Split Learning (SL) is a promising Distributed Learning approach in electromyography (EMG) based prosthetic control, due to its applicability within resource-constrained environments. Other learning approaches, such as Deep Learning and Federated Learning (FL), provide suboptimal solutions, since prosthetic devices are extremely limited in terms of processing power and battery life. The viability of implementing SL in such scenarios is caused by its inherent model partitioning, with clients executing the smaller model segment. However, selecting an inadequate cut layer hinders the training process in SL systems. This paper presents an algorithm for optimal cut layer selection in terms of maximizing the convergence rate of the model. The performance evaluation demonstrates that the proposed algorithm substantially accelerates the convergence in an EMG pattern recognition task for improving prosthetic device control.

Understanding emotional states through facial expressions plays a pivotal role in various domains, from mental health assessments to human-computer interaction. In this study, we present an algorithm tailored for efficient, real-time, on-the-edge monitoring of key facial expressions, utilizing the data from novel optomyography (OMG) based smart glasses - OCOsense™. The expressions targeted in this study include low-and high-intensity variation of: smile, frown, eyebrow raise, and winks, facilitating a comprehensive understanding of key facial expressions essential for emotional assessment. The algorithm, developed and evaluated on a large dataset of 40 participants, prioritizes low power consumption and fast inference times. After performing optimization steps that include feature selection and model hyper-parameter tuning, our final prototype achieved a compact code size of 71.3 kB and an accuracy of 93.8%, all while maintaining power consumption at 0.43 watts.

Human physiological monitoring has become easily accessible by integrating wearable devices into our lives, providing valuable real-time data. Methods for Cognitive Workload (CW) estimation utilize such physiological data to quantify CW during task execution. These methods are crucial for various domains, including mobile healthcare, forecasting human errors, and human-machine interaction. However, accurately estimating CW continues to pose a challenge due to the absence of objective ground truth data, context dependency, and the privacy sensitivity of the data. This study tackled the complex task of estimating CW based on privacy-sensitive data (e.g., eye movement, pupil diameter, blink information, and other physiological signals) using Federated Learning (FL) methods to improve user privacy. We compared the outcomes of the FL models with the more conventional centralized approach on two publicly-available datasets COLET and ADABase, which include data from 75 participants overall. The results highlight the efficacy of FL in collaboratively training a global (person-independent) model. The FL models achieved performances on par with centralized state-of-the-art models while preserving data privacy. Recognizing the importance of privacy in user sensing, FL presents a promising approach that enables wearable sensing applications in privacy-sensitive domains.

Virtual Reality (VR) has become a mainstream opportunity to develop immersive environments where people are exposed to relevant stimuli in a systematic but safe way. Besides the controlled exposure to stimuli, VR systems enable a more efficient and unbiased gathering of information with practical applications in diagnosis, intervention, and health monitoring processes. Nonetheless, scientific literature has demonstrated that interacting with VR technology and its peripherals can be challenging, especially in populations less familiar with technology (e.g., older adults) or with clinical conditions that are not adequately accommodated by the technology, such as cognitive (e.g., dementia) or physical impairments (e.g., blindness). This workshop will focus on systems, technological approaches, and theoretical frameworks to develop user/patient-centred VR tools for diagnosis, intervention, and monitoring of health and wellbeing outcomes. Moreover, we welcome work focused on accessibility issues, aiming to promote equal access and opportunity to use VR tools by people with diverse abilities.

Information technologies can assist the elderly in their daily lives and thus improve their quality of life. Here, we present a system that was developed within the framework of the EU H2020 project IN LIFE to make the elderly feel more secure. The system consists of a smartwatch, a tablet, and a web portal for carers. The smartwatch has several functionalities; the most important are automatic fall detection, SOS button, communication with carers, location detection in case of emergency, and general activity monitoring. The smartwatch communicates with the server via GSM, therefore it does not depend on wireless internet or Bluetooth connection. The tablet acts as a virtual doorman and also as an interface for the carer, while the portal acts as a central information hub for notifications, scheduling of tasks, and user overview. We present the initial feedback from the users in a pilot study and discuss some modifications that we carried out considering this feedback.

We have completed the collection of one of the richest accurately annotated mobile dataset of modes of transportation and locomotion. To do this, we developed a highly reliable Android application called DataLogger capable of recording multisensor data from multiple synchronized smartphones simultaneously. The application allows real-time data annotation. We explain how we designed the app to achieve high reliability and ease of use. We also present an evaluation of the application in a big-data collection (750 hours, 950 GB of data, 17 different sensor modalities), analysing the data loss (less than 0.4%) and battery consumption (≈ 6% on average per hour). The application is available as open source.

We explain how to obtain a highly versatile and precisely annotated dataset for the multimodal locomotion of mobile users. After presenting the experimental setup, data management challenges and potential applications, we conclude with the best practices for assuring data quality and reducing loss. The dataset currently comprises 7 months of measurements, collected by smartphone's sensors and a body-worn camera, while the 3 participants used 8 different modes of transportation. It comprises 950 GB of sensor data, which corresponds to 750 hours of labelled data. The obtained data will be useful for a wide range of research questions related to activity recognition, and will be made available to the community1.

