Melola Discovery

← Melola Discovery

Open access Journal SINTA 1

SHAP-Based Framework for Temporal Detection of Sensor Drift in Gas Sensor Arrays

Journal of Robotics and Control (JRC) · Vol. 6 No. 5 (2025) · pp. 2592–2601

DOI
10.18196/jrc.v6i5.28048
ISSN
2715-5072, 2715-5056
Published
2025-11-03
Publisher
Universitas Muhammadiyah Yogyakarta
Language
eng
License
creativecommons.org/licenses/by-sa/4.0

Abstract

Sensor drift is a fundamental problem that undermines the long-term reliability of machine-learning models, as gradual changes in sensor response can silently degrade predictive performance. This challenge is particularly relevant in gas sensor arrays, where environmental variability and sensor aging strongly affect data quality. Ensuring effective monitoring of such drift is essential for industrial safety, environmental monitoring, and other applications that depend on stable sensing systems. To address this issue, we develop a SHAP (SHapley Additive Explanations)–based framework combined with an XGBoost classifier to detect drift at the feature level. The model is trained on structured sensor data, and SHAP values are computed batch-wise to capture temporal changes in feature relevance. Preprocessing enforces balanced class distributions and consistent concentration ranges, reducing potential confounding effects. Results from the Gas Sensor Array Drift dataset demonstrate that several sensor channels exhibit clear temporal variability in SHAP importance. Notably, these changes were observed even when accuracy and F1-score remained stable, highlighting that SHAP provides a complementary early-warning signal of drift. Case studies further confirm that the framework can capture both gradual and abrupt drift patterns. The research contribution of this study lies in providing an interpretable and time-resolved perspective on drift detection, enabling the localization of drift signals to specific sensors and features, independent of drift type or feature domain. This approach advances the state of the art by bridging explainable AI and drift monitoring. In conclusion, the framework supports practical deployment of adaptive sensing systems by making drift behaviour visible before conventional metrics degrade. Future work will focus on real-time scalability, broader datasets, and automated drift correction through recalibration or retraining.

Keywords

Collaboration network of the authors

40 authors · 113 co-authorship links · 73 across different organisations · showing the 40 most connected

Hover or tap a name to highlight its co-authors. Double-click to open the author's page.

  • Sebelas Maret University
  • Universitas Ahmad Dahlan
  • Batman University
  • Universiti Teknikal Malaysia Melaka
  • Islamic Azad University, Tehran
  • University of Hassan II Casablanca
  • Gedik University
  • Other organisations
  • Affiliation unknown
  • Different organisations
  • Same organisation
  • Affiliation unknown
  • Thicker line = more joint articles · bigger circle = more articles
Show as table
Co-authorOrganisationJoint articles
Mostafa JabariSahand University of Technology6
Iswanto SuwarnoMuhammadiyah University of Yogyakarta4
Hari MaghfirohSebelas Maret University3
Magdi S. MahmoudKing Fahd University of Petroleum and Minerals3
Mahmoud A. MossaMinia University3
Abdullah ÇakanKonya Technical University2
Marco Antonio Márquez-VeraUniversidad Politécnica de Pachuca2
N. S. AbuUniversiti Teknikal Malaysia Melaka2
Wan Mohd BukhariUniversiti Teknikal Malaysia Melaka2
M. H. AdliAdvanced Semiconductor Engineering (Taiwan)2
Furizal FurizalUniversitas Ahmad Dahlan2
Muhammad NizamSebelas Maret University1
Joko Slamet SaputroSebelas Maret University1
Berlian Shanaza AndianySebelas Maret University1
Chico HermanuSebelas Maret University1
Miftahul AnwarSebelas Maret University1
Sunardi SunardiUniversitas Ahmad Dahlan1
Rio Ikhsan AlfianUniversitas Ahmad Dahlan1
Naufal Rahmat SetiawanAffiliation unknown1
Ahmed Jaber AbougarairUniversity of Tripoli1
Edwin Albert UmohAffiliation unknown1
Safinta Nurindra RahmadhiaUniversitas Ahmad Dahlan1
Samir LadaciEcole Nationale Polytechnique de Constantine1
Jonattan Niño ParadaUniversidad de los Llanos1
Reza AlayiIslamic Azad University, Tehran1
Yaser EbazadehIslamic Azad University, Tehran1
Ferydon GharadaghiAffiliation unknown1
Farnaz JahanbinIslamic Azad University, Mashhad1
Nima ShafaghatianUniversity of Zanjan1
Hamdi EcheikhEcole Nationale d'Ingénieurs de Monastir1
Mohamed MoutchouUniversity of Hassan II Casablanca1
Souad TayaneUniversity of Hassan II Casablanca1
Yassine ZahraouiHassania School of Public Works1
Chaymae FahassaEcole Mohammadia d'Ingénieurs1

Affiliations come from OpenAlex; journal OAI-PMH metadata carries none. Authors without an OpenAlex ID are matched by name, which can merge or split people.

