Multi-Frequency Federated Learning for Human Activity Recognition Using Head-Worn Sensors
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912745705701376 |
|---|---|
| author | Fenoglio, Dario Li, Mohan Casnici, Davide Laporte, Matias Gashi, Shkurta Santini, Silvia Gjoreski, Martin Langheinrich, Marc |
| author_facet | Fenoglio, Dario Li, Mohan Casnici, Davide Laporte, Matias Gashi, Shkurta Santini, Silvia Gjoreski, Martin Langheinrich, Marc |
| contents | Human Activity Recognition (HAR) benefits various application domains, including health and elderly care. Traditional HAR involves constructing pipelines reliant on centralized user data, which can pose privacy concerns as they necessitate the uploading of user data to a centralized server. This work proposes multi-frequency Federated Learning (FL) to enable: (1) privacy-aware ML; (2) joint ML model learning across devices with varying sampling frequency. We focus on head-worn devices (e.g., earbuds and smart glasses), a relatively unexplored domain compared to traditional smartwatch- or smartphone-based HAR. Results have shown improvements on two datasets against frequency-specific approaches, indicating a promising future in the multi-frequency FL-HAR task. The proposed network's implementation is publicly available for further research and development. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_03287 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Multi-Frequency Federated Learning for Human Activity Recognition Using Head-Worn Sensors Fenoglio, Dario Li, Mohan Casnici, Davide Laporte, Matias Gashi, Shkurta Santini, Silvia Gjoreski, Martin Langheinrich, Marc Machine Learning Distributed, Parallel, and Cluster Computing Human Activity Recognition (HAR) benefits various application domains, including health and elderly care. Traditional HAR involves constructing pipelines reliant on centralized user data, which can pose privacy concerns as they necessitate the uploading of user data to a centralized server. This work proposes multi-frequency Federated Learning (FL) to enable: (1) privacy-aware ML; (2) joint ML model learning across devices with varying sampling frequency. We focus on head-worn devices (e.g., earbuds and smart glasses), a relatively unexplored domain compared to traditional smartwatch- or smartphone-based HAR. Results have shown improvements on two datasets against frequency-specific approaches, indicating a promising future in the multi-frequency FL-HAR task. The proposed network's implementation is publicly available for further research and development. |
| title | Multi-Frequency Federated Learning for Human Activity Recognition Using Head-Worn Sensors |
| topic | Machine Learning Distributed, Parallel, and Cluster Computing |
| url | https://arxiv.org/abs/2512.03287 |