Towards Cross-Environment Human Activity Recognition Based on Radar Without Source Data

Radar-based human activity recognition (HAR) finds various applications like assisted living and driver behavior monitoring. As radar data are heavily environment-dependent, it is becoming increasingly important to develop a transfer learning mechanism that enables a radar-based HAR system with desi...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE transactions on vehicular technology Ročník 70; číslo 11; s. 11843 - 11854
Hlavní autoři: Cao, Zhongping, Li, Zhenchang, Guo, Xuemei, Wang, Guoli
Médium: Journal Article
Jazyk:angličtina
Vydáno: New York IEEE 01.11.2021
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:
Activity recognition
Adaptation
Clustering
Continuous radiation
Deep learning
deep neural networks
Driver behavior
Feature extraction
Human activity recognition
Labeling
Labels
Learning
Moving object recognition
Radar
Radar data
Radar-based human activity recognition
Reliability
Transfer learning
unsupervised domain adaption
ISSN:0018-9545, 1939-9359
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Radar-based human activity recognition (HAR) finds various applications like assisted living and driver behavior monitoring. As radar data are heavily environment-dependent, it is becoming increasingly important to develop a transfer learning mechanism that enables a radar-based HAR system with desirable cross-environment adaptation feasibility. This paper concerns the issue of how radar-based HAR system can adapt to a new environment without source data. To this end, we devote to using the source hypothesis transfer learning architecture to build such an environment adaptation mechanism towards cross-environment radar-based HAR. In doing this, it is a challenging task to develop a reliable self-supervised labeling strategy for generating pseudo labels associated with the unlabeled target data, which is crucial to facilitate the learning of a target-specific feature extractor being responsible for environment adaptation. This paper presents the neighbor-aggregating-based labeling method and incorporates it with the existing clustering-based labeling method to perform the self-supervised labeling task. The logic behind our approach is that the above two labeling methods are complementary to each other in terms of making use of both local and global structures of adaptation data to supervise the labeling task. The coordination of both labeling methods is motivated to be implemented in the weighted combination form, which contributes to improving the reliability of generated labels. Experimental results on a public HAR dataset based on the frequency modulated continuous wave (FMCW) radar demonstrate the effectiveness of our approach.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0018-9545
1939-9359
DOI:10.1109/TVT.2021.3115877