Two-dimensional discrete feature based spatial attention CapsNet For sEMG signal recognition

被引:21
作者
Chen, Guoqi [1 ]
Wang, Wanliang [1 ]
Wang, Zheng [1 ]
Liu, Honghai [2 ]
Zang, Zelin [1 ]
Li, Weikun [1 ]
机构
[1] Zhejiang Univ Technol, Coll Comp Sci & Technol, Hangzhou, Zhejiang, Peoples R China
[2] Univ Portsmouth, Sch Comp, Intelligent Syst & Biomed Robot Grp, Portsmouth PO1 3HE, Hants, England
基金
中国国家自然科学基金;
关键词
Two-Dimensional discrete feature; Spatial attention; Capsule network; sEMG signal; VISUAL-ATTENTION; SELECTION; REPRESENTATION; NETWORKS;
D O I
10.1007/s10489-020-01725-0
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Deep learning frameworks(such as deep convolutional networks) require data to have a regular shape. However, discrete features extracted from heterogeneous data cannot be collected in a regular shape to convolute. In this article, a Two-Dimensional Discrete Feature Based Spatial Attention CapsNet(TDACAPS) is proposed to convert one-dimensional discrete features into two-dimensional structured data through Cartesian Product for surface electromyogram(sEMG) signal recognition. sEMG signal varies from person to person is the main signal source of prosthetic control. Our model transforms multi-angle discrete features into structured data to find the inherent law of sEMG signal. Due to uneven information distribution of structured data, this model combines capsule network with attention mechanism to place emphasis on abundant information regions and reduce ancillary information loss. Extensive experiments show our model yields an improvement for sEMG signal recognition of almost 3% than capsule network and other neural networks under different conditions. Our attention mechanism that employs overlapping pooling to search feature map weight is preferable to the squeeze-and-excitation module, convolutional block attention module and others. Moreover, we validate that our model has great expansibility on Wine Quality Dataset and Breast Cancer Wisconsin.
引用
收藏
页码:3503 / 3520
页数:18
相关论文
共 64 条
[1]   Salp swarm algorithm: a comprehensive survey [J].
Abualigah, Laith ;
Shehab, Mohammad ;
Alshinwan, Mohammad ;
Alabool, Hamzeh .
NEURAL COMPUTING & APPLICATIONS, 2020, 32 (15) :11195-11215
[2]   Unsupervised text feature selection technique based on hybrid particle swarm optimization algorithm with genetic operators for the text clustering [J].
Abualigah, Laith Mohammad ;
Khader, Ahamad Tajudin .
JOURNAL OF SUPERCOMPUTING, 2017, 73 (11) :4773-4795
[3]  
Abualigah LMQ., 2019, FEATURE SELECTION EN, DOI [DOI 10.1007/978-3-030-10674-4, 10.1007/978-3-030-10674-4]
[4]   Breast cancer diagnosis using GA feature selection and Rotation Forest [J].
Alickovic, Emina ;
Subasi, Abdulhamit .
NEURAL COMPUTING & APPLICATIONS, 2017, 28 (04) :753-763
[5]  
Allard UC, 2016, 2016 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS 2016), P2464, DOI 10.1109/IROS.2016.7759384
[6]  
[Anonymous], 2011, Stages for Developing Control Systems Using EMG and EEG Signals: A Survey
[7]  
Appalasamy P., 2012, Journal of Applied Sciences, V12, P598, DOI 10.3923/jas.2012.598.601
[8]   Deep Learning with Convolutional Neural Networks Applied to Electromyography Data: A Resource for the Classification of Movements for Prosthetic Hands [J].
Atzori, Manfredo ;
Cognolato, Matteo ;
Mueller, Henning .
FRONTIERS IN NEUROROBOTICS, 2016, 10
[9]   Breast cancer diagnosis using Genetically Optimized Neural Network model [J].
Bhardwaj, Arpit ;
Tiwari, Aruna .
EXPERT SYSTEMS WITH APPLICATIONS, 2015, 42 (10) :4611-4620
[10]  
BONYADI MR, 2018, IEEE T MEURAL METW L, V30, P511