Federated Learning for Human Activity Recognition: Overview, Advances, and Challenges
Human Activity Recognition (HAR) has seen remarkable advances in recent years, driven by the widespread use of wearable devices and the increasing demand for personalized healthcare and activity tracking. Federated Learning (FL) is a promising paradigm for HAR that enables the collaborative training...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Open Journal of the Communications Society |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10726594/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850266290778800128 |
|---|---|
| author | Ons Aouedi Alessio Sacco Latif U. Khan Dinh C. Nguyen Mohsen Guizani |
| author_facet | Ons Aouedi Alessio Sacco Latif U. Khan Dinh C. Nguyen Mohsen Guizani |
| author_sort | Ons Aouedi |
| collection | DOAJ |
| description | Human Activity Recognition (HAR) has seen remarkable advances in recent years, driven by the widespread use of wearable devices and the increasing demand for personalized healthcare and activity tracking. Federated Learning (FL) is a promising paradigm for HAR that enables the collaborative training of machine learning models on decentralized devices while preserving data privacy. It improves not only data privacy but also training efficiency as it utilizes the computing power and data of potentially millions of smart devices for parallel training. In addition, it helps end-user devices avoid sending users’ private data to the cloud, eliminates the need for a network connection, and saves the latency of back-and-forth communication. FL also offers significant advantages for communication by reducing the amount of data transmitted over the network, alleviating network congestion and reducing communication costs. By distributing the training process across devices, FL minimizes the need for centralized data storage and processing, leading to more scalable and resilient systems. This paper provides a comprehensive survey of the integration of FL into HAR applications. Unlike existing reviews, this paper uniquely focuses on the intersection of FL and HAR, providing an in-depth analysis of recent advances and their practical implications. We explore key advances in FL-based HAR methodologies, including model architectures, optimization techniques, and different applications. Furthermore, we highlight the major challenges and future research questions in this domain, such as model personalization and robustness, privacy concerns, concept drift, and the limited capacity of edge devices. |
| format | Article |
| id | doaj-art-83f406b36f1c4befa46c6784a1ac1816 |
| institution | OA Journals |
| issn | 2644-125X |
| language | English |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Open Journal of the Communications Society |
| spelling | doaj-art-83f406b36f1c4befa46c6784a1ac18162025-08-20T01:54:12ZengIEEEIEEE Open Journal of the Communications Society2644-125X2024-01-0157341736710.1109/OJCOMS.2024.348422810726594Federated Learning for Human Activity Recognition: Overview, Advances, and ChallengesOns Aouedi0https://orcid.org/0000-0002-2343-0850Alessio Sacco1https://orcid.org/0000-0003-2835-5455Latif U. Khan2https://orcid.org/0000-0002-7678-6949Dinh C. Nguyen3https://orcid.org/0000-0002-8092-6756Mohsen Guizani4https://orcid.org/0000-0002-8972-8094SnT, University of Luxembourg, Luxembourg City, LuxembourgDAUIN, Politecnico di Torino, Turin, ItalyMachine Learning Department, Mohamed Bin Zayed University of Artificial Intelligence, Abu Dhabi, UAEDepartment of Electrical and Computer Engineering, The University of Alabama in Huntsville, Huntsville, AL, USAMachine Learning Department, Mohamed Bin Zayed University of Artificial Intelligence, Abu Dhabi, UAEHuman Activity Recognition (HAR) has seen remarkable advances in recent years, driven by the widespread use of wearable devices and the increasing demand for personalized healthcare and activity tracking. Federated Learning (FL) is a promising paradigm for HAR that enables the collaborative training of machine learning models on decentralized devices while preserving data privacy. It improves not only data privacy but also training efficiency as it utilizes the computing power and data of potentially millions of smart devices for parallel training. In addition, it helps end-user devices avoid sending users’ private data to the cloud, eliminates the need for a network connection, and saves the latency of back-and-forth communication. FL also offers significant advantages for communication by reducing the amount of data transmitted over the network, alleviating network congestion and reducing communication costs. By distributing the training process across devices, FL minimizes the need for centralized data storage and processing, leading to more scalable and resilient systems. This paper provides a comprehensive survey of the integration of FL into HAR applications. Unlike existing reviews, this paper uniquely focuses on the intersection of FL and HAR, providing an in-depth analysis of recent advances and their practical implications. We explore key advances in FL-based HAR methodologies, including model architectures, optimization techniques, and different applications. Furthermore, we highlight the major challenges and future research questions in this domain, such as model personalization and robustness, privacy concerns, concept drift, and the limited capacity of edge devices.https://ieeexplore.ieee.org/document/10726594/Federated learningmachine learninghuman activity recognitiondata privacy |
| spellingShingle | Ons Aouedi Alessio Sacco Latif U. Khan Dinh C. Nguyen Mohsen Guizani Federated Learning for Human Activity Recognition: Overview, Advances, and Challenges IEEE Open Journal of the Communications Society Federated learning machine learning human activity recognition data privacy |
| title | Federated Learning for Human Activity Recognition: Overview, Advances, and Challenges |
| title_full | Federated Learning for Human Activity Recognition: Overview, Advances, and Challenges |
| title_fullStr | Federated Learning for Human Activity Recognition: Overview, Advances, and Challenges |
| title_full_unstemmed | Federated Learning for Human Activity Recognition: Overview, Advances, and Challenges |
| title_short | Federated Learning for Human Activity Recognition: Overview, Advances, and Challenges |
| title_sort | federated learning for human activity recognition overview advances and challenges |
| topic | Federated learning machine learning human activity recognition data privacy |
| url | https://ieeexplore.ieee.org/document/10726594/ |
| work_keys_str_mv | AT onsaouedi federatedlearningforhumanactivityrecognitionoverviewadvancesandchallenges AT alessiosacco federatedlearningforhumanactivityrecognitionoverviewadvancesandchallenges AT latifukhan federatedlearningforhumanactivityrecognitionoverviewadvancesandchallenges AT dinhcnguyen federatedlearningforhumanactivityrecognitionoverviewadvancesandchallenges AT mohsenguizani federatedlearningforhumanactivityrecognitionoverviewadvancesandchallenges |