More Reliable Neighborhood Contrastive Learning for Novel Class Discovery in Sensor-Based Human Activity Recognition
Sensors · 2023
DOI: 10.3390/s23239529 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, 2023. Verfasst von Mingcong Zhang und 3 weiteren Autor:innen. Beteiligte Einrichtung: The School of Computer Science, University of South China, Hengyang 421001, China. Hauptthemen laut MEDLINE: Noncommunicable Diseases. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 53 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Research Foundation of Education Bureau of Hunan Province.
Abstract (Originalsprache)
Human Activity Recognition (HAR) systems have made significant progress in recognizing and classifying human activities using sensor data from a variety of sensors. Nevertheless, they have struggled to automatically discover novel activity classes within massive amounts of unlabeled sensor data without external supervision. This restricts their ability to classify new activities of unlabeled sensor data in real-world deployments where fully supervised settings are not applicable. To address this limitation, this paper presents the Novel Class Discovery (NCD) problem, which aims to classify new class activities of unlabeled sensor data by fully utilizing existing activities of labeled data. To address this problem, we propose a new end-to-end framework called More Reliable Neighborhood Contrastive Learning (MRNCL), which is a variant of the Neighborhood Contrastive Learning (NCL) framework commonly used in visual domain. Compared to NCL, our proposed MRNCL framework is more lightweight and introduces an effective similarity measure that can find more reliable k-nearest neighbors of an unlabeled query sample in the embedding space. These neighbors contribute to contrastive learning to facilitate the model. Extensive experiments on three public sensor datasets demonstrate that the proposed model outperforms existing methods in the NCD task in sensor-based HAR, as indicated by the fact that our model performs better in clustering performance of new activity class instances.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- The School of Computer Science, University of South China, Hengyang 421001, China.
ORCID-Profile: Tao Zhu, Mingxing Nie
Förderung
- Research Foundation of Education Bureau of Hunan Province
Zitieren
APA
Zhang, M., Zhu, T., Nie, M., & Liu, Z. (2023). More Reliable Neighborhood Contrastive Learning for Novel Class Discovery in Sensor-Based Human Activity Recognition. Sensors. https://doi.org/10.3390/s23239529
Vancouver
Zhang M, Zhu T, Nie M, Liu Z. More Reliable Neighborhood Contrastive Learning for Novel Class Discovery in Sensor-Based Human Activity Recognition. Sensors. 2023. doi:10.3390/s23239529
BibTeX
@article{Zhang2023,
author = {Zhang, Mingcong and Zhu, Tao and Nie, Mingxing and Liu, Zhenyu},
title = {More Reliable Neighborhood Contrastive Learning for Novel Class Discovery in Sensor-Based Human Activity Recognition},
journal = {Sensors},
year = {2023},
doi = {10.3390/s23239529}
}
EUVIMED