br>Medical devices with connectivity are more expensive, such as CT (Computerized Tomography), NMR(Nuclear Magnetic Resonance),and use DICOM (Digital Images-and Communication in Medicine standard)protocol for medical images transmission. The popularity of use is not high. There are many different equipment in the outpatient department, and the data format are different. This caused confusion for nurses and very inconvenient for the patient. We called non-DICOM equipment is no system integration and no communication. In order to improve such problems, this paper uses the NFC (Near Field Communication) to turn devices into IoT, and use the Smart210 to integrate medical equipment (including height, weight, sphygmomanometer) Reduce the time that nurses write cases.

<div>Energy-efficient communication has remained the primary bottleneck in achieving fully energy-autonomous IoT nodes. Several scenarios including In-Sensor-Analytics (ISA), Collaborative Intelligence (CI) and Context-Aware-Switching (CAS) of the cluster-head during CI have been explored to trade-off the energies required for communication and computation in a wireless sensor network deployed in a mesh for multi-sensor measurement. A real-time co-optimization algorithm was developed for minimizing the energy consumption in the network for maximizing the overall battery lifetime of individual nodes.</div><div><br></div><div>The difficulty of achieving the design goals of lifetime, information accuracy, transmission distance, and cost, using traditional battery powered devices has driven significant research in energy-harvested wireless sensor nodes. This challenge is further amplified by the inherent power intensive nature of long-range communication when sensor networks are required to span vast areas such as agricultural fields and remote terrain. Solar power is a common energy source is wireless sensor nodes, however, it is not reliable due to fluctuations in power stemming from the changing seasons and weather conditions. This paper tackles these issues by presenting a perpetually-powered, energy-harvesting sensor node which utilizes a minimally sized solar cell and is capable of long range communication by dynamically co-optimizing energy consumption and information transfer, termed as Energy-Information Dynamic Co-Optimization (EICO). This energy-information intelligence is achieved by adaptive duty cycling of information transfer based on the total amount of energy available from the harvester and charge storage element to optimize the energy consumption of the sensor node, while employing event driven communication to minimize loss of information. We show results of continuous monitoring across 1Km without replacing the battery and maintaining an information accuracy of at least 95%.</div><div><br></div><div>Decades of continuous scaling in semiconductor technology has resulted in a drastic reduction in the cost and size of unit computing. This has enabled the design and development of small form factor wearable devices which communicate with each other to form a network around the body, commonly known as the Wireless Body Area Network (WBAN). These devices have found significant application for medical purposes such as reading surface bio-potential signals for monitoring, diagnosis, and therapy. One such device for the management of oropharyngeal swallowing disorders is described in this thesis. Radio wave transmission over air is the commonly used method of communication among these devices, but in recent years Human Body Communication has shown great promise to replace wireless communication for information exchange in a WBAN. However, there are very few studies in literature, that systematically study the channel loss of capacitive HBC for <i>wearable devices</i> over a wide frequency range with different terminations at the receiver, partly due to the need for <i>miniaturized wearable devices</i> for an accurate study. This thesis also measures and explores the channel loss of capacitive HBC from 100KHz to 1GHz for both high-impedance and 50Ohm terminations using wearable, battery powered devices; which is mandatory for accurate measurement of the HBC channel-loss, due to ground coupling effects. The measured results provide a consistent wearable, wide-frequency HBC channel loss data and could serve as a backbone for the emerging field of HBC by aiding in the selection of an appropriate operation frequency and termination.</div><div><br></div><div>Lastly, the power and security benefits of human body communication is demonstrated by extending it to animals (animal body communication). A sub-inch^3, custom-designed sensor node is built using off the shelf components which is capable of sensing and transmitting biopotential signals, through the body of the rat at significantly lower powers compared to traditional wireless transmissions. In-vivo experimental analysis proves that ABC successfully transmits acquired electrocardiogram (EKG) signals through the body with correlation accuracy >99% when compared to traditional wireless communication modalities, with a 50x reduction in power consumption.</div>

碩士<br>國立聯合大學<br>資訊管理學系碩士班<br>107<br>At present, social environment got the problem of aging of population in Taiwan. It caused more and more demand of medical resources. Besides, the issue of low birth rate has induced the shortage of working-age population year by year. These problems not only caused the deficiency of medical human resources in medical institution but also increased the working load of medical staffs. With the rapid development of mobile communications and wearable devices, the technology of Internet of Things has enabled many good applications in many domains, especially in the industry of medical care. Through the integration of the mobile wearable devices and the technology of Internet of Things, the working performance will be improved and further reduced the effect of insufficient medical human resources. Therefore, this thesis proposed a platform to integrate them and this platform could manage the medical information and medical resources well for promoting the working efficiency of medical staffs. Furthermore, it could reduce the working load of medical staffs. Through the implementation of this platform, it was found out that the platform is efficient and feasible.

