Alessandro Gobbetti
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Alessandro Gobbetti has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Hristijan Gjoreski
Ss. Cyril and Methodius University in Skopje, Skopje, Macedonia
2 shared publications - Marc Langheinrich
Faculty of Informatics, Universitá della Svizzera italiana (USI), Lugano, Switzerland
2 shared publications - Martin Gjoreski
Faculty of Informatics, Università della Svizzera italiana, Lugano, Switzerland
2 shared publications - Daniel Josifovski
Faculty of Electrical Engineering and Information Technologies, Macedonia
1 shared publication - Dario Fenoglio
Universita della Svizzera italiana, Switzerland
1 shared publication - Mattias Formo
Universita della Svizzera italiana, Switzerland
1 shared publication
Latest Publications
- 22 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Pervasive Computing
- Vol. 23 (4) , 40-49
FedMMA-HAR: Federated Learning for Human Activity Recognition With Missing Modalities Using Head-Worn Wearables
Regular physical activity benefits physical and mental health, making it essential for overall population health. Wearable devices using data from multiple modalities (e.g., accelerometers and gyroscopes), combined with machine learning (ML) insights, help improve exercise regimens. However, continuous data collection and personal data processing raise privacy concerns. Federated learning (FL) mitigates these by keeping data on user devices, training ML models locally, and sharing only model updates, but its applicability to human activity recognition is limited. We propose the missing modality agnostic (MMA) method, which makes FL robust to missing data, enabling accurate output even if some modalities are missing. Experimental results on two datasets (OCOsense Smart Glasses and USI-HEAR Earbuds) show that MMA-based models are effective with feature-based ML and deep learning and compatible with centralized ML and FL. This work fills a critical gap in current FL methodologies, ensuring robustness under imperfect data conditions, common in real-world scenarios.
- 22 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Pervasive Computing
- Vol. 23 (4) , 40-49
FedMMA-HAR: Federated Learning for Human Activity Recognition With Missing Modalities Using Head-Worn Wearables
Regular physical activity benefits physical and mental health, making it essential for overall population health. Wearable devices using data from multiple modalities (e.g., accelerometers and gyroscopes), combined with machine learning (ML) insights, help improve exercise regimens. However, continuous data collection and personal data processing raise privacy concerns. Federated learning (FL) mitigates these by keeping data on user devices, training ML models locally, and sharing only model updates, but its applicability to human activity recognition is limited. We propose the missing modality agnostic (MMA) method, which makes FL robust to missing data, enabling accurate output even if some modalities are missing. Experimental results on two datasets (OCOsense Smart Glasses and USI-HEAR Earbuds) show that MMA-based models are effective with feature-based ML and deep learning and compatible with centralized ML and FL. This work fills a critical gap in current FL methodologies, ensuring robustness under imperfect data conditions, common in real-world scenarios.
- Open Access
- 3 December 2023
- Published by Association for Computing Machinery (ACM)
- p. 25-36
Federated Learning for Privacy-aware Cognitive Workload Estimation
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.
- 3 December 2023
- Published by Association for Computing Machinery (ACM)
- p. 25-36
Open AccessFederated Learning for Privacy-aware Cognitive Workload Estimation
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.