One of the major open problems in sensor-based Human Activity Recognition (HAR) is the scarcity of labeled data. Among the many solutions to address this challenge, semi-supervised learning approaches represent a promising direction. However, their centralized architecture incurs in the scalability and privacy problems that arise when the process involves a large number of users. Federated learning (FL) is a promising paradigm to address these problems. However, the FL methods that have been proposed for HAR assume that the participating users can always obtain labels to train their local models (i.e., they assume a fully supervised setting). In this work, we propose FedAR: a novel hybrid method for HAR that combines semi-supervised and federated learning to take advantage of the strengths of both approaches. FedAR combines active learning and label propagation to semi-automatically annotate the local streams of unlabeled sensor data, and it relies on FL to build a global activity model in a scalable and privacy-aware fashion. FedAR also includes a transfer learning strategy to fine-tune the global model on each user. We evaluated our method on two public datasets, showing that FedAR reaches recognition rates and personalization capabilities similar to state-of-the-art FL supervised approaches. As a major advantage, FedAR only requires a very limited number of annotated data to populate a pre-trained model and a small number of active learning questions that quickly decrease while using the system, leading to an effective and scalable solution for the data scarcity problem of HAR.

Semi-supervised and personalized federated activity recognition based on active learning and label propagation / R. Presotto, G. Civitarese, C. Bettini. - In: PERSONAL AND UBIQUITOUS COMPUTING. - ISSN 1617-4909. - 26:5(2022 Jun), pp. 1281-1298. [10.1007/s00779-022-01688-8]

Semi-supervised and personalized federated activity recognition based on active learning and label propagation

R. Presotto
Primo
;
G. Civitarese
Secondo
;
C. Bettini
Ultimo
2022

Abstract

One of the major open problems in sensor-based Human Activity Recognition (HAR) is the scarcity of labeled data. Among the many solutions to address this challenge, semi-supervised learning approaches represent a promising direction. However, their centralized architecture incurs in the scalability and privacy problems that arise when the process involves a large number of users. Federated learning (FL) is a promising paradigm to address these problems. However, the FL methods that have been proposed for HAR assume that the participating users can always obtain labels to train their local models (i.e., they assume a fully supervised setting). In this work, we propose FedAR: a novel hybrid method for HAR that combines semi-supervised and federated learning to take advantage of the strengths of both approaches. FedAR combines active learning and label propagation to semi-automatically annotate the local streams of unlabeled sensor data, and it relies on FL to build a global activity model in a scalable and privacy-aware fashion. FedAR also includes a transfer learning strategy to fine-tune the global model on each user. We evaluated our method on two public datasets, showing that FedAR reaches recognition rates and personalization capabilities similar to state-of-the-art FL supervised approaches. As a major advantage, FedAR only requires a very limited number of annotated data to populate a pre-trained model and a small number of active learning questions that quickly decrease while using the system, leading to an effective and scalable solution for the data scarcity problem of HAR.
Activity recognition; Federated learning; Semi-supervised learning; Mobile computing
Settore INF/01 - Informatica
Article (author)
File in questo prodotto:
File Dimensione Formato  
Presotto2022_Article_Semi-supervisedAndPersonalized.pdf

accesso aperto

Tipologia: Publisher's version/PDF
Dimensione 3.24 MB
Formato Adobe PDF
3.24 MB Adobe PDF Visualizza/Apri
s00779-022-01688-8.pdf

accesso aperto

Tipologia: Publisher's version/PDF
Dimensione 3.26 MB
Formato Adobe PDF
3.26 MB Adobe PDF Visualizza/Apri
Pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/2434/932104
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? ND
social impact