A spacewalk, or extravehicular activity (EVA), is one of the most mission critical and physically and cognitively challenging tasks that crewmembers complete. With next-generation missions to the Moon and Mars, exploration EVA will challenge crewmembers in partial gravity environments with increased frequency, duration, and autonomy of operations. Given the distance from Earth, associated communication delays, and durations of exploration missions, there is a monumental shift in responsibility and authority taking place in spaceflight; moving from Earth-dependent to crew self-reliant. For the safety, efficacy, and efficiency of future surface EVAs, there is a need to better understand crew health and performance. With this knowledge, technology and operations can be designed to better support future crew autonomy. The focus of this dissertation is to develop and evaluate a psychophysiological monitoring tool to classify cognitive workload during an operationally relevant EVA task. This was completed by compiling a sensor suite of commercial wearable devices to record physiological signals in two human research studies, one at Virginia Tech and one at NASA Johnson Space Center. The approach employs supervised machine learning to recognize patterns in psychophysiological features across different psychological states. This relies on the ability to simulate, or induce, cognitive workload in order to label data for training the model. A virtual reality (VR) Translation Task was developed to control and quantify cognitive demands during an immersive, ambulatory EVA scenario. Participants walked on a passive treadmill while wearing a VR headset to move along a virtual lunar surface. They walked with constraints on time and resources, while simultaneously identifying and recalling waypoints in the scene. Psychophysiological features were extracted and labeled according to the task demands, i.e. high or low cognitive workload, for the novel Translation Task, as well as for the benchmark Multi-Attribute Task Battery (MATB). Predictive models were created using the K Nearest Neighbor (KNN) algorithm. The contributions of this dissertation span the simulation, characterization, and modeling of cognitive state. Ultimately, this work tests the limits of extending laboratory psychophysiological monitoring to more realistic environments using wearable devices, and of generalizing predictive models across participants, times, and tasks. This work paves the way for future field studies and real-time implementation to close the loop between human and automation. / Doctor of Philosophy / A spacewalk is one of the most important and physically and mentally challenging tasks that astronauts complete. With next-generation missions to the Moon and Mars, exploration spacewalks will challenge astronauts in reduced-weight environments (1/6 and 1/3 Earth's gravity) with longer, more frequent spacewalks and with less help from mission control. To keep astronauts safe while exploring there is a need to better understand astronaut health and performance (physical and mental) during spacewalks. With knowledge of how astronauts will respond to high workload and stressful events, we can plan missions and design tools that can best assist them during spacewalks on the Moon and Mars when help from Earth mission control is limited. Traditional tools of quantifying mental state are not suitable for real-time assessment during spacewalks. Current methods, including subjective surveys and performance-based computer tests, require time and attention to complete and cannot assess real-time operations. The focus of this dissertation is to create a psychophysiological monitoring tool to measure mental workload during a virtual reality (VR) spacewalk. Psychophysiological monitoring uses physiological measures, like heart rate and breathing rate, to predict psychological state, like high workload or stress. Physiological signals were recorded using commercial wearable devices in two human research studies, one at Virginia Tech and one at NASA Johnson Space Center. With machine learning, computer models can be trained to recognize patterns in physiological measures for different psychological states. Once a model is trained, it can be tested on new data to predict mental workload. To train and test the models, participants in the studies completed high and low workload versions of the VR task. The VR task was specifically designed for this study to simulate and measure performance during a mentally-challenging spacewalk scenario. The participants walked at their own pace on a treadmill while wearing a VR headset to move along a virtual lunar surface, while balancing their time and resources. They were also responsible for identifying and recalling flags along their virtual path. Ultimately, this work tests the limits of extending laboratory psychophysiological monitoring to more realistic environments using wearable devices, and of generalizing predictive models across participants, times, and tasks. This work paves the way for future field studies and real-time implementation to close the loop between human and automation.

Acquiring joint kinematics, joint moments, and ground reaction forces (GRFs) during walking is essential for assessing disease progression and health monitoring during rehabilitation. However, spatial and temporal constraints, expert processing, and high costs limit the current gold standard methods, such as optical motion capture systems and floor-embedded force plates. Experts have suggested wearables with machine learning methods to address this issue, but their large sensor count renders them impractical for daily use, and the use of generic algorithms limits their accuracy. As a result, learning kinematics and kinetics in everyday life outside of laboratory settings is challenging. Thus, there is a need for an inexpensive, near-real-time system and an accurate method for estimating kinematics, joint moments, and GRFs. This dissertation proposes using shoe-mounted IMU sensors and deep learning to estimate these parameters across various locomotion modes, reflecting everyday walking conditions. Four different approaches are explored. The first approach uses shoe-embedded IMU sensors with novel deep learning models, DeepBBWAE-Net, Kinetics-FM-DLR-Ensemble-Net, and DL-Kinetics-FM-Net, which outperform state-of-the-art models but are computationally expensive. The second approach introduces Kinematics-Net and Kinetics-MMF-Net, which are lightweight yet maintain similar performance. Sparse IMU sensors on the feet may miss critical walking dynamics, so the third approach proposes a sensor distillation technique, transferring knowledge from a teacher model (trained with full sensors) to a student model (trained with sparse IMUs), enhancing estimation accuracy. Although our models are trained on a substantial number of subjects, deep learning models tend to perform better with larger datasets. Collecting extensive subject data is resource-intensive and time-consuming. Additionally, public datasets often differ in sensor types, locations, and protocols. Our fourth approach addresses this by proposing a domain adaptation technique that transfers knowledge from source datasets to the target dataset, improving performance in the target domain.

