MCDCD: Multi-Source Unsupervised Domain Adaptation for Abnormal Human Gait Detection

• Published in: IEEE journal of biomedical and health informatics Vol. 25; no. 10; pp. 4017 - 4028
• Main Authors: Guo, Yao, Gu, Xiao, Yang, Guang-Zhong
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.10.2021; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Abnormalities; Adaptation; Adaptation models; Classification; Classifiers; cross-domain; Data mining; Data models; Electromyography; EMG; Entropy; Feature extraction; Gait; Gait abnormality detection; Gait recognition; Kinematics; mocap; Motion capture; multi-source unsupervised domain adaptation; Training
• ISSN: 2168-2194; 2168-2208; 2168-2208
• DOI: 10.1109/JBHI.2021.3080502

For gait analysis, especially for the detection of subtle gait abnormalities, the collected datasets involve high variability across subjects due to inherent biometric traits and movement behaviors, leading to limited detection accuracy and poor generalizability. To address this, we propose a novel deep multi-source Unsupervised Domain Adaptation (UDA) approach, namely Maximum Cross-Domain Classifier Discrepancy (MCDCD), which aims to improve the classification performance on the test subject (target domain) by leveraging the information from multiple labelled training subjects (source domains). Specifically, the proposed model consists of a feature extractor and a domain-specific category classifier per source domain. The former feature extractor learns to generate discriminative gait features. For the latter classifiers, we minimize the cross-entropy loss to accurately classify source samples, and simultaneously maximize a novel cross-domain discrepancy loss between any two category classifiers to minimize domain shift between multiple sources and the target domain. To validate the proposed MCDCD for detecting gait abnormalities on novel subjects, we collected both high-quality Motion capture (Mocap) and noisy Electromyography (EMG) data from eighteen subjects with both normal and imitated abnormal gaits. Experiment results using both data modalities demonstrate that the proposed approach can achieve superior performance in abnormal gait classification compared to baseline deep models and state-of-the-art UDA methods.