Hierarchical Federated Learning for Hybrid Data Partitioning Across Multitype Sensors

Emerging hardware technology enables the utilization of a large number of multitype sensors with diverse sensing capabilities for data collection and the training of AI models. Each sensor collects partial data samples on a type-specific feature space, which results in hybrid data partitioning acros...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE internet of things journal 2021-07, Vol.8 (13), p.10922-10939
Hauptverfasser:	Su, Liqun, Lau, Vincent K. N.
Format:	Artikel
Sprache:	eng
Schlagworte:	Agglomeration Algorithms Artificial neural networks Collaborative work Computer architecture Data collection Data models Federated learning Federated learning (FL) Harnesses heterogeneous sensor hybrid data partitioning Machine learning Neural networks over-the-air aggregation Partitioning Perturbation Sensor phenomena and characterization Sensors Servers Signal transmission stochastic coordinate gradient descent ascent Stochastic models Stochastic processes Training
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!