The EU-funded WideHealth project aims to conduct research on pervasive eHealth and establish a sustainable network of research and dissemination across Europe.
Title: Federated Learning for Activity Recognition: A System Level Perspective
Speaker: Borche Jovanovski, Ss. Cyril and Methodius University (UKIM)
When: May 9th, 2023, 16:00 CET (15:00 in Portugal)
Where: zoom link shared before the session to those who register (registration is free but mandatory)
Registration link: https://shre.ink/18thWideHealthSeminar
Abstract: The past decade has seen substantial growth in the prevalence and capabilities of wearable devices. For instance, recent human activity recognition (HAR) research has explored using wearable devices in applications such as remote monitoring of patients, detection of gait abnormalities, and cognitive disease identification. However, data collection poses a major challenge in developing HAR systems, especially because of the need to store data at a central location. This raises privacy concerns and makes continuous data collection difficult and expensive due to the high cost of transferring data from a user’s wearable device to a central repository. Considering this, we explore the adoption of federated learning (FL) as a potential solution to address the privacy and cost issues associated with data collection in HAR. More specifically, we investigate the performance and behavioral differences between FL and deep learning (DL) HAR models, under various conditions relevant to real-world deployments. Namely, we explore the differences between the two types of models when (i) using data from different sensor placements, (ii) having access to users with data from heterogeneous sensor placements, (iii) considering bandwidth efficiency, and (iv) dealing with data with incorrect labels. Our results show that FL models suffer from a consistent performance deficit in comparison to their DL counterparts, but achieve these results with much better bandwidth efficiency. Furthermore, we observe that FL models exhibit very similar responses to those of DL models when exposed to data from heterogeneous sensor placements and are also more robust to data with incorrect labels.
Short Bio: Borche Jovanovski received a BSc degree in electrical engineering and information technologies from the field of Telecommunications and M.Sc. degree in electrical and information technology from the field of wireless systems, services and applications, both from the Faculty of Electrical Engineering and Information Technologies (FEEIT), Ss. Cyril and Methodius University (UKIM) in Skopje, Macedonia in 2019 and 2021, respectively. He is currently working towards a Ph.D. degree in electrical engineering and information technologies at the same University, where he is a research associate and part of the Laboratory for Wireless and Mobile Networks. His research interests include areas of wireless networks, wireless communications, cloud computing, and recently application of machine learning and federated learning in different domains.