Multi-Classifier Tree With Transient Features for Drift Compensation in Electronic Nose

<p dir="ltr">Long term sensors drift is a challenging problem to solve for instruments like an Electronic Nose System (ENS). These electronic instruments rely on Machine Learning (ML) algorithms for recognizing the sensed odors. The effect of long-term drift influences the performanc...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Atiq Ur Rehman (8843024) (author)
مؤلفون آخرون: Samir Brahim Belhaouari (9427347) (author), Muhammad Ijaz (677144) (author), Amine Bermak (1895947) (author), Mounir Hamdi (14150652) (author)
منشور في: 2020
الموضوعات:
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
_version_ 1864513561245515776
author Atiq Ur Rehman (8843024)
author2 Samir Brahim Belhaouari (9427347)
Muhammad Ijaz (677144)
Amine Bermak (1895947)
Mounir Hamdi (14150652)
author2_role author
author
author
author
author_facet Atiq Ur Rehman (8843024)
Samir Brahim Belhaouari (9427347)
Muhammad Ijaz (677144)
Amine Bermak (1895947)
Mounir Hamdi (14150652)
author_role author
dc.creator.none.fl_str_mv Atiq Ur Rehman (8843024)
Samir Brahim Belhaouari (9427347)
Muhammad Ijaz (677144)
Amine Bermak (1895947)
Mounir Hamdi (14150652)
dc.date.none.fl_str_mv 2020-12-02T00:00:00Z
dc.identifier.none.fl_str_mv 10.1109/jsen.2020.3041949
dc.relation.none.fl_str_mv https://figshare.com/articles/journal_contribution/Multi-Classifier_Tree_With_Transient_Features_for_Drift_Compensation_in_Electronic_Nose/24006795
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Engineering
Electronics, sensors and digital hardware
Information and computing sciences
Machine learning
Sensors
Transient analysis
Sensor systems
Sensor phenomena and characterization
Gas detectors
Steady-state
Time factors
Artificial olfaction
Electronic nose
Heuristic optimization
Industrial gases
Sensors drift
dc.title.none.fl_str_mv Multi-Classifier Tree With Transient Features for Drift Compensation in Electronic Nose
dc.type.none.fl_str_mv Text
Journal contribution
info:eu-repo/semantics/publishedVersion
text
contribution to journal
description <p dir="ltr">Long term sensors drift is a challenging problem to solve for instruments like an Electronic Nose System (ENS). These electronic instruments rely on Machine Learning (ML) algorithms for recognizing the sensed odors. The effect of long-term drift influences the performance of ML algorithms and the models those are trained on drift free data fail to perform on the drifted data. Moreover, the response of an electronic nose system depends on the variable response of the sensors and a delay is expected in reaching a steady state by the sensors. In this paper, these two problems of `sensors long term drift' and `delayed response' are solved simultaneously to propose a robust and fast electronic nose system, with following merits: (i) only initial transient state features are used in the proposed system without waiting for the sensors to reach a steady state, (ii) a modified boxplot approach is used to handle noisy/drifted data points as a preprocessing step before the classification setup, (iii) a heuristic tree classification approach with optimized transient features is proposed, (iv) the proposed approach only relies on adapted ML methods contrary to the traditional approaches like system recalibration or sensors replacement for handling sensors drift, and (v) the proposed ML model does not require any target domain data and uses only the source domain data for learning the classifier, opposed to the other ML solutions available in the existing literature. The proposed method is tested using a large scale gas sensors drift benchmark dataset available freely on UCI Machine Learning repository and is found better than the existing state-of-the art approaches with an overall accuracy of 87.34%.</p><h2>Other Information</h2><p dir="ltr">Published in: IEEE Sensors Journal<br>License: <a href="https://creativecommons.org/licenses/by/4.0/legalcode" target="_blank">https://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1109/jsen.2020.3041949" target="_blank">https://dx.doi.org/10.1109/jsen.2020.3041949</a></p>
eu_rights_str_mv openAccess
id Manara2_1967bbfbd4238e2e4af4cc0cf9142631
identifier_str_mv 10.1109/jsen.2020.3041949
network_acronym_str Manara2
network_name_str Manara2
oai_identifier_str oai:figshare.com:article/24006795
