Gaussian-guided feature alignment for unsupervised cross-subject adaptation

Zhang，Kuangen1,2,3; Chen，Jiahong3; Wang，Jing4; Leng，Yuquan1,2; de Silva，Clarence W.3; Fu，Chenglong1,2

2022-02-01

10.1016/j.patcog.2021.108332

PATTERN RECOGNITION   影响因子和分区

0031-3203

Human activities recognition (HAR) and human intent recognition (HIR) are important for medical diagnosis and human-robot interaction. HAR and HIR usually rely on the signals of some wearable sensors, such as inertial measurement unit (IMU), but these signals may be user-dependent, which degrades the performance of the recognition algorithm on new subjects. Traditional supervised learning methods require labeling signals and training specific classifiers for each new subject, which is burdensome. To deal with this problem, this paper proposes a novel non-adversarial cross-subject adaptation method called Gaussian-guided feature alignment (GFA). The proposed GFA metric quantifies the discrepancy between the labeled features of source subjects and the unlabeled features of target subjects so that minimizing the GFA metric leads to the alignment of the source and target features. The GFA metric is estimated by calculating the divergence between the feature distribution and Gaussian distribution, as well as the mean squared error of the mean and variance between source and target features. This paper analytically proves the effect of the GFA metric and validates its performance using three public human activity datasets. Experimental results show that the proposed GFA achieves 1% higher target classification accuracy and 0.5% lower variance than state-of-the-art methods in case of cross-subject validation. These results indicate that the proposed GFA is feasible for improving the generalization of the HAR and HIR.

Domain adaptation Feature alignment Human activity recognition Human intent recognition Sensor fusion

SCI ; EI

英语

第一 ; 通讯

WOS:000704893500013

20213910955059

Alignment ; Diagnosis ; Human robot interaction ; Learning systems ; Mean square error ; Wearable sensors

Medicine and Pharmacology:461.6 ; Mechanical Devices:601.1 ; Robotics:731.5 ; Probability Theory:922.1 ; Mathematical Statistics:922.2

ENGINEERING

2-s2.0-85115779175

Scopus

1.Shenzhen Key Laboratory of Biomimetic Robotics and Intelligent Systems,Department of Mechanical and Energy Engineering,Southern University of Science and Technology,Shenzhen,518055,China
2.Guangdong Provincial Key Laboratory of Human-Augmentation and Rehabilitation Robotics in Universities,Southern University of Science and Technology,Shenzhen,518055,China
3.Department of Mechanical Engineering,The University of British Columbia,Vancouver,Canada
4.Department of Electrical and Computer Engineering,The University of British Columbia,Vancouver,Canada

Zhang，Kuangen,Chen，Jiahong,Wang，Jing,et al. Gaussian-guided feature alignment for unsupervised cross-subject adaptation[J]. PATTERN RECOGNITION,2022,122.

Zhang，Kuangen,Chen，Jiahong,Wang，Jing,Leng，Yuquan,de Silva，Clarence W.,&Fu，Chenglong.(2022).Gaussian-guided feature alignment for unsupervised cross-subject adaptation.PATTERN RECOGNITION,122.

Zhang，Kuangen,et al."Gaussian-guided feature alignment for unsupervised cross-subject adaptation".PATTERN RECOGNITION 122(2022).