Drift Compensation on Massive Online Electronic-Nose Responses
Gas sensor drift is an important issue of electronic nose (E-nose) systems. This study follows this concern under the condition that requires an instant drift compensation with massive online E-nose responses. Recently, an active learning paradigm has been introduced to such condition. However, it d...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-04-01
|
Series: | Chemosensors |
Subjects: | |
Online Access: | https://www.mdpi.com/2227-9040/9/4/78 |
_version_ | 1797538072387125248 |
---|---|
author | Jianhua Cao Tao Liu Jianjun Chen Tao Yang Xiuxiu Zhu Hongjin Wang |
author_facet | Jianhua Cao Tao Liu Jianjun Chen Tao Yang Xiuxiu Zhu Hongjin Wang |
author_sort | Jianhua Cao |
collection | DOAJ |
description | Gas sensor drift is an important issue of electronic nose (E-nose) systems. This study follows this concern under the condition that requires an instant drift compensation with massive online E-nose responses. Recently, an active learning paradigm has been introduced to such condition. However, it does not consider the “noisy label” problem caused by the unreliability of its labeling process in real applications. Thus, we have proposed a class-label appraisal methodology and associated active learning framework to assess and correct the noisy labels. To evaluate the performance of the proposed methodologies, we used the datasets from two E-nose systems. The experimental results show that the proposed methodology helps the E-noses achieve higher accuracy with lower computation than the reference methods do. Finally, we can conclude that the proposed class-label appraisal mechanism is an effective means of enhancing the robustness of active learning-based E-nose drift compensation. |
first_indexed | 2024-03-10T12:25:16Z |
format | Article |
id | doaj.art-979b29c8a6014bc79fb7190b18b3e22a |
institution | Directory Open Access Journal |
issn | 2227-9040 |
language | English |
last_indexed | 2024-03-10T12:25:16Z |
publishDate | 2021-04-01 |
publisher | MDPI AG |
record_format | Article |
series | Chemosensors |
spelling | doaj.art-979b29c8a6014bc79fb7190b18b3e22a2023-11-21T15:06:37ZengMDPI AGChemosensors2227-90402021-04-01947810.3390/chemosensors9040078Drift Compensation on Massive Online Electronic-Nose ResponsesJianhua Cao0Tao Liu1Jianjun Chen2Tao Yang3Xiuxiu Zhu4Hongjin Wang5School of Microelectronics and Communication Engineering, Chongqing University, Chongqing 400044, ChinaSchool of Microelectronics and Communication Engineering, Chongqing University, Chongqing 400044, ChinaSchool of Microelectronics and Communication Engineering, Chongqing University, Chongqing 400044, ChinaSchool of Microelectronics and Communication Engineering, Chongqing University, Chongqing 400044, ChinaSchool of Microelectronics and Communication Engineering, Chongqing University, Chongqing 400044, ChinaSchool of Microelectronics and Communication Engineering, Chongqing University, Chongqing 400044, ChinaGas sensor drift is an important issue of electronic nose (E-nose) systems. This study follows this concern under the condition that requires an instant drift compensation with massive online E-nose responses. Recently, an active learning paradigm has been introduced to such condition. However, it does not consider the “noisy label” problem caused by the unreliability of its labeling process in real applications. Thus, we have proposed a class-label appraisal methodology and associated active learning framework to assess and correct the noisy labels. To evaluate the performance of the proposed methodologies, we used the datasets from two E-nose systems. The experimental results show that the proposed methodology helps the E-noses achieve higher accuracy with lower computation than the reference methods do. Finally, we can conclude that the proposed class-label appraisal mechanism is an effective means of enhancing the robustness of active learning-based E-nose drift compensation.https://www.mdpi.com/2227-9040/9/4/78electronic nosedrift compensationactive learningnoisy label problemmixed Gaussian modelexpected entropy |
spellingShingle | Jianhua Cao Tao Liu Jianjun Chen Tao Yang Xiuxiu Zhu Hongjin Wang Drift Compensation on Massive Online Electronic-Nose Responses Chemosensors electronic nose drift compensation active learning noisy label problem mixed Gaussian model expected entropy |
title | Drift Compensation on Massive Online Electronic-Nose Responses |
title_full | Drift Compensation on Massive Online Electronic-Nose Responses |
title_fullStr | Drift Compensation on Massive Online Electronic-Nose Responses |
title_full_unstemmed | Drift Compensation on Massive Online Electronic-Nose Responses |
title_short | Drift Compensation on Massive Online Electronic-Nose Responses |
title_sort | drift compensation on massive online electronic nose responses |
topic | electronic nose drift compensation active learning noisy label problem mixed Gaussian model expected entropy |
url | https://www.mdpi.com/2227-9040/9/4/78 |
work_keys_str_mv | AT jianhuacao driftcompensationonmassiveonlineelectronicnoseresponses AT taoliu driftcompensationonmassiveonlineelectronicnoseresponses AT jianjunchen driftcompensationonmassiveonlineelectronicnoseresponses AT taoyang driftcompensationonmassiveonlineelectronicnoseresponses AT xiuxiuzhu driftcompensationonmassiveonlineelectronicnoseresponses AT hongjinwang driftcompensationonmassiveonlineelectronicnoseresponses |