Melola Discovery

← Melola Discovery

Akses terbuka Jurnal SINTA 1

Predictive Modeling of Carbon Monoxide with MOS Sensors and Machine Learning: A Potential Tool for Process Safety Improvement

Jurnal Nasional Teknik Elektro (2026)

DOI
10.25077/jnte.v15n1.1390.2026
ISSN
2302-2949, 2407-7267
Terbit
2026-03-29
Penerbit
Andalas University
Bahasa
en
Lisensi
creativecommons.org/licenses/by-nc-sa/4.0/

Abstrak

Carbon monoxide (CO) is a toxic, odorless gas commonly present in industrial processes and poses serious risks to occupational safety and health. This study proposes an optimized machine-learning-based approach to predict CO concentration using metal-oxide semiconductor (MOS) sensor arrays. The model was trained and evaluated on a public dataset comprising 650 time-series measurements from 14 thermally modulated MOS sensors, tested across CO concentrations ranging from 0 to 8.9 ppm under dynamic relative humidity (15%–75%). To optimize computational efficiency and mitigate multicollinearity, a multi-method feature selection strategy that combines Random Forest importance, Recursive Feature Elimination (RFE), and Mutual Information (MI) was implemented, successfully isolating sensors R10, R11, and R13 as the most robust predictors. A Random Forest Regression model, optimized via grid search and validated through five-fold cross-validation, was subsequently developed. The proposed framework demonstrated high predictive accuracy, achieving an R² of 0.884, Root Mean Square Error (RMSE) of 2.189 ppm, Mean Absolute Error (MAE) of 1.215 ppm, and Symmetric Mean Absolute Percentage Error (SMAPE) of 34.27%. These results highlight the potential of combining low-cost, feature-optimized MOS sensor arrays with ensemble machine learning for accurate, real-time gas monitoring. The framework provides a computationally efficient decision-support tool for the early detection of hazardous CO levels, contributing to safer process environments.

Kata kunci

Jaringan kolaborasi para penulis

12 penulis · 36 tautan kepenulisan bersama

Arahkan kursor atau ketuk sebuah nama untuk menyorot rekan penulisnya. Klik dua kali untuk membuka