SigRep: Towards Robust Wearable Emotion Recognition with Contrastive Representation Learning
Article
Article Title | SigRep: Towards Robust Wearable Emotion Recognition with Contrastive Representation Learning |
---|---|
ERA Journal ID | 210567 |
Article Category | Article |
Authors | Dissanayake, Vipula (Author), Seneviratne, Sachith (Author), Rana, Rajib (Author), Wen, Elliot (Author), Kaluarachchi, Tharindu (Author) and Nanayakkara, Suranga (Author) |
Journal Title | IEEE Access |
Journal Citation | 10, pp. 18105-18120 |
Number of Pages | 16 |
Year | 2022 |
Publisher | IEEE (Institute of Electrical and Electronics Engineers) |
Place of Publication | United States |
ISSN | 2169-3536 |
Digital Object Identifier (DOI) | https://doi.org/10.1109/ACCESS.2022.3149509 |
Web Address (URL) | https://ieeexplore.ieee.org/document/9706192 |
Abstract | Extracting emotions from physiological signals has become popular over the past decade. Recent advancements in wearable smart devices have enabled capturing physiological signals continuously and unobtrusively. However, signal readings from different smart wearables are lossy due to user activities, making it difficult to develop robust models for emotion recognition. Also, the limited availability of data labels is an inherent challenge for developing machine learning techniques for emotion classification. This paper presents a novel self-supervised approach inspired by contrastive learning to address the above challenges. In particular, our proposed approach develops a method to learn representations of individual physiological signals, which can be used for downstream classification tasks. Our evaluation with four publicly available datasets shows that the proposed method surpasses the emotion recognition performance of state-of-the-art techniques for emotion classification. In addition, we show that our method is more robust to losses in the input signal. |
Keywords | emotion recognition, representation learning, self-supervised learning, wearable signals |
Contains Sensitive Content | Does not contain sensitive content |
ANZSRC Field of Research 2020 | 460212. Speech recognition |
461199. Machine learning not elsewhere classified | |
Byline Affiliations | University of Auckland, New Zealand |
University of Melbourne | |
School of Mathematics, Physics and Computing | |
Institution of Origin | University of Southern Queensland |
https://research.usq.edu.au/item/q714y/sigrep-towards-robust-wearable-emotion-recognition-with-contrastive-representation-learning
Download files
Published Version
Dissanayake-2022-Sigrep-toward-robust-wearable-emoti.pdf | ||
License: CC BY 4.0 | ||
File access level: Anyone |
155
total views104
total downloads13
views this month2
downloads this month