The increasing life expectancy of an aging population has caused a higher demand for healthcare services, highlighting a shortage within the healthcare system due to insufficient projected growth of healthcare personnel. One solution to this issue is the utilization of the Internet of Medical Things (IoMT). This study aims to describe the general acceptance level amongst healthcare recipients of adopting IoMT in Swedish remote healthcare and how the acceptance level differs amongst different age groups depending on the application of IoMT. Acceptance and implementation of IoMT in remote healthcare are discussed, with an emphasis on factors such as user-friendliness and practical hardware design. In this study, a digital survey was conducted with 103 respondents, which demonstrated that the majority were positive about using IoMT for monitoring and treating health conditions remotely. Although awareness of security risks exists, respondents generally expressed a low number of concerns regarding unauthorized access to information and modification of IoMT devices in general. The study's conclusion highlights the notable acceptance of IoMT in remote healthcare in Sweden. The results indicate network-connected devices are integrated into people's daily lives, and user-friendliness and cybersecurity influence the adoption of IoMT. Older age groups demonstrated less concern about cybersecurity than younger age groups. When analysing specific applications, the results show some age-related differences in acceptance, which also varied depending on the application, particularly when comparing more life-critical devices such as IoMT pacemakers with IoMT fall detectors. / Den ökande livslängden hos en ökande befolkning har skapat ett ökat vårdbehov och detta har påvisat en brist inom sjukvården då den förväntade utvecklingen av sjukvårdspersonal är otillräcklig. En lösning på detta är användandet av Internet of Medical Things (IoMT) och denna studie har som syfte att beskriva den allmänna acceptansnivån hos vårdtagare för användandet av IoMT inom den svenska distansvården samt hur acceptansnivån skiljer sig för olika åldrar beroende på tillämpning av IoMT. Acceptans och implementering av IoMT i distanssjukvården diskuteras, och faktorer som användarvänlighet och praktisk hårdvarudesign betonas. I denna studie utfördes en digital enkätundersökning innehållande 103 respondenter som visade att majoriteten var positiva till att använda IoMT för att övervaka och behandla hälsotillstånd på distans. Även om medvetenheten om säkerhetsrisker finns, var respondenternas oro för obehörig åtkomst till information samt modifiering av IoMT-utrustning generellt låg. Studiens slutsats framhäver att distansvård med IoMT har en hög acceptans i Sverige. Resultaten indikerar att nätverksanslutna enheter är integrerade i människors vardag och att användarvänlighet samt cybersäkerhet påverkar användningen av IoMT. Äldre åldersgrupper visade mindre oro för cybersäkerheten än yngre åldersgrupper. Vid analys av specifika tillämpningar visar resultaten att det finns vissa åldersrelaterade skillnader i acceptans, vilka också varierade beroende på tillämpning, särskilt i jämförelse med mer livskritiska enheter såsom IoMT-pacemakers i jämförelse med IoMT-falldetektorer.

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.

This work develops a simple and low-cost microphone-based spirometer with a scalable infrastructure that can be used to monitor COPD and Asthma symptoms. The data acquired from the system is archived in the cloud for further procuring and reporting. To develop this system, we utilize an off-the-shelf ESP32 development board, MEMS microphone, oxygen mask, and 3D printable mounting tube to keep the costs low. The system utilizes the MEMS microphone to measure the audio signal of a user's exhalation, calculates diagnostic estimations and uploads the estimations to the cloud to be remotely monitored. Our results show a practical system that can identify COPD and Asthma symptoms and report the data to both the patient and the physician. The system developed can provide a means of gathering respiratory data to better assist doctors and assess patients to provide remote care.

