A Novel PSO-Based Optimized Lightweight Convolution Neural Network for Movements Recognizing from Multichannel Surface Electromyogram
A Novel PSO-Based Optimized Lightweight Convolution Neural Network for Movements Recognizing from Multichannel Surface Electromyogram
复制标题
一种基于 PSO 的新型优化轻量级卷积神经网络，用于多通道表面肌电图运动识别
DOI：
10.1155/2020/6642463
复制
发表时间：
2020-12
期刊：
影响因子：
2.3
通讯作者：
Zhang Xiafeng
中科院分区：
文献类型：
--
作者：
Kan Xiu;Yang Dan;Cao Le;Shu Huisheng;Li Yuanyuan;Yao Wei;Zhang Xiafeng
作为人机交互的媒介，正确、快速地解读表面肌电（sEMG）的运动信息至关重要。深度学习可以通过端到端训练来识别各种表面肌电动作。然而，现有的深度学习方法大多结构复杂、参数众多，导致网络优化问题难以实现。本文设计了一种新型的基于 PSO 的优化轻量级卷积神经网络（PLCNN），以提高精度并优化模型，应用于 sEMG 信号运动识别。以降低深度神经网络结构复杂度为目的，设计的卷积神经网络模型主要由三个卷积层和两个全连接层组成。同时，利用粒子群优化（PSO）来优化超参数，提高所设计的表面肌电模式识别模型的自适应能力。为了进一步表明潜在的应用，根据 Ninapro 标准数据集的身体运动渐进过程设计了三个实验。实验结果表明，所提出的 PLCNN 识别方法优于其他四种流行的分类方法。
As the medium of human-computer interaction, it is crucial to correctly and quickly interpret the motion information of surface electromyography (sEMG). Deep learning can recognize a variety of sEMG actions by end-to-end training. However, most of the existing deep learning approaches have complex structures and numerous parameters, which make the network optimization problem difficult to realize. In this paper, a novel PSO-based optimized lightweight convolution neural network (PLCNN) is designed to improve the accuracy and optimize the model with applications in sEMG signal movement recognition. With the purpose of reducing the structural complexity of the deep neural network, the designed convolution neural network model is mainly composed of three convolution layers and two full connection layers. Meanwhile, the particle swarm optimization (PSO) is used to optimize hyperparameters and improve the autoadaptive ability of the designed sEMG pattern recognition model. To further indicate the potential application, three experiments are designed according to the progressive process of body movements with respect to the Ninapro standard data set. Experiment results demonstrate that the proposed PLCNN recognition method is superior to the four other popular classification methods.
登录
查看更多内容
DOI：
10.1109/iww-bci.2016.7457459
发表时间：
2016-02
期刊：
2016 4th International Winter Conference on Brain-Computer Interface (BCI)
影响因子：
--
作者：
Ki-Hee Park;Seong-Whan Lee
通讯作者：
Ki-Hee Park;Seong-Whan Lee
DOI：
10.1017/cbo9780511801389.013
发表时间：
2000-03
期刊：
--
影响因子：
--
作者：
N. Cristianini;J. Shawe-Taylor
通讯作者：
N. Cristianini;J. Shawe-Taylor
DOI：
10.1007/978-1-4471-0285-4
发表时间：
2012-10
期刊：
--
影响因子：
--
作者：
Shigeo Abe DrEng
通讯作者：
Shigeo Abe DrEng
DOI：
10.29007/bld3
发表时间：
2018-08
期刊：
EasyChair Preprints
影响因子：
--
作者：
Wenjin Tao;Ze-Hao Lai;M. Leu;Zhaozheng Yin
通讯作者：
Wenjin Tao;Ze-Hao Lai;M. Leu;Zhaozheng Yin
影响因子：
14.3
作者：
Liu, Weibo;Wang, Zidong;Bell, David
通讯作者：
Bell, David