The purpose of this thesis is to devise a system based on RFID (Radio Frequency IDentification) that can be used for smart healthcare applications. Location estimation, eloping prevention and occupancy detection are monitoring applications of smart healthcare which can provide very useful information for the nursing and administration staff of the nursing-home/hospital. The introduction of ubiquitous networking along with the concepts such as Internet of Things (IoT) can certainly help achieve the goals of smart healthcare. RFID technology has features, such as low power and small size, which makes this technology suitable for researching solutions for smart healthcare. Today several nursing-home/hospital monitoring solutions exist in the market and academia alike. The solutions marketed commercially are very expensive whereas the solutions from academia provides solutions to isolated problems but a comprehensive all in one solution that can meet the need of smart healthcare monitoring applications is missing. In this thesis we present a system that is low cost and suitable for accommodating a number of the smart healthcare applications including occupancy detection, location estimation, eloping prevention and access control. The solution is implemented on a customized Openbeacon Active RFID System (OARS). Active RFID based proximity detection is the core of our system. Practical experiments based on novel Proximity Detection based Weighted Centroid Localization (PD-WCL) method were done to analyze the performance of the system with different applications to highlight the applicability of the system.

The purpose of this thesis is to devise a system based on RFID (Radio Frequency IDentification) that can be used for smart healthcare applications. Location estimation, eloping prevention and occupancy detection are monitoring applications of smart healthcare which can provide very useful information for the nursing and administration staff of the nursing-home/hospital. The introduction of ubiquitous networking along with the concepts such as Internet of Things (IoT) can certainly help achieve the goals of smart healthcare. RFID technology has features, such as low power and small size, which makes this technology suitable for researching solutions for smart healthcare. Today several nursing-home/hospital monitoring solutions exist in the market and academia alike. The solutions marketed commercially are very expensive whereas the solutions from academia provides solutions to isolated problems but a comprehensive all in one solution that can meet the need of smart healthcare monitoring applications is missing. In this thesis we present a system that is low cost and suitable for accommodating a number of the smart healthcare applications including occupancy detection, location estimation, eloping prevention and access control. The solution is implemented on a customized Openbeacon Active RFID System (OARS). Active RFID based proximity detection is the core of our system. Practical experiments based on novel Proximity Detection based Weighted Centroid Localization (PD-WCL) method were done to analyze the performance of the system with different applications to highlight the applicability of the system.

A promising approach to raising the caliber and accessibility of healthcare services is the development of Smart Healthcare Systems. However, the union of wireless networks and smart medical devices has created additional security issues, such as the possibility of identity theft, data breaches, and denial-of-service assaults. These flaws emphasize the significance of creating a safe and dependable smart healthcare system that can safeguard patient data and guarantee the confidentiality of private medical information. This study suggests adopting 5G security standards to address the security issues with smart healthcare systems. The STRIDE threat modeling approach, which includes six threat categories (spoofing, tampering, repudiation, information disclosure, denial of service, and elevation of privilege), is used in this study to investigate potential threats in smart healthcare systems. The report suggests using strong encryption protocols, such as AES-CCM and ECDH, between smart healthcare equipment and5G-AKA to reduce these potential threats. The proposed approach showed appreciable advancements in data security and privacy. According to the findings, 5G security standards can be used to efficiently reduce security risks in smart healthcare systems and establish a trustworthy and secure platform for delivering medical services. The study emphasizes the significance of including strong security controls in Smart Healthcare Systems to secure patient information and raise the standard of treatment generally.