碩士<br>國立彰化師範大學<br>資訊管理學系<br>106<br>Thanks to the rapid development of technology and the Internet of Things (IoT), the number of medical devices that can output measure results through internet is increasing. With the assistance of these devices, nursing staff can reduce paperwork by a considerable amount. At the same time, it can also increase the accuracy of electronic forms, letting nurses focus more on the actual clinical work and reduce the risk of erroneous medical treatment This study was based on the analysis of relevant literature, and used the Delphi Technique research method to conduct an expert questionnaire. The purpose of this research is to discuss the critical success factors for the establishment of medical paperless operations using IoT. Through a three-time expert survey of Delphi Technique, we concluded that the critical factors were: "security factors", "organizational factors", "intrinsic environmental factors", and "system factors". There were altogether four constructs and ten subtopics. The results of this study can provide reference for the future development of the medical industry in paperless operations.

碩士<br>國立彰化師範大學<br>電機工程學系<br>107<br>The open ward design in most Taiwan hospitals allows people to freely move around inpatients’ space. Establishing an access control system is the general solution. However, the rooming-in practice in obstetrics wards while encouraging mothers to stay with their neonates increases the risks of stolen or mismatch. That is not preventable by any access control system. By the Internet of Things (IoT) technology and application, the Neonate Positioning System utilizing the indoor positioning techniques could be an effective solution. If a neonate shows up in the wrong place, the system will notify responsible parties to react immediately. This study sets up a neonate positioning system in a hospital obstetrics ward. The system includes the Bluetooth 4.0 Bluetooth Low Energy (BLE 4.0) ankle bracelet, the Raspberry Pi3 as a positioning gateway, an integrated server, and the monitoring software. The system applies Cell of Origin (COO) as the positioning technique. The gateway received signal strength indicator (RSSI) and indicates the actual location.

碩士<br>國立臺灣大學<br>資訊管理組<br>104<br>According to the statistical data from the Ministry of Health and Welfare, Taiwan, the ratio of people over the age of 65 continues to increase, from 9.1% of the total population in 2003 up to 12.69% of the total population in 2014. This not only indicates that Taiwan is facing toward to an aged society, but also that appropriate health care and policies need to be made for the elderly in the future. Indeed, aging has changed the concept of health, sub-health and disease towards a more proactive view, causing modern countries to face not only the disease burden, which will cause the complications or serious damages to the daily ability or self-care, but also the increasing cost of health care expenditure [2]. The world is adopting a proactive and positive attitude in the aging population and related health and disease-related issues. Active ageing and healthy ageing are the important concept we focused on the development of the modern society. The “Internet of Things”, referred to as IoT, is not only a network, but also an information exchange between devices. The communication devices combined with engineering and medical science and technology have made IoT more appreciable and reachable through the internet without boundaries. IoT also helps advance the healthy and medical industry. For example, IoT for the diagnosis instrument has the following advantages: 1.With remote monitoring and support systems, equipment testing and remote diagnostics can reduce equipment downtime. 2. High efficiency usage and scheduling will be advantageous for patients. Of course, the exchange of data and information to health care is important. The IoT not only provides big data analytics, but also individual personal data gathered from medical devices and cloud database sharing. The healthy and medical care industry, like another industry, is now possible through the use of better cross-industry commonality of technology. With the ratio of people over the age of 65 in Taiwan will reach 14 percent, the Ministry of Health and Welfare also launched the future implementation of mental and physical disability, long-term care for the elderly people, community-based, home-style long-term care services. Therefore, how to establish long-term care information systems, and establish a networking concept of long-term care will be the perfect solution and integration platform to improve the quality of care and efficiency of institutions in the future. This thesis is to explore the concept of IoT in healthy and medical care industry and to integrate the expertise, network engineering and technical analysis and other indicators. With the application of management knowledge, we hope to construct the roadmap for analysis and evaluation of the IoT in the healthy and medical care industry. Keywords: Internet of Things (IoT), Medical care, Health care