In this paper we propose a method for continuous stress monitoring using data provided by a commercial wrist device equipped with common physiological sensors and an accelerometer. The method consists of three machine-learning components: a laboratory stress-detector that detects short-term stress every 2 minutes; an activity recognizer that continuously recognizes user's activity and thus provides context information; and a context-based stress detector that first aggregates the predictions of the laboratory detector, and then exploits the user's context in order to provide the final decision in a 20 minute interval. The method was trained on 21 subjects in a laboratory setting and tested on 5 subjects in a real-life setting. The accuracy on 55 days of real-life data was 92%. The method is currently being implemented as a smartphone application, which will be demonstrated at the conference.

The constant increase of the elderly population and the need to prolong the independent live, is driving the development of telecare systems. Two of the key factors of such systems are their simplicity of usage and minimal obtrusiveness. Therefore, in this paper we propose a practical, intuitive and simple smartwatch-based telecare system. The system has several functionalities, including: automatic fall detection, activity analysis, SOS red button, location information, and reminders. The proposed system can work indoors as well as outdoors, and is completely independent, i.e., it requires only a SIM card to function and does not depend on base stations, internet connection, Bluetooth and similar. The evaluation of the fall detection algorithm showed that it detects all of the fast falls and minimizes the false positives, achieving 85% accuracy.

This paper presents an approach to detecting perceived stress in students using data collected with smartphones. The goal is to develop a machine-learning model that can unobtrusively detect the stress level in students using data from several smartphone sources: accelerometers, audio recorder, GPS, Wi-Fi, call log and light sensor. From these, features were constructed describing the students' deviation from usual behaviour. As ground truth, we used the data obtained from stress level questionnaires with three possible stress levels: "Not stressed", "Slightly stressed" and "Stressed". Several machine learning approaches were tested: a general models for all the students, models for cluster of similar students, and student-specific models. Our findings show that the perceived stress is highly subjective and that only person-specific models are substantially better than the baseline.

Activity recognition with a single accelerometer placed on the torso is fairly common task, but distinguishing standing from sitting in this way is very difficult because the torso is oriented the same way during both activities, and the transition between the two is very hard to classify into going down or up. We propose a novel approach based on the Multiple Contexts Ensemble (MCE) algorithm which classifies the activity with an ensemble of classifiers, each of which considers the problem in the context of a single feature. The improvement stems from using multiple viewpoints, based on accelerometer data only, designed specifically to distinguish standing from sitting. This approach improves the accuracy on the two activities by 24 percentage points compared to regular machine learning.

Monitoring human energy expenditure is important in many health and sport applications, since the energy expenditure directly reflects the level of physical activity. The actual energy expenditure is unpractical to measure; hence, the field aims at estimating it by measuring the physical activity with accelerometers and other sensors. Current advanced estimators use a context-dependent approach in which a different regression model is invoked for different activities of the user. In this paper, we go a step further and use multiple contexts corresponding to multiple sensors, resulting in an ensemble of models for energy expenditure estimation. This provides a multi-view perspective, which leads to a better estimation of the energy. The proposed method was experimentally evaluated on a comprehensive set of activities where it outperformed the current state-of-the-art.

Due to the rapid aging of the population, many technical solutions for the care of the elderly are being developed, often involving fall detection with accelerometers. We present a novel approach to fall detection with location sensors. In our application, a user wears up to four tags on the body whose locations are detected with radio sensors. This makes it possible to recognize the user’s activity, including falling any lying afterwards, and the context in terms of the location in the apartment. We compared fall detection using location sensors, accelerometers and accelerometers combined with the context. A scenario consisting of events difficult to recognize as falls or non- falls was used for the comparison. The accuracy of the methods that utilized the context was almost 40 percentage points higher compared to the methods without the context. The accuracy of pure location-based methods was around 10 percentage points higher than the accuracy of accelerometers combined with the context.

This paper presents an approach to fall detection with accelerometers that exploits posture recognition to identify postures that may be the result of a fall. Posture recognition as a standalone task was also studied. Nine placements of up to four sensors were considered: on the waist, chest, thigh and ankle. The results are compared to the results of a system using ultra wide band location sensors on a scenario consisting of events difficult to recognize as falls or non-falls. Three accelerometers proved sufficient to correctly recognize all the events except one(a slow fall). The location-based system was comparable to two accelerometers, except that it was able to recognize the slow fall because it resulted in lying outside the bed, whose location was known to the system. One accelerometer was able to recognize only the most clear-cut fall. Two accelerometers achieved over 90% accuracy of posture recognition, which was better than the location-based system. Chest and waist accelerometers proved best at both tasks, with the chest accelerometer having a slight advantage in posture recognition.