Das weite Feld der Digitalisierung findet in Deutschland unter dem Begriff "Industrie 4.0" erste Anwendungen in der Arbeitswelt. Die vorliegende Bachelorarbeit untersucht industrielle Assistenzsysteme. Diese können in ganz unterschiedler Art und Weise dem Mitarbeiter zur Verfügung gestellt werden. Unterstützung bei der Verrichtung von Arbeitsaufgaben ist das Ziel. Dabei können die Systeme als tragbare Kleinstcomputer am Körper eingesetzt werden, oder als umfassendes Verarbeitungssystem von Produktionsdaten im Unternehmen implementiert werden. Betrachtet werden zwei prägnante Beispiele aus diesem Bereich der Assistenz für den Mitarbeiter im produzierenden Unternehmen. Eine ständig wachsende Menge von Assistenzsystemen am Markt lässt sich bislang nur anhand von Werbung und Produktvorstellungen charakterisieren. Das Ziel dieser Arbeit ist es, die beiden Beispielsysteme nach Gesichtspunkten der Arbeitswissenschaft zu untersuchen. Tauglichkeit für das Tagesgeschäft, ergonomische und mitarbeiterfreundliche Bedienung werden betrachtet. In den theoretischen Grundlagen wird ein allgemeines Verständnis der Begriffe aus dem Bereich der Digitalisierung aufgebaut. Weiterhin wird ein Überblick über die verwendeten Beispielsysteme ausgehend von deren Produktvorstellungen gegeben. Diese Systeme werden mit qualitativen Forschungsmethoden durch einen Experten der Branche evaluiert. Kernaussagen aus verschiedenen Bereichen, wie beispielsweise Ergonomie und Einsetzbarkeit werden abgeleitet. / The broad field of digitalisation finds its first applications in the German working environment under the term "Industry 4.0". This bachelor thesis examines industrial assistance systems that can be made available to employees in many different ways, with the goal to support the performance of work tasks. The systems can be used as portable microcomputers on the body or implemented as a comprehensive processing system for company production data. The thesis examines two concise examples from this area of employee assistance in manufacturing companies. To date, a constantly growing number of assistance systems on the market can only be characterised by advertising and product concepts. The aim of this thesis is to analyize the two example systems from an ergonomics point of view as well as suitability for day-to-day business and employee-friendly operations. In the theoretical basics, a general understanding of terms from the field of digitalisation is developed. Furthermore, an overview of the example systems utilized is provided based on their product presentations. These systems are evaluated by an industry expert using qualitative research method to determine core statements from various areas, such as ergonomics and usability.

Wearables som teknologi inom träning är ett etablerat koncept och många använder sig av dessa bärbara enheter. Statistik från Världshälsoorganisationen (WHO) visar att 23% av alla vuxna inte är tillräckligt fysiskt aktiva och forskning visar även på att många slutar använda sina wearables. Samtidigt har det gjorts få studier som undersöker dem faktorer som får användarna att acceptera teknologin. Denna studie kommer med utgångspunkt i UTAUT-modellens konstrukt och demografiska variabler, studera svenskatalande användares acceptans av deras wearable i träning. Den data som studien bygger på samlades in genom en surveyundersökning och analyserades med statistiska metoder. Resultatet av den kvantitativa studien påvisade att intentionen till att använda en wearable i träning har störst påverkan på den faktiska användningen. Intentionen påverkas främst av förväntad prestanda. / Wearable fitness technology is a well known concept, with plenty of users. Statististics from the WorldHealthOrganization show that 23% of all adults do not exercise enough. Other studies have shown that many users stop using their wearable devices, as well as the fact that earlier studies have not focused on explaining acceptance and intention to use wearables in fitness. Following study is based on the constructs and moderating variables of the UTAUT-model and implies to investigate wearables acceptance in fitness of swedish speaking people. The data was gathered by a survey and was analysed using statistical methods. We found that Behavioral intention explained Use behaviour, and the intention to use wearable in fitness was mostly affected by Performance Expectancy.

To measure physical activity in a wheelchair user is important. Disabled people have been found to be less active and it has negative health implications. By relating to ones own physical activity in concrete form it is easier to reinforce a positive attitude towards being physically active. The aim of this thesis is to show how a system can be built, that is able to collect measurements from sensors, with usability in mind. The system consists of software that integrates an iPhone, Apple Watch and a Tacx rotation sensor mounted on a wheelchair. With the help of a physics model these measurements can estimate energy expenditure of a wheelchair user. The system was tested with four participants performing subjectively decided low, moderate and vigorous physical activity while the system collected data. In terms of absolute energy expenditure the system was inaccurate. On the other hand, correlations were found between the calculated energy expenditures and physical activity. Using measurements from the rotations sensor a correlation of 0.7315 was found between the calculated energy expenditure and physical activity, a correlation of 0.5385 using measurements from the GPS and a correlation of 0.6452 using measurements from Apples own proprietary algorithm. The created system is a promising prototype towards objective measurement of physical activity in wheelchair users.