<p>This dissertation explores the world of non-intrusive wireless sensing for diet and fitness activity monitoring, in addition to assessing security risks in human activity recognition (HAR). It delves into the use of WiFi and millimeter wave (mmWave) signals for monitoring eating behaviors, discerning intricate eating activities, and observing fitness movements. The proposed systems harness variations in wireless signal propagation to record human behavior while providing exhaustive details on dietary and exercise habits. Significant contributions encompass unsupervised learning methodologies for detecting dietary and fitness activities, implementing soft-decision and deep neural networks for assorted activity recognition, constructing tiny motion mechanisms for subtle mouth muscle movement recovery, employing space-time-velocity features for multi-person tracking, as well as utilizing generative adversarial networks and domain adaptation structures to enable less cumbersome training efforts and cross-domain deployments. A series of comprehensive tests validate the efficacy and precision of the proposed non-intrusive wireless sensing systems. Additionally, the dissertation probes the security vulnerabilities in mmWave-based HAR systems and puts forth various sophisticated adversarial attacks - targeted, untargeted, universal, and black-box. It designs adversarial perturbations aiming to deceive the HAR models whilst striving to minimize detectability. The research offers powerful insights into issues and efficient solutions relative to non-intrusive sensing tasks and security challenges linked with wireless sensing technologies.</p>

This research proposes FruitPAL and FruitPAL 2.0. They are full automatic devices that can detect fruit consumption to reduce the risk of disease. Allergies to fruits can seriously impair the immune system. A novel device (FruitPAL) detecting fruit that can cause allergies is proposed in this thesis. The device can detect fifteen types of fruit and alert the caregiver when an allergic reaction may have happened. The YOLOv8 model is employed to enhance accuracy and response time in detecting dangers. The notification will be transmitted to the mobile device through the cloud, as it is a commonly utilized medium. The proposed device can detect the fruit with an overall precision of 86%. FruitPAL 2.0 is envisioned as a device that encourages people to consume fruit. Fruits contain a variety of essential nutrients that contribute to the general health of the human body. FruitPAL 2.0 is capable of analyzing the consumed fruit and then determining its nutritional value. FruitPAL 2.0 has been trained on YOLOv5 V6.0. FruitPAL 2.0 has an overall precision of 90% in detecting the fruit. The purpose of this study is to encourage fruit consumption unless it causes illness. Even though fruit plays an important role in people's health, it might cause dangers. The proposed work can not only alert people to fruit that can cause allergies, but also it encourages people to consume fruit that is beneficial for their health.

The rise of internet connected devices has enabled the home with a vast amount of enhancements to make life more convenient. These internet connected devices can be used to form a community of devices known as the internet of things (IoT). There is great value in IoT devices to promote healthy independent living for older adults. Fall-related injuries has been one of the leading causes of death in older adults. For example, every year more than a third of people over 65 in the U.S. experience a fall, of which up to 30 percent result in moderate to severe injury. Therefore, this thesis proposes an IoT-based fall detection system for smart home environments that not only to send out alerts, but also launches interaction models, such as voice assistance and camera monitoring. Such connectivity could allow older adults to interact with the system without concern of a learning curve. The proposed IoT-based fall detection system will enable family and caregivers to be immediately notified of the event and remotely monitor the individual. Integrated within a smart home environment, the proposed IoT-based fall detection system can improve the quality of life among older adults. Along with the physical concerns of health, psychological stress is also a great concern among older adults. Stress has been linked to emotional and physical conditions such as depression, anxiety, heart attacks, stroke, etc. Increased susceptibility to stress may accelerate cognitive decline resulting in conversion of cognitively normal older adults to MCI (Mild Cognitive Impairment), and MCI to dementia. Thus, if stress can be measured, there can be countermeasures put in place to reduce stress and its negative effects on the psychological and physical health of older adults. This thesis presents a framework that can be used to collect and pre-process physiological data for the purpose of validating galvanic skin response (GSR), heart rate (HR), and emotional valence (EV) measurements against the cortisol and self-reporting benchmarks for stress detection. The results of this framework can be used for feature extraction to feed into a regression model for validating each combination of physiological measurement. Also, the potential of this framework to automate stress protocols like the Trier Social Stress Test (TSST) could pave the way for an IoT-based platform for automated stress detection and management.

