A novel fusion strategy for locomotion activity recognition based on multimodal signals. (May 2021)

• Record Type: Journal Article
• Authors: Hu, Fo; Wang, Hong; Feng, Naishi; Zhou, Bin; Wei, Chunfeng; Lu, YanZheng; Qi, Yangyang; Jia, Xiaocong; Tang, Hao; Gouda, Mohamed Amin
• Is Part Of: Biomedical signal processing and control. Volume 67(2021)
• Publication Date: 2021-05
• Subjects: Locomotion activities -- Gait events -- Multimodal signals -- Convolutional neural network -- Canonical correlation analysis -- Bi-directional Long short-term memory; Signal processing -- Periodicals; Biomedical engineering -- Periodicals; Signal Processing, Computer-Assisted -- Periodicals; Image Processing, Computer-Assisted -- Periodicals; Biomedical Engineering -- Periodicals; 610.28
• DOI: 10.1016/j.bspc.2021.102524
• Languages: English
• ISSNs: 1746-8094

Abstract

Abstract: Detecting locomotion activities and gait phases are critical for recognizing movement intent and assisting humans in activities of daily living. This paper introduces a novel fusion strategy that analyzes multimodal signals (electromyograms, angular rates, and footswitches) to identify four lower limb locomotion activities (walking, running, stair ascent, and descent), four gait phases (push-up, stance, step-up, and swing) and detect gait events (heel strike and toe-off). This strategy uses different networks (convolutional neural network and Bi-directional Long Short-Term Memory) and a feature fusion method (Canonical Correlation Analysis) to perform the classification tasks and gait event detection, which transcends the limitations of conventional methods that only analyze a single signal. Then, an adaptive online algorithm is proposed, which helps the model to automatically fine-tune its parameters and gradually approach the convergence state. The offline experiment results on 20 healthy subjects show an average accuracy of 99.33 % and an average Matthews correlation coefficient of 99.56. Besides, with the help of the adaptive online algorithm, lower errors are shown in gait event detection, including 18.43 ± 7.38 ms for heel strike and 22.25 ± 7.06 ms for toe-off. Consequently, our proposed model can provide more accurate quantitative results than mainstream methods, giving it a competitive advantage for future applications.