The market for wearable devices is continuously growing and has seen an in- crease in interest and demand this past year, specifically smartwatch devices. With several big players entering and trying to take place in the market the number of devices and platforms grow. This leads to device and software fragmentation like the one seen in the world of smartphones. In this paper I discuss and compare the two smartwatch platforms Android Wear and Apple Watch in terms of possibilities, limitations and differences. Research is done to find cross-platform development possibilities for these platforms. Extensive theoretical background of both APIs is researched and presented. An app for both smartwatch platforms is developed with integration of the WebSocket protocol to function as a remote control for a Video-On-Demand web service. This is done to showcase the cross-platform possibilities and differences of the platforms. As a result the biggest differences are out- lined and a conclusion is made that cross-platform development for these platforms can be challenging but is possible on certain levels.

The aim of diploma thesis is description and application of new product in life insurance area. This product is based on insured body parameters and physical activity monitoring with the assistance of wearables. Based on analysis of the data obtained by the insurance company, it can be setting appropriate and fair price of life insurance. Introduction describes principle of Internet of Things, which idea is reflected in next part described eHealth and telemedicine industries, where will be defined the possibilities of use information and communication technologies in these industries. One from the technologies using in these industries are already mentioned wearables, which can be used into the basic monitoring of individuals health condition. Except of health services is possible use these wearables in insurance industry too, where can monitor physical activity and selected body parameters of individuals and motivate them to exercise and healthy lifestyle in form of insurance discounts. The thesis points to current situation of using these devices at the local as well as global insurance market and possible principle of monitoring and analysis body parameters and lifestyle at Czech insurance market in the form of a new life insurance product.

Equilab is a specific solution of a self-tracking application specially developed for the field of horse riding. The aim of the thesis is to study the effects of the application on already existing rider-horse relationship from the rider's perspective. The study examines human-horse relationships in history and today, considering the possibilities of Equilab and use of wearable electronics in animals. The qualitative research was based on structured interviews with open questions.

Wearable technology has many potential benefits for employees in the workplace, including safety, health, and motivation. However, there are also many concerns about privacy and the use of data from these devices. More research is needed to understand how privacy affects the user acceptance of wearables in the workplace. The purpose of this thesis is to understand how users perceive and accept wearables at work from a privacy perspective. The thesis studied wearable fitness trackers and evaluated the acceptance of these based on an extended version of the technology acceptance model (TAM). The thesis performed qualitative interviews with users who use wearables daily and presents the largest factors identified to influence the acceptance of wearable fitness trackers at work from a privacy context. The result of the research shows that there are three main factors influencing the acceptance of wearables in the workplace from a privacy perspective: User’s privacy and data disposition, the importance of transparency, and the importance of aligned subjective norms.

The presence of smart wearables has established itself as a norm of the 21 st century, but the state of their trustworthiness from the viewpoint of personal safety remains debatable. The information gathered by such devices has great potential for personal safety risks and must be handled safely. Previous work on the Garmin Venu watch gave room for relevant future work. This thesis aims to perform further evaluation of this smartwatch in unexplored areas. The work took inspiration from the relatively new “PatrIoT” penetration testing methodology, developed in-house at the Network and Systems Engineering lab, customized for penetration testing of Internet of Things devices. This project examined a broad surface on the watch including network traffic, data over USB connection, a few details in the watch’s update mechanism, probed for some memory attack mitigations, fuzz testing of some functions in the Software Development Kit’s Application Programming Interface, and some more. According to these investigations, the watch is perceived as safe. A deeper look into some investigations is left for future work. / Bärbara enheter har blivit en normal del av 21:a århundradet, men deras pålitlighet från ett personligt säkerhetssynvinkel är diskutabelt. Informationen som samlas in av dessa har stort potential för att orsaka personliga säkerhetsrisker och måste hanteras säkert. Tidigare utförda undersökningar av Garmin Venu-smartklockan lämnade utrymme för relevant framtida arbete. Det här examensarbetet siktar på att utföra ytterligare undersökningar av denna smartklocka. Arbetet tog inspiration av det relativt nya “PatrIoT” intrångstestmetodologin, internt utvecklad av personalen i avdelningen för nätverk och systemteknik, skräddarsydd för intrångstestning av Sakernas Internet-enheter. Det här projektet undersökte en bred attackyta på klockan, inkluderande datatrafik, data över USB-anslutning, några detaljer i klockans uppdateringsmekanism, undersökte närvaron av några mekanismer för minnesbaserade attacker, försök till störningsattacker i programvaruutvecklingssatsens applikationsprogrammeringsgränssnitt, med flera. Enligt dessa undersökningar uppfattas klockan vara säker. En djupare undersökning av dessa aspekter lämnas till framtida arbete.