Spiking neural network tactile classification method with faster and more accurate membrane potential representation

Abstract Robot perception is an important topic in artificial intelligence field, and tactile recognition in particular is indispensable for human–computer interaction. Efficiently classifying data obtained by touch sensors has long been an issue. In recent years, spiking neural networks (SNNs) have...

Full description

Saved in:
Bibliographic Details
Main Authors: Jing Yang, Zukun Yu, Xiaoyang Ji, Zhidong Su, Shaobo Li, Yang Cao
Format: Article
Language:English
Published: Wiley 2024-12-01
Series:IET Collaborative Intelligent Manufacturing
Subjects:
Online Access:https://doi.org/10.1049/cim2.70004
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846102072083087360
author Jing Yang
Zukun Yu
Xiaoyang Ji
Zhidong Su
Shaobo Li
Yang Cao
author_facet Jing Yang
Zukun Yu
Xiaoyang Ji
Zhidong Su
Shaobo Li
Yang Cao
author_sort Jing Yang
collection DOAJ
description Abstract Robot perception is an important topic in artificial intelligence field, and tactile recognition in particular is indispensable for human–computer interaction. Efficiently classifying data obtained by touch sensors has long been an issue. In recent years, spiking neural networks (SNNs) have been widely used in tactile data categorisation due to their temporal information processing benefits, low power consumption, and high biological dependability. However, traditional SNN classification methods often encounter under‐convergence when using membrane potential representation, decreasing their classification accuracy. Meanwhile, due to the time‐discrete nature of SNN models, classification requires a significant time overhead, which restricts their real‐time tactile sensing application potential. Considering these concerns, the authors propose a faster and more accurate SNN tactile classification approach using improved membrane potential representation. This method effectively overcomes model convergence problems by optimising the membrane potential expression and the relationship between the loss function and network parameters while significantly reducing the time overhead and enhancing the classification accuracy and robustness of the model. The experimental results show that the propose approach improves the classification accuracy by 4.16% and 2.71% and reduces the overall time by 8.00% and 8.14% on the EvTouch‐Containers dataset and EvTouch‐Objects dataset, respectively, when compared with existing models.
format Article
id doaj-art-88c28069fc4c4b56aca63d6fa40a8b7f
institution Kabale University
issn 2516-8398
language English
publishDate 2024-12-01
publisher Wiley
record_format Article
series IET Collaborative Intelligent Manufacturing
spelling doaj-art-88c28069fc4c4b56aca63d6fa40a8b7f2024-12-28T04:20:30ZengWileyIET Collaborative Intelligent Manufacturing2516-83982024-12-0164n/an/a10.1049/cim2.70004Spiking neural network tactile classification method with faster and more accurate membrane potential representationJing Yang0Zukun Yu1Xiaoyang Ji2Zhidong Su3Shaobo Li4Yang Cao5Key Laboratory of Advanced Manufacturing Technology of the Ministry of Education Guizhou University Guiyang ChinaKey Laboratory of Advanced Manufacturing Technology of the Ministry of Education Guizhou University Guiyang ChinaState Key Laboratory of Public Big Data Ministry of Education Guizhou University Guiyang ChinaSchool of Electrical and Computer Engineering Oklahoma State University Stillwater Oklahoma USAKey Laboratory of Advanced Manufacturing Technology of the Ministry of Education Guizhou University Guiyang ChinaSchool of Mechanical Engineering Guizhou University Guiyang ChinaAbstract Robot perception is an important topic in artificial intelligence field, and tactile recognition in particular is indispensable for human–computer interaction. Efficiently classifying data obtained by touch sensors has long been an issue. In recent years, spiking neural networks (SNNs) have been widely used in tactile data categorisation due to their temporal information processing benefits, low power consumption, and high biological dependability. However, traditional SNN classification methods often encounter under‐convergence when using membrane potential representation, decreasing their classification accuracy. Meanwhile, due to the time‐discrete nature of SNN models, classification requires a significant time overhead, which restricts their real‐time tactile sensing application potential. Considering these concerns, the authors propose a faster and more accurate SNN tactile classification approach using improved membrane potential representation. This method effectively overcomes model convergence problems by optimising the membrane potential expression and the relationship between the loss function and network parameters while significantly reducing the time overhead and enhancing the classification accuracy and robustness of the model. The experimental results show that the propose approach improves the classification accuracy by 4.16% and 2.71% and reduces the overall time by 8.00% and 8.14% on the EvTouch‐Containers dataset and EvTouch‐Objects dataset, respectively, when compared with existing models.https://doi.org/10.1049/cim2.70004data analysishuman‐robot interactionneural nets
spellingShingle Jing Yang
Zukun Yu
Xiaoyang Ji
Zhidong Su
Shaobo Li
Yang Cao
Spiking neural network tactile classification method with faster and more accurate membrane potential representation
IET Collaborative Intelligent Manufacturing
data analysis
human‐robot interaction
neural nets
title Spiking neural network tactile classification method with faster and more accurate membrane potential representation
title_full Spiking neural network tactile classification method with faster and more accurate membrane potential representation
title_fullStr Spiking neural network tactile classification method with faster and more accurate membrane potential representation
title_full_unstemmed Spiking neural network tactile classification method with faster and more accurate membrane potential representation
title_short Spiking neural network tactile classification method with faster and more accurate membrane potential representation
title_sort spiking neural network tactile classification method with faster and more accurate membrane potential representation
topic data analysis
human‐robot interaction
neural nets
url https://doi.org/10.1049/cim2.70004
work_keys_str_mv AT jingyang spikingneuralnetworktactileclassificationmethodwithfasterandmoreaccuratemembranepotentialrepresentation
AT zukunyu spikingneuralnetworktactileclassificationmethodwithfasterandmoreaccuratemembranepotentialrepresentation
AT xiaoyangji spikingneuralnetworktactileclassificationmethodwithfasterandmoreaccuratemembranepotentialrepresentation
AT zhidongsu spikingneuralnetworktactileclassificationmethodwithfasterandmoreaccuratemembranepotentialrepresentation
AT shaoboli spikingneuralnetworktactileclassificationmethodwithfasterandmoreaccuratemembranepotentialrepresentation
AT yangcao spikingneuralnetworktactileclassificationmethodwithfasterandmoreaccuratemembranepotentialrepresentation