The problem of insufficient healthcare is particularly noticeable in rural regions. Despite this, there is still little research on the digital transformation of healthcare in rural areas. This thesis aims to bridge the gap between the two research fields of "digital health” and “rural development” to find out the most significant challenges for rural areas when implementing and using digital health solutions. "Rural areas" in this work are referring to areas with low population density and small settlements in the industrialised EU countries. First of all, a “Digital Health Ecosystem” was developed based on a research review, which served as an overview of the most important factors and stakeholders regarding digital health in general. The “Digital Health Ecosystem” was used as part of the qualitative research method and interview guide to identify the challenges in transferring the overview to rural areas. An interview study was conducted with eight experts from the field of digital health with different backgrounds like technology, economics, social sciences, healthcare systems and smart village. The results show that digital health in general involves many barriers, which also apply to rural areas. The specific challenges for rural areas could be divided into four main categories: broadband and mobile networks; structural barriers; digital acceptance &amp; competence; rural innovation. The findings reveal that the smart village concept and rural initiatives are still in their early stages and digital strategies and networks will have to spread more widely across the entire countries. Furthermore, services must be better targeted to the specific problems of rural communities. In particular, because the need for digital health solutions is very great in rural areas, where they can counteract problems like lack of healthcare providers and poor healthcare. In this context, all the general and specific challenges should not be considered separately, because the complexity of the ecosystem can only be understood by connecting all the different fields of action. / Problemet med otillräcklig sjukvård märks särskilt på landsbygden. Trots detta finns det fortfarande lite forskning om den digitala omvandlingen av sjukvården på landsbygden. Denna rapport syftar till att överbrygga klyftan mellan de två forskningsområdena "digital health" och "rural development" för att ta reda på de viktigaste utmaningarna för landsbygden när de implementerar och använder digitala hälsolösningar. "Landsbygdsområden" avser i detta arbete områden med låg befolkningstäthet och små bosättningar i de industrialiserade EU-länderna. Till att börja med byggdes ett ramverk, “Digital Health Ecosystem”, baserat på en forskningsöversikt. Detta ramverk fungerade som en översikt över de viktigaste faktorerna och intressenterna beträffande digital hälsa i allmänhet. ”Digital Health Ecosystem” användes som en del av den kvalitativa forskningsmetoden och intervjuguiden för att identifiera utmaningarna i överföringen av översikten till landsbygden. En intervjustudie genomfördes med åtta experter inom området digital hälsa med olika bakgrunder som teknik, ekonomi, samhällsvetenskap, hälsovårdssystem och smart by. Resultaten visar att det finns många hinder för digital hälsa i allmänhet, som också gäller för landsbygden. De specifika utmaningarna för landsbygden kan delas in i fyra huvudkategorier: bredbands- och mobilnät; strukturella hinder; digital acceptans &amp; kompetens; landsbygdens innovation. Resultaten visar att det smarta landsbygder och andra typer av liknande initiativ i rurala områden fortfarande befinner sig i sina tidiga stadier och att digitala strategier och nätverk måste spridas mer över hela länderna. Dessutom måste tjänsterna riktas bättre mot de specifika problemen i landsbygdssamhällen. I synnerhet eftersom behovet av digitala sjukvårdslösningar är mycket stort på landsbygden, där de kan motverka problem som brist på vårdgivare och dålig sjukvård. I detta sammanhang bör alla allmänna och specifika utmaningar inte beaktas separat, eftersom ekosystemets komplexitet bara kan förstås genom att koppla samman alla olika handlingsfält.

<p dir="ltr">In this dissertation, efforts and innovations are made to advance subtle pattern mining, edge computing, and system efficiency optimization for biomedical applications, thereby advancing precision medicine big data.</p><p dir="ltr">Brain visual dynamics encode rich functional and biological patterns of the neural system, promising for applications like intention decoding, cognitive load quantization and neural disorder measurement. We here focus on the understanding of the brain visual dynamics for the Amyotrophic lateral sclerosis (ALS) population. We leverage a deep learning framework for automatic feature learning and classification, which can translate the eye Electrooculography (EOG) signal to meaningful words. We then build an edge computing platform on the smart phone, for learning, visualization, and decoded word demonstration, all in real-time. In a further study, we have leveraged deep transfer learning to boost EOG decoding effectiveness. More specifically, the model trained on basic eye movements is leveraged and treated as an additional feature extractor when classifying the signal to the meaningful word, resulting in higher accuracy.</p><p dir="ltr">Efforts are further made to decoding functional Near-Infrared Spectroscopy (fNIRS) signal, which encodes rich brain dynamics like the cognitive load. We have proposed a novel Multi-view Multi-channel Graph Neural Network (mmGNN). More specifically, we propose to mine the multi-channel fNIRS dynamics with a multi-stage GNN that can effectively extract the channel- specific patterns, propagate patterns among channels, and fuse patterns for high-level abstraction. Further, we boost the learning capability with multi-view learning to mine pertinent patterns in temporal, spectral, time-frequency, and statistical domains.</p><p dir="ltr">Massive-device systems, like wearable massive-sensor computers and Internet of Things (IoTs), are promising in the era of big data. The crucial challenge is about how to maximize the efficiency under coupling constraints like energy budget, computing, and communication. We propose a deep reinforcement learning framework, with a pattern booster and a learning adaptor. This framework has demonstrated optimally maximizes the energy utilization and computing efficiency on the local massive devices under a one-center fifteen-device circumstance.</p><p dir="ltr">Our research and findings are expected to greatly advance the intelligent, real-time, and efficient big data harnessing, leveraging deep learning, edge computing, and efficiency optimization.</p>

This research proposes Stress-Lysis, iLog and SaYoPillow to automatically detect and monitor the stress levels of a person. To self manage psychological stress in the framework of smart healthcare, a deep learning based novel system (Stress-Lysis) is proposed in this dissertation. The learning system is trained such that it monitors stress levels in a person through human body temperature, rate of motion and sweat during physical activity. The proposed deep learning system has been trained with a total of 26,000 samples per dataset and demonstrates accuracy as high as 99.7%. The collected data are transmitted and stored in the cloud, which can help in real time monitoring of a person's stress levels, thereby reducing the risk of death and expensive treatments. The proposed system has the ability to produce results with an overall accuracy of 98.3% to 99.7%, is simple to implement and its cost is moderate. Chronic stress, uncontrolled or unmonitored food consumption, and obesity are intricately connected, even involving certain neurological adaptations. In iLog we propose a system which can not only monitor but also create awareness for the user of how much food is too much. iLog provides information on the emotional state of a person along with the classification of eating behaviors to Normal-Eating or Stress-Eating. This research proposes a deep learning model for edge computing platforms which can automatically detect, classify and quantify the objects in the plate of the user. Three different paradigms where the idea of iLog can be performed are explored in this research. Two different edge platforms have been implemented in iLog. The platforms include mobile, as it is widely used, and a single board computer which can easily be a part of network for executing experiments, with iLog Glasses being the main wearable. The iLog model has produced an overall accuracy of 98% with an average precision of 85.8%. Smart-Yoga Pillow (SaYoPillow) is envisioned as a device that may help in recognizing the importance of a good quality sleep to alleviate stress while establishing a measurable relationship between stress and sleeping habits. A system that analyzes the sleeping habits by continuously monitoring the physiological changes that occur during rapid eye movement (REM) and non-rapid eye movement (NREM) stages of sleep is proposed in the current work. In addition to the physiological parameter changes, factors such as sleep duration, snoring range, eye movement, and limb movements are also monitored. The SaYoPillow system is processed at the edge level with the storage being at the cloud. SaYoPillow has 96% accuracy which is close to other existing research works. This research can not only help in keeping an individual self-aware by providing immediate feedback to change the lifestyle of the person in order to lead a healthier life, but can also play a significant role in the state-of-the-art by allowing computing on the edge devices.

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.