publishDate 2020
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling Multi-Classifier Tree With Transient Features for Drift Compensation in Electronic NoseAtiq Ur Rehman (8843024)Samir Brahim Belhaouari (9427347)Muhammad Ijaz (677144)Amine Bermak (1895947)Mounir Hamdi (14150652)EngineeringElectronics, sensors and digital hardwareInformation and computing sciencesMachine learningSensorsTransient analysisSensor systemsSensor phenomena and characterizationGas detectorsSteady-stateTime factorsArtificial olfactionElectronic noseHeuristic optimizationIndustrial gasesSensors drift<p dir="ltr">Long term sensors drift is a challenging problem to solve for instruments like an Electronic Nose System (ENS). These electronic instruments rely on Machine Learning (ML) algorithms for recognizing the sensed odors. The effect of long-term drift influences the performance of ML algorithms and the models those are trained on drift free data fail to perform on the drifted data. Moreover, the response of an electronic nose system depends on the variable response of the sensors and a delay is expected in reaching a steady state by the sensors. In this paper, these two problems of `sensors long term drift' and `delayed response' are solved simultaneously to propose a robust and fast electronic nose system, with following merits: (i) only initial transient state features are used in the proposed system without waiting for the sensors to reach a steady state, (ii) a modified boxplot approach is used to handle noisy/drifted data points as a preprocessing step before the classification setup, (iii) a heuristic tree classification approach with optimized transient features is proposed, (iv) the proposed approach only relies on adapted ML methods contrary to the traditional approaches like system recalibration or sensors replacement for handling sensors drift, and (v) the proposed ML model does not require any target domain data and uses only the source domain data for learning the classifier, opposed to the other ML solutions available in the existing literature. The proposed method is tested using a large scale gas sensors drift benchmark dataset available freely on UCI Machine Learning repository and is found better than the existing state-of-the art approaches with an overall accuracy of 87.34%.</p><h2>Other Information</h2><p dir="ltr">Published in: IEEE Sensors Journal<br>License: <a href="https://creativecommons.org/licenses/by/4.0/legalcode" target="_blank">https://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1109/jsen.2020.3041949" target="_blank">https://dx.doi.org/10.1109/jsen.2020.3041949</a></p>2020-12-02T00:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.1109/jsen.2020.3041949https://figshare.com/articles/journal_contribution/Multi-Classifier_Tree_With_Transient_Features_for_Drift_Compensation_in_Electronic_Nose/24006795CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/240067952020-12-02T00:00:00Z
spellingShingle Multi-Classifier Tree With Transient Features for Drift Compensation in Electronic Nose
Atiq Ur Rehman (8843024)
Engineering
Electronics, sensors and digital hardware
Information and computing sciences
Machine learning
Sensors
Transient analysis
Sensor systems
Sensor phenomena and characterization
Gas detectors
Steady-state
Time factors
Artificial olfaction
Electronic nose
Heuristic optimization
Industrial gases
Sensors drift
status_str publishedVersion
title Multi-Classifier Tree With Transient Features for Drift Compensation in Electronic Nose
title_full Multi-Classifier Tree With Transient Features for Drift Compensation in Electronic Nose
title_fullStr Multi-Classifier Tree With Transient Features for Drift Compensation in Electronic Nose
title_full_unstemmed Multi-Classifier Tree With Transient Features for Drift Compensation in Electronic Nose
title_short Multi-Classifier Tree With Transient Features for Drift Compensation in Electronic Nose
title_sort Multi-Classifier Tree With Transient Features for Drift Compensation in Electronic Nose
topic Engineering
Electronics, sensors and digital hardware
Information and computing sciences
Machine learning
Sensors
Transient analysis
Sensor systems
Sensor phenomena and characterization
Gas detectors
Steady-state
Time factors
Artificial olfaction
Electronic nose
Heuristic optimization
Industrial gases
Sensors drift