Evaluation and comparison of federated learning algorithms for Human Activity Recognition on smartphones

Autor: Sannara Ek, François Portet, Philippe Lalanda, German Vega

Pervasive computing promotes the integration of smart devices in our living spaces to develop services providing assistance to people. Such smart devices are increasingly relying on cloud-based Machine Learning, which raises questions in terms of sec

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a3a37b26087c066d8aa155671e730524
http://arxiv.org/abs/2210.16918

Federated Self-Supervised Learning in Heterogeneous Settings: Limits of a Baseline Approach on HAR

Autor: Sannara Ek, Romain Rombourg, Francois Portet, Philippe Lalanda

Publikováno v: 2022 IEEE International Conference on Pervasive Computing and Communications Workshops and other Affiliated Events (PerCom Workshops).

Federated Learning is a new machine learning paradigm dealing with distributed model learning on independent devices. One of the many advantages of federated learning is that training data stay on devices (such as smartphones), and only learned model

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::805712a94d4540384f4481e83eea5d75
https://doi.org/10.1109/percomworkshops53856.2022.9767369

A Federated Learning Aggregation Algorithm for Pervasive Computing: Evaluation and Comparison

Autor: François Portet, Sannara Ek, German Vega, Philippe Lalanda

Publikováno v: HAL
19th IEEE International Conference on Pervasive Computing and Communications PerCom 2021
19th IEEE International Conference on Pervasive Computing and Communications PerCom 2021, Mar 2021, Kassel (virtual), Germany

Pervasive computing promotes the installation of connected devices in our living spaces in order to provide services. Two major developments have gained significant momentum recently: an advanced use of edge resources and the integration of machine l

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d00c568ab866a7bf82bc56739b49c925
https://doi.org/10.1109/percom50583.2021.9439129

Evaluation of Federated Learning Aggregation Algorithms Application to Human Activity Recognition

Autor: Sannara Ek, German Vega, Philippe Lalanda, François Portet

Publikováno v: UbiComp/ISWC '20: 2020 ACM International Joint Conference on Pervasive and Ubiquitous Computing and 2020 ACM International Symposium on Wearable Computers
UbiComp/ISWC '20: 2020 ACM International Joint Conference on Pervasive and Ubiquitous Computing and 2020 ACM International Symposium on Wearable Computers, Sep 2020, Virtual Event Mexico, France. pp.638-643, ⟨10.1145/3410530.3414321⟩
UbiComp/ISWC Adjunct

International audience; Pervasive computing promotes the integration of connected electronic devices in our living spaces in order to assist us through appropriate services. Two major developments have gained significant momentum recently: a better u

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::318863352be7b3a040fdc54afc9fc5f9
https://hal.archives-ouvertes.fr/hal-02941944/document