Metadata source: OAI-PMH (metadata jurnal) https://journal.umy.ac.id/index.php/jrc/oai, first harvested 9 Nov 2026, last seen 9 Nov 2026.
Original metadata (oai_dc)
<oai_dc:dc xmlns="http://www.openarchives.org/OAI/2.0/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/  http://www.openarchives.org/OAI/2.0/oai_dc.xsd">
	<dc:title xml:lang="en-US">SHAP-Based Framework for Temporal Detection of Sensor Drift in Gas Sensor Arrays</dc:title>
	<dc:creator>Cinar, Ridvan Firat</dc:creator>
	<dc:creator>Yuksek, Gokhan</dc:creator>
	<dc:creator>Lale, Timur</dc:creator>
	<dc:creator>Ekinci, Serdar</dc:creator>
	<dc:creator>Izci, Davut</dc:creator>
	<dc:creator>Ma'arif, Alfian</dc:creator>
	<dc:subject xml:lang="en-US">SHapley Additive Explanations (SHAP)</dc:subject>
	<dc:subject xml:lang="en-US">Sensor Drift</dc:subject>
	<dc:subject xml:lang="en-US">Concept Drift</dc:subject>
	<dc:subject xml:lang="en-US">Model Monitoring</dc:subject>
	<dc:subject xml:lang="en-US">Time-Series Interpretability</dc:subject>
	<dc:subject xml:lang="en-US">Feature Importance Analysis</dc:subject>
	<dc:description xml:lang="en-US">Sensor drift is a fundamental problem that undermines the long-term reliability of machine-learning models, as gradual changes in sensor response can silently degrade predictive performance. This challenge is particularly relevant in gas sensor arrays, where environmental variability and sensor aging strongly affect data quality. Ensuring effective monitoring of such drift is essential for industrial safety, environmental monitoring, and other applications that depend on stable sensing systems. To address this issue, we develop a SHAP (SHapley Additive Explanations)–based framework combined with an XGBoost classifier to detect drift at the feature level. The model is trained on structured sensor data, and SHAP values are computed batch-wise to capture temporal changes in feature relevance. Preprocessing enforces balanced class distributions and consistent concentration ranges, reducing potential confounding effects. Results from the Gas Sensor Array Drift dataset demonstrate that several sensor channels exhibit clear temporal variability in SHAP importance. Notably, these changes were observed even when accuracy and F1-score remained stable, highlighting that SHAP provides a complementary early-warning signal of drift. Case studies further confirm that the framework can capture both gradual and abrupt drift patterns. The research contribution of this study lies in providing an interpretable and time-resolved perspective on drift detection, enabling the localization of drift signals to specific sensors and features, independent of drift type or feature domain. This approach advances the state of the art by bridging explainable AI and drift monitoring. In conclusion, the framework supports practical deployment of adaptive sensing systems by making drift behaviour visible before conventional metrics degrade. Future work will focus on real-time scalability, broader datasets, and automated drift correction through recalibration or retraining.</dc:description>
	<dc:publisher xml:lang="en-US">Universitas Muhammadiyah Yogyakarta</dc:publisher>
	<dc:date>2025-11-03</dc:date>
	<dc:type>info:eu-repo/semantics/article</dc:type>
	<dc:type>info:eu-repo/semantics/publishedVersion</dc:type>
	<dc:format>application/pdf</dc:format>
	<dc:identifier>https://journal.umy.ac.id/index.php/jrc/article/view/28048</dc:identifier>
	<dc:identifier>10.18196/jrc.v6i5.28048</dc:identifier>
	<dc:source xml:lang="en-US">Journal of Robotics and Control (JRC); Vol. 6 No. 5 (2025); 2592-2601</dc:source>
	<dc:source>2715-5072</dc:source>
	<dc:source>2715-5056</dc:source>
	<dc:language>eng</dc:language>
	<dc:relation>https://journal.umy.ac.id/index.php/jrc/article/view/28048/11992</dc:relation>
	<dc:rights xml:lang="en-US">Copyright (c) 2025 Ridvan Firat Cinar, Gokhan Yuksek, Timur Lale, Serdar Ekinci, Davut Izci, Alfian Ma'arif</dc:rights>
	<dc:rights xml:lang="en-US">https://creativecommons.org/licenses/by-sa/4.0</dc:rights>
</oai_dc:dc>