Indiana University-Purdue University Indianapolis (IUPUI)<br>The life expectancy of humans in today's era have increased to a very large extent due to the advancement of medical science and technology. The research in medical science has largely been focused towards developing methods and medicines to cure a patient after a diagnosis of an ailment. It is crucial to maintain the quality of life and health of the patient. It is of most importance to provide a healthy life to the elderly as this particular demographic is the most severely affected by health issues, which make them vulnerable to accidents, thus lowering their independence and quality of life. Due to the old age, most of the people become weak and inefficient in carrying their weight, this increases the probability of falling when moving around. This research of iterative nature focuses on developing a device which works as a preventive measure to reduce the damage due to a fall. The research critically evaluates the best approach for the design of the Pre-Fall detection system. In this work, we develop two wearable Pre-Fall detection system with reduced hardware and practical design. One which provides the capability of logging the data on an SD card in CSV format so that the data can be analyzed, and second, capability to connect to the Internet through Wifi. In this work, data from multiple accelerometers attached at different locations of the body are analyzed in Matlab to find the optimum number of sensors and the best suitable position on the body that gives the optimum result. In this work, a strict set of considerations are followed to develop a flexible, practical and robust prototype which can be augmented with different sensors without changing the fundamental design in order to further advance the research. The performance of the system to distinguish between fall and non-fall is improved by selecting and developing the most suitable way of calculating the body orientation. The different ways of calculating the orientation of the body are scrutinized and realized to compare the performance using the hardware. To reduce the number of false positives, the system considers the magnitude and the orientation to make a decision.

У цій роботі пропонується архітектура та схему розумної лікарні, заснованої на Інтернеті речей (IoT), з метою подолання недоліків існуючої лікарняної інформаційної системи. Основні технології та побудова розумної лікарні представлені на основі розуміння суті та архітектури розумної лікарні. Крім того, наводиться схема розумної лікарні, а також детально описуються її логічна структура, структура програм, побудова базового мережевого середовища тощо. Розгортання інтелектуальної лікарні може ефективно вирішити важливі проблеми діагностики та лікування лікарні, і це приносить позитивний та глибокий ефект для сучасного режиму діагностики та лікування в лікарні.<br>This paper proposes the architecture and scheme of a smart hospital based on the Internet of Things (IoT), in order to overcome the shortcomings of the existing hospital information system. The basic technologies and construction of a smart hospital are presented on the basis of understanding the essence and architecture of a smart hospital. In addition, the scheme of a smart hospital is given, as well as its logical structure, program structure, construction of a basic network environment, etc. are described in detail. Deployment of an intelligent hospital can effectively solve important problems of diagnosis and treatment of the hospital, and this brings a positive and profound effect to the current mode of diagnosis and treatment in the hospital.<br>Вступ 1 Розумна лікарня на основі інтернет речей 1.1 Ключові технології ІоТ 1.1.1 Інтернет-технології 1.1.2 Технологія RFID 1.1.3 Мережа сенсорів 1.1.4 Бездротова комунікація 1.2 Розумна лікарня 1.3 Архітектура розумної лікарні 1.3.1 Рівень сприйняття 1.3.2 Мережевий рівень 1.3.3 Рівень додатків 1.4 Побудова розумної лікарні 1.4.1 Компіляція інформації, специфікації і стандарту 1.4.2 Створення об'єднаної мережевої допоміжної платформи 1.4.3 Створення спільних даних 1.4.4 Створення інтегрованого інформаційного порталу 1.4.5 Створення вбудованого мобільного медичного запису 1.5 Схема застосування розумної лікарні 1.5.1 Логічна структура 1.5.2 Структура додатків 1.5.3 Мережеве підтримувальне середовище 2 Система моніторингу стану здоров'я пацієнтів за допомогою ІоТ 2.1 Загальна характеристика системи 2.2 Існуючі системи 2.3 Архітектура запропонованої системи 3 Безпека життєдіяльності, основи хорони праці 3.1 Вплив факторів трудового середовища на здоров’я та працездатність розробника програм 3.2 Вплив електромагнітного імпульсу (ЕМІ) на роботу комп’ютерної мережі 3.3 Здоровий спосіб життя користувача та його вплив на професійну діяльність Висновки Список використаних джерел