Human Activity Recognition Using Federated Learning

State-of-the-art deep learning models for human activity recognition use large amount of sensor data to achieve high accuracy. However, training of such models in a data center using data collected from smart devices leads to high communication costs and possible privacy infringement. In order to mi...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	2018 IEEE Intl Conf on Parallel & Distributed Processing with Applications, Ubiquitous Computing & Communications, Big Data & Cloud Computing, Social Computing & Networking, Sustainable Computing & Communications (ISPA/IUCC/BDCloud/SocialCom/SustainCom) S. 1103 - 1111
Hauptverfasser:	Sozinov, Konstantin, Vlassov, Vladimir, Girdzijauskas, Sarunas
Format:	Tagungsbericht
Sprache:	Englisch
Veröffentlicht:	IEEE 01.12.2018
Schlagworte:	Accelerometers Activity recognition Computational modeling Data models Distributed databases Distributed Machine Learning Federated Learning Human Activity Recognition Privacy Task analysis Training
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!