A lightweight multi-scale convolutional attention network for lower limb motion recognition with transfer learning

被引:2
作者
Ling, Liuyi [1 ,2 ,3 ]
Wei, Liyu [1 ]
Feng, Bin [1 ]
Lin, Zhu [3 ]
Jin, Li [1 ]
Wang, Yiwen [1 ]
Li, Weixiao [3 ]
机构
[1] Anhui Univ Sci & Technol, Sch Artificial Intelligence, Huainan 232001, Peoples R China
[2] Anhui Univ Sci & Technol, Inst Environm Friendly Mat & Occupat Hlth, Wuhu 241003, Peoples R China
[3] Anhui Univ Sci & Technol, Sch Elect & Informat Engn, Huainan 232001, Peoples R China
关键词
Wearable robots; Surface electromyography; Intention recognition; Deep learning; Transfer learning;
D O I
10.1016/j.bspc.2024.106803
中图分类号
R318 [生物医学工程];
学科分类号
0831 ;
摘要
Surface electromyography (sEMG) signals can directly reflect intention of human motion, therefore are widely used in motion recognition and robot control. However, the accuracy of recognizing lower limb gait patterns tends to decrease when applying a pre-trained model to new users. Additionally, gathering sufficient data from new users to calibrate a new model in practical applications is challenging. To address this issue, this study proposes a lightweight deep learning model that utilizes multi-scale depthwise convolution to extract multi- scale features from multi-channel sEMG signals. An attention mechanism is employed to fuse these features across channels. A transfer learning strategy involves transferring the parameters of the feature extractor from the pre-trained model to the target model. The label classifier is fine-tuned using limited data from unseen subjects. The experimental results show that the proposed model can effectively extract the features from sparse multi-channel sEMG signals and accurately identify motion intentions of lower limbs. The average recognition accuracies achieved on the Gravity dataset and ENABL3S dataset are 91.49% and 93.07%, respectively. The proposed model outperforms the baseline model in terms of recognition accuracy and training time burden. Moreover, our proposed transfer learning approach has greater efficiency compared with a training model specialized for each new users from scratch, which owes to its ability to achieve satisfactory recognition accuracy within a short calibration time by utilizing only six repetitions of training data. The research provides a viable solution to address the issue of data scarcity in practical applications and enhance user-friendliness.
引用
收藏
页数:11
相关论文
共 50 条
[41]   Multi-scale Attention Recalibration Network for crowd counting [J].
Xie, Jinyang ;
Pang, Chen ;
Zheng, Yanjun ;
Li, Liang ;
Lyu, Chen ;
Lyu, Lei ;
Liu, Hong .
APPLIED SOFT COMPUTING, 2022, 117
[42]   Multi-Scale Dense Attention Network for Stereo Matching [J].
Chang, Yuhui ;
Xu, Jiangtao ;
Gao, Zhiyuan .
ELECTRONICS, 2020, 9 (11) :1-12
[43]   Multi-scale attention in attention neural network for single image deblurring☆ [J].
Lee, Ho Sub ;
Cho, Sung In .
DISPLAYS, 2024, 85
[44]   A Multi-Scale CNN for Transfer Learning in sEMG-Based Hand Gesture Recognition for Prosthetic Devices [J].
Fratti, Riccardo ;
Marini, Niccolo ;
Atzori, Manfredo ;
Mueller, Henning ;
Tiengo, Cesare ;
Bassetto, Franco .
SENSORS, 2024, 24 (22)
[45]   A deep learning network based on multi-scale and attention for the diagnosis of chronic atrophic gastritis [J].
Chong, Yanwen ;
Xie, Ningdi ;
Liu, Xin ;
Zhang, Meng ;
Huang, Fengxing ;
Fang, Jun ;
Wang, Fan ;
Pan, Shaoming ;
Nie, Haihang ;
Zhao, Qiu .
ZEITSCHRIFT FUR GASTROENTEROLOGIE, 2022, 60 (12) :1770-1778
[46]   Chicken Image Segmentation via Multi-Scale Attention-Based Deep Convolutional Neural Network [J].
Li, Wei ;
Xiao, Yang ;
Song, Xibin ;
Lv, Na ;
Jiang, Xinbo ;
Huang, Yan ;
Peng, Jingliang .
IEEE ACCESS, 2021, 9 :61398-61407
[47]   LEVERAGE MULTI-SCALE DILATED CONVOLUTIONAL NEURAL NETWORK WITH GLOBAL ATTENTION FEATURE FUSION FOR CROWD COUNTING [J].
Lv, Meilei ;
Zhang, Kuncai ;
Zheng, Xiaoyun ;
Yang, W. E., I ;
Lu, Zhe-Ming .
INTERNATIONAL JOURNAL OF INNOVATIVE COMPUTING INFORMATION AND CONTROL, 2022, 18 (04) :1147-1162
[48]   Multi-Scale Convolutional Attention and Riemannian Geometry Network for EEG-Based Motor Imagery Classification [J].
Zhou, Ben ;
Wang, Lei ;
Xu, Wenchang ;
Jiang, Chenyu .
IEEE ACCESS, 2024, 12 :79731-79740
[49]   A Convolutional Neural Network Based on Soft Attention Mechanism and Multi-Scale Fusion for Skin Cancer Classification [J].
Bao, Qiwei ;
Han, Hua ;
Huang, Li ;
Muzahid, A. A. M. .
INTERNATIONAL JOURNAL OF PATTERN RECOGNITION AND ARTIFICIAL INTELLIGENCE, 2023, 37 (14)
[50]   Micro-expression recognition using a multi-scale feature extraction network with attention mechanisms [J].
Wang, Yan ;
Zhang, Qingyun ;
Shu, Xin .
SIGNAL IMAGE AND VIDEO PROCESSING, 2024, 18 (6-7) :5137-5147