A Rapid Spiking Neural Network Approach With an Application on Hand Gesture Recognition

doi:10.1109/TCDS.2019.2918228

CORC > 自动化研究所 > 中国科学院自动化研究所 > 复杂系统管理与控制国家重点实验室 > 先进机器人控制团队

	A Rapid Spiking Neural Network Approach With an Application on Hand Gesture Recognition
	Cheng, Long 2,3; Liu, Yang 2,3; Hou, Zeng-Guang 2,3; Tan, Min 2,3; Du, Dajun 1; Fei, Minrui 1
刊名	IEEE TRANSACTIONS ON COGNITIVE AND DEVELOPMENTAL SYSTEMS
	2021-03-01
卷号	13 期号:1 页码:151-161
关键词	Forward propagation hand gesture recognition spiking neural networks (SNNs) surface electromyography
ISSN号	2379-8920
DOI	10.1109/TCDS.2019.2918228
通讯作者	Cheng, Long(long.cheng@ia.ac.cn)
英文摘要	The spiking neural network (SNN) is considered to be the third generation of neural networks featured by its low power consumption and high computing capability, which has great application potential in robotics. However, the present SNN has two limitations: 1) the neuron's spike firing time is calculated based on the iterative approach, which dramatically slows down the calculation rate of the SNN and 2) the existing learning algorithm is more suitable for the single-layer structure, which can hardly train the network with "deep structure." To this end, this paper proposes a novel spike firing time search algorithm that can narrow the search interval. In addition, a pretrained subnet SNN is designed, which makes the SNN have more hidden layers. This setting of the SNN can effectively improve its performance in pattern recognition tasks. Furthermore, by using the surface electromyography signal (sEMG), the proposed SNN is used to recognize the hand gestures. The experimental results show that: 1) the spike firing time search algorithm can significantly increase the forward propagation rate of the SNN and 2) the proposed SNN can reach a satisfactory recognition accuracy ratio 97.4%, which is 0.9% higher than that of the fully connected SNN.
资助项目	National Natural Science Foundation of China[61873268] ; National Natural Science Foundation of China[61633016] ; Beijing Municipal Natural Science Foundation[L182060] ; Major Science and Technology Fund of Beijing[Z181100003118006] ; Research Fund for Young Top-Notch Talent of National Ten Thousand Talent Program
WOS研究方向	Computer Science ; Robotics ; Neurosciences & Neurology
语种	英语
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号	WOS:000628911300014
资助机构	National Natural Science Foundation of China ; Beijing Municipal Natural Science Foundation ; Major Science and Technology Fund of Beijing ; Research Fund for Young Top-Notch Talent of National Ten Thousand Talent Program
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/44057]
专题	自动化研究所_复杂系统管理与控制国家重点实验室_先进机器人控制团队
通讯作者	Cheng, Long
作者单位	1.Shanghai Univ, Sch Mechatron Engn & Automat, Shanghai 200072, Peoples R China 2.Chinese Acad Sci, Inst Automat, State Key Lab Control & Management Complex Syst, Beijing 100190, Peoples R China 3.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China
推荐引用方式 GB/T 7714	Cheng, Long,Liu, Yang,Hou, Zeng-Guang,et al. A Rapid Spiking Neural Network Approach With an Application on Hand Gesture Recognition[J]. IEEE TRANSACTIONS ON COGNITIVE AND DEVELOPMENTAL SYSTEMS,2021,13(1):151-161.
APA	Cheng, Long,Liu, Yang,Hou, Zeng-Guang,Tan, Min,Du, Dajun,&Fei, Minrui.(2021).A Rapid Spiking Neural Network Approach With an Application on Hand Gesture Recognition.IEEE TRANSACTIONS ON COGNITIVE AND DEVELOPMENTAL SYSTEMS,13(1),151-161.
MLA	Cheng, Long,et al."A Rapid Spiking Neural Network Approach With an Application on Hand Gesture Recognition".IEEE TRANSACTIONS ON COGNITIVE AND DEVELOPMENTAL SYSTEMS 13.1(2021):151-161.