A Novel Active Learning Framework for Cross-Subject Human Activity Recognition from Surface Electromyography

被引:0
作者
Ding, Zhen [1 ]
Hu, Tao [2 ]
Li, Yanlong [2 ]
Li, Longfei [2 ]
Li, Qi [2 ]
Jin, Pengyu [2 ]
Yi, Chunzhi [3 ]
机构
[1] Northeast Forestry Univ, Coll Comp & Control Engn, Harbin 150040, Peoples R China
[2] Harbin Inst Technol, Sch Mechatron Engn, Harbin 150001, Peoples R China
[3] Harbin Inst Technol, Sch Med & Hlth, Harbin 150001, Peoples R China
关键词
wearable sensors; human activity recognition; cross-subject issue; relation network; classifier discrepancy; surface electromyography signals; DOMAIN ADAPTATION; MOVEMENTS;
D O I
10.3390/s24185949
中图分类号
O65 [分析化学];
学科分类号
070302 ; 081704 ;
摘要
Wearable sensor-based human activity recognition (HAR) methods hold considerable promise for upper-level control in exoskeleton systems. However, such methods tend to overlook the critical role of data quality and still encounter challenges in cross-subject adaptation. To address this, we propose an active learning framework that integrates the relation network architecture with data sampling techniques. Initially, target data are used to fine tune two auxiliary classifiers of the pre-trained model, thereby establishing subject-specific classification boundaries. Subsequently, we assess the significance of the target data based on classifier discrepancy and partition the data into sample and template sets. Finally, the sampled data and a category clustering algorithm are employed to tune model parameters and optimize template data distribution, respectively. This approach facilitates the adaptation of the model to the target subject, enhancing both accuracy and generalizability. To evaluate the effectiveness of the proposed adaptation framework, we conducted evaluation experiments on a public dataset and a self-constructed electromyography (EMG) dataset. Experimental results demonstrate that our method outperforms the compared methods across all three statistical metrics. Furthermore, ablation experiments highlight the necessity of data screening. Our work underscores the practical feasibility of implementing user-independent HAR methods in exoskeleton control systems.
引用
收藏
页数:18
相关论文
共 41 条
  • [1] ConTraNet: A hybrid network for improving the classification of EEG and EMG signals with limited training data
    Ali, Omair
    Saif-ur-Rehman, Muhammad
    Glasmachers, Tobias
    Iossifidis, Ioannis
    Klaes, Christian
    [J]. COMPUTERS IN BIOLOGY AND MEDICINE, 2024, 168
  • [2] Deep Learning with Convolutional Neural Networks Applied to Electromyography Data: A Resource for the Classification of Movements for Prosthetic Hands
    Atzori, Manfredo
    Cognolato, Matteo
    Mueller, Henning
    [J]. FRONTIERS IN NEUROROBOTICS, 2016, 10
  • [3] Inter-Subject Domain Adaptation for CNN-Based Wrist Kinematics Estimation Using sEMG
    Bao, Tianzhe
    Zaidi, Syed Ali Raza
    Xie, Shengquan
    Yang, Pengfei
    Zhang, Zhi-Qiang
    [J]. IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING, 2021, 29 : 1068 - 1078
  • [4] Deep Cross-User Models Reduce the Training Burden in Myoelectric Control
    Campbell, Evan
    Phinyomark, Angkoon
    Scheme, Erik
    [J]. FRONTIERS IN NEUROSCIENCE, 2021, 15
  • [5] Walking Speed Estimation and Gait Classification Using Plantar Pressure and On-Device Deep Learning
    Cho, Hyuntae
    [J]. IEEE SENSORS JOURNAL, 2023, 23 (19) : 23336 - 23347
  • [6] MCDAL: Maximum Classifier Discrepancy for Active Learning
    Cho, Jae Won
    Kim, Dong-Jin
    Jung, Yunjae
    Kweon, In So
    [J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2023, 34 (11) : 8753 - 8763
  • [7] TSception: Capturing Temporal Dynamics and Spatial Asymmetry From EEG for Emotion Recognition
    Ding, Yi
    Robinson, Neethu
    Zhang, Su
    Zeng, Qiuhao
    Guan, Cuntai
    [J]. IEEE TRANSACTIONS ON AFFECTIVE COMPUTING, 2023, 14 (03) : 2238 - 2250
  • [8] A systematic literature review of evidence for the use of assistive exoskeletons in defence and security use cases
    Farris, Dominic J.
    Harris, David J.
    Rice, Hannah M.
    Campbell, James
    Weare, Alistair
    Risius, Debbie
    Armstrong, Nicola
    Rayson, Mark P.
    [J]. ERGONOMICS, 2023, 66 (01) : 61 - 87
  • [9] MCDCD: Multi-Source Unsupervised Domain Adaptation for Abnormal Human Gait Detection
    Guo, Yao
    Gu, Xiao
    Yang, Guang-Zhong
    [J]. IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS, 2021, 25 (10) : 4017 - 4028
  • [10] Benchmark Datasets for Bilateral Lower-Limb Neuromechanical Signals from Wearable Sensors during Unassisted Locomotion in Able-Bodied Individuals
    Hu, Blair
    Rouse, Elliott
    Hargrove, Levi
    [J]. FRONTIERS IN ROBOTICS AND AI, 2018, 5