An incremental learning method with hybrid data over/down-sampling for sEMG-based gesture classification. (May 2023)

• Record Type: Journal Article
• Authors: Hua, Shaoyang; Wang, Congqing; Lam, H.K.; Wen, Shuhuan
• Is Part Of: Biomedical signal processing and control. Volume 83(2023)
• Publication Date: 2023-05
• Subjects: Incremental learning (IL) -- Surface electromyography (sEMG) -- Convolutional neural network (CNN) -- Gestures recognition -- Data imbalance; 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.2023.104613
• Languages: English
• ISSNs: 1746-8094

Abstract

Highlights: An incremental learning method is introduced to learn additional gestures continuously. A dual-stream CNN is built to extract both fully and local field information based on frequency spectrum. Various of representative sample selection methods are compared to analyze the sEMG dataset. Data augmentation and loss function modification have been attempted to solve data imbalance. Furthermore, a HDOD method considering the ratio of gestures number is proposed to improve the overall performance. Better performance with both small- and large-scale incremental learning is achieved. Abstract: Surface electromyography(sEMG)-based gesture classification methods have been widely developed in neural decoding. However, these decoding methods are usually constrained to a fixed set of gestures, which hinders flexibility in practical application. This paper contributes to an incremental learning framework to make classifiers learn different gesture sets (new tasks) gradually without catastrophic forgetting. First, this study analyzes the existing neural decoding methods with deep learning, and introduces an early and late fusion convolutional neural network (ELFCNN) structure based on frequency spectrum. Then, a sEMG-based gesture classification with incremental learning is demonstrated, which modifies the end to end learning method with hybrid data over/down-sampling (HDOD) method. By combining ELFCNN and the HDOD progress, the incremental learning method can make a comparable performance without data dimension reduction, and mitigate catastrophic forgetting while reducing data storage. Experimental results on both small and large size situations show consistent classification accuracy improvement from 0.47% to 0.71% compared with other popular incremental learning methods.