Cargando…
A Bio-Inspired Spiking Neural Network with Few-Shot Class-Incremental Learning for Gas Recognition
The sensitivity and selectivity profiles of gas sensors are always changed by sensor drifting, sensor aging, and the surroundings (e.g., temperature and humidity changes), which lead to a serious decline in gas recognition accuracy or even invalidation. To address this issue, the practical solution...
Autores principales: | , , , , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10006916/ https://www.ncbi.nlm.nih.gov/pubmed/36904636 http://dx.doi.org/10.3390/s23052433 |
_version_ | 1784905389340360704 |
---|---|
author | Huo, Dexuan Zhang, Jilin Dai, Xinyu Zhang, Pingping Zhang, Shumin Yang, Xiao Wang, Jiachuang Liu, Mengwei Sun, Xuhui Chen, Hong |
author_facet | Huo, Dexuan Zhang, Jilin Dai, Xinyu Zhang, Pingping Zhang, Shumin Yang, Xiao Wang, Jiachuang Liu, Mengwei Sun, Xuhui Chen, Hong |
author_sort | Huo, Dexuan |
collection | PubMed |
description | The sensitivity and selectivity profiles of gas sensors are always changed by sensor drifting, sensor aging, and the surroundings (e.g., temperature and humidity changes), which lead to a serious decline in gas recognition accuracy or even invalidation. To address this issue, the practical solution is to retrain the network to maintain performance, leveraging its rapid, incremental online learning capacity. In this paper, we develop a bio-inspired spiking neural network (SNN) to recognize nine types of flammable and toxic gases, which supports few-shot class-incremental learning, and can be retrained quickly with a new gas at a low accuracy cost. Compared with gas recognition approaches such as support vector machine (SVM), k-nearest neighbor (KNN), principal component analysis (PCA) +SVM, PCA+KNN, and artificial neural network (ANN), our network achieves the highest accuracy of 98.75% in five-fold cross-validation for identifying nine types of gases, each with five different concentrations. In particular, the proposed network has a 5.09% higher accuracy than that of other gas recognition algorithms, which validates its robustness and effectiveness for real-life fire scenarios. |
format | Online Article Text |
id | pubmed-10006916 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2023 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-100069162023-03-12 A Bio-Inspired Spiking Neural Network with Few-Shot Class-Incremental Learning for Gas Recognition Huo, Dexuan Zhang, Jilin Dai, Xinyu Zhang, Pingping Zhang, Shumin Yang, Xiao Wang, Jiachuang Liu, Mengwei Sun, Xuhui Chen, Hong Sensors (Basel) Article The sensitivity and selectivity profiles of gas sensors are always changed by sensor drifting, sensor aging, and the surroundings (e.g., temperature and humidity changes), which lead to a serious decline in gas recognition accuracy or even invalidation. To address this issue, the practical solution is to retrain the network to maintain performance, leveraging its rapid, incremental online learning capacity. In this paper, we develop a bio-inspired spiking neural network (SNN) to recognize nine types of flammable and toxic gases, which supports few-shot class-incremental learning, and can be retrained quickly with a new gas at a low accuracy cost. Compared with gas recognition approaches such as support vector machine (SVM), k-nearest neighbor (KNN), principal component analysis (PCA) +SVM, PCA+KNN, and artificial neural network (ANN), our network achieves the highest accuracy of 98.75% in five-fold cross-validation for identifying nine types of gases, each with five different concentrations. In particular, the proposed network has a 5.09% higher accuracy than that of other gas recognition algorithms, which validates its robustness and effectiveness for real-life fire scenarios. MDPI 2023-02-22 /pmc/articles/PMC10006916/ /pubmed/36904636 http://dx.doi.org/10.3390/s23052433 Text en © 2023 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). |
spellingShingle | Article Huo, Dexuan Zhang, Jilin Dai, Xinyu Zhang, Pingping Zhang, Shumin Yang, Xiao Wang, Jiachuang Liu, Mengwei Sun, Xuhui Chen, Hong A Bio-Inspired Spiking Neural Network with Few-Shot Class-Incremental Learning for Gas Recognition |
title | A Bio-Inspired Spiking Neural Network with Few-Shot Class-Incremental Learning for Gas Recognition |
title_full | A Bio-Inspired Spiking Neural Network with Few-Shot Class-Incremental Learning for Gas Recognition |
title_fullStr | A Bio-Inspired Spiking Neural Network with Few-Shot Class-Incremental Learning for Gas Recognition |
title_full_unstemmed | A Bio-Inspired Spiking Neural Network with Few-Shot Class-Incremental Learning for Gas Recognition |
title_short | A Bio-Inspired Spiking Neural Network with Few-Shot Class-Incremental Learning for Gas Recognition |
title_sort | bio-inspired spiking neural network with few-shot class-incremental learning for gas recognition |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10006916/ https://www.ncbi.nlm.nih.gov/pubmed/36904636 http://dx.doi.org/10.3390/s23052433 |
work_keys_str_mv | AT huodexuan abioinspiredspikingneuralnetworkwithfewshotclassincrementallearningforgasrecognition AT zhangjilin abioinspiredspikingneuralnetworkwithfewshotclassincrementallearningforgasrecognition AT daixinyu abioinspiredspikingneuralnetworkwithfewshotclassincrementallearningforgasrecognition AT zhangpingping abioinspiredspikingneuralnetworkwithfewshotclassincrementallearningforgasrecognition AT zhangshumin abioinspiredspikingneuralnetworkwithfewshotclassincrementallearningforgasrecognition AT yangxiao abioinspiredspikingneuralnetworkwithfewshotclassincrementallearningforgasrecognition AT wangjiachuang abioinspiredspikingneuralnetworkwithfewshotclassincrementallearningforgasrecognition AT liumengwei abioinspiredspikingneuralnetworkwithfewshotclassincrementallearningforgasrecognition AT sunxuhui abioinspiredspikingneuralnetworkwithfewshotclassincrementallearningforgasrecognition AT chenhong abioinspiredspikingneuralnetworkwithfewshotclassincrementallearningforgasrecognition AT huodexuan bioinspiredspikingneuralnetworkwithfewshotclassincrementallearningforgasrecognition AT zhangjilin bioinspiredspikingneuralnetworkwithfewshotclassincrementallearningforgasrecognition AT daixinyu bioinspiredspikingneuralnetworkwithfewshotclassincrementallearningforgasrecognition AT zhangpingping bioinspiredspikingneuralnetworkwithfewshotclassincrementallearningforgasrecognition AT zhangshumin bioinspiredspikingneuralnetworkwithfewshotclassincrementallearningforgasrecognition AT yangxiao bioinspiredspikingneuralnetworkwithfewshotclassincrementallearningforgasrecognition AT wangjiachuang bioinspiredspikingneuralnetworkwithfewshotclassincrementallearningforgasrecognition AT liumengwei bioinspiredspikingneuralnetworkwithfewshotclassincrementallearningforgasrecognition AT sunxuhui bioinspiredspikingneuralnetworkwithfewshotclassincrementallearningforgasrecognition AT chenhong bioinspiredspikingneuralnetworkwithfewshotclassincrementallearningforgasrecognition |