This research was about the continuous intention of healthcare professionals to use internet of medical things (IoMT) embedded with artificial intelligence (AI). IoMT and AI are evolving innovations and diffusing at the same time. It was not known in what way the two complex technologies diffusing concurrently could influence continuous intention to use IoMT. In addition, behavioural aspects namely motivation and training to use IoMT have been argued to intervene in the relationship between an AI based IoMT and continuous intention to use IoMT. Diffusion of Innovation theory was applied to explain the relationship between diffusion factors that aid the diffusion of AI based IoMT and continuous intention to use IoMT. The five factors relative advantage, compatibility, complexity, observability and trialability were chosen as determinants of continuous intention to use IoMT using DoI theory. Self-determination theory and theory of planned behaviour were used to introduce the interventions in the relationship between diffusion factors and continuous intention to use IoMT. UTAUT was used to explain the influence of the moderators artificial intelligence awareness, novelty seeking behaviour and age of healthcare professionals. The central issue investigated was the determinants of continuous intention of healthcare professionals to use IoMT with behavioural attributes of motivation and training conceived as mediators of the relationship between diffusion factors and continuous intention to use IoMT in the presence of moderators. Quantitative research methodology was used to test the research model developed to understand the relationship between the five diffusion of innovation theory factors and continuous intention to use IoMT when AI based IoMT is still diffusing. The concurrent diffusion of two new technologies was investigated using a research model that was developed for studying the healthcare professionals and their intention. The research was conducted in Bahrain in the healthcare sector. A sample of 354 healthcare professionals participated in the research. Structural equation modelling was used to analyse the data and test the hypothesis. The research showed that healthcare professionals will continue to use concurrently diffusing technologies depending on the relative advantage, complexity and compatibility of the innovations that diffuse. In addition, the results show that healthcare professionals will be motivated by the compatibility of AI-based IoMT if they have to continuously use IoMT. Furthermore, training enables both the organization and the healthcare professionals to overcome dilemma in case they have to continue to use an innovation during its diffusion or when new innovation surface in the market. Finally, artificial intelligence awareness is able to moderate the relationship between relative advantage, complexity and training to use IoMT. Thus, this research contributes to the discipline of behavioural intention of healthcare professionals in determining the influence of an artificial intelligence based IoMT on continuous intention to use IoMT when artificial intelligence embedded in IoMT diffuses concurrently with IoMT. Where IoMT diffusion factors can be used as a determine of continuous intention to use IoMT, artificial intelligence could be understood as a moderator of the relationship between diffusion factors and training to use IoMT, thus demonstrating the combined diffusion of the two technologies diffusing concurrently.

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.

As the rapid progress in technology changes our daily life, it also changes how the Industry works. The new developments enable technologies such as the Internet of Moving Things (IoMT), and through these technologies, new challenges arise. IoMT adds one more vital issue, localization, to be solved in comparison to the Internet of Things (IoT). To enable IoMT in the manufacturing industry, there are still problems that need to be overcome. Critical statements such as power consumption, price, accuracy, data management, and size. In this thesis, an evaluation of a new sensor system for an air pneumatic grinder is conducted. The features of the sensor system are to report data from the grinder to the cloud and to localize the position of the grinder. The focus was to optimize the localization algorithm and power consumption of the system. The localization of the grinder was conducted with a new and improved algorithm, Ring Error Difference System (REDS), introduced in this thesis. The new algorithm increased the previous known iRingLA accuracy from 2.91 m to 2.33 m for Bluetooth Low Energy (BLE) and from 3.99 m to 2.84 for Wi-Fi, according to the experiments performed. The final system was able to estimate the operation runtime with an error of 24 s for an operational runtime of 905 s. The operational lifetime of the system was 242 h and 45 h, respectively, for BLE and Wi-Fi. An optimized software was introduced to decrease power consumption. The optimized version was estimated to have an operational lifetime of 1540 h for BLE, which did not reach the wanted lifetime of 3000 h set by Atlas Copco. Hence, I conclude that the hardware, Wemos ESP32, used in the thesis, is not feasible for this solution. Simpler hardware, than the Wemos ESP32, should be used to be able to reach the goal of 3000 h. / De stora framstegen inom dagens teknik förvandlar inte bara vårt dagliga liv det förändrar också tekniken inom industrin. Den nya tekniken möjliggör framsteg så som Internet of Moving Things (IOMT), vilket leder till nya utmaningar. IoMT jämfört med Internet of Things (IoT) lägger till ytterligare utmaningar att lösa så som lokalisering. För att kunna använda IoMT inom tillverkningsindustrin måste ett flertal problem hanteras så som strömförbrukning, pris och noggrannhet på lokaliseringen, datahantering och storlek på systemet. I denna masteruppsatts gör jag en utvärdering av ett nytt sensorsystem för luftdrivna slipmaskiner. Detta sensorsystem rapporterar data från slipmaskinen till molnet och rapporterar positionen av utrustningen. Fokuset på uppsatsen var att optimera lokaliseringsalgoritmen och minska strömförbrukningen för systemet. Lokaliseringen av slipmaskinen gjordes med en ny och förbättrad algoritm, Ring Error Difference System (REDS), som jag introducerar i avhandlingen. Algoritmen förbättrade den tidigare kända RSSI-baserade iRingLA från 2,91 m till 2,33 m med Bluetooth Low Energy (BLE) och från 3,99 m till 2,84 m för Wi-Fi. Det slutliga systemet kunde uppskatta drifttiden med en avvikelse på 24 s av den verkliga drifttiden, 905 s. Systemets operativa livslängd var 242 timmar och 45 timmar för BLE respektive Wi-Fi. Dessutom infördes en optimerad programvara för att minska strömförbrukningen. Den optimerade versionen beräknades ha en livslängd på 1540 timmar för BLE, vilket inte når den önskade livslängden på 3000 timmar satt av Atlas Copco. Ifrån mitt arbete drar jag slutsatsen att hårdvaran som används i uppsatsen, inte kan användas i en slutlig produkt. En enklare hårdvara än Wemos ESP32 bör användas för att kunna nå målet på 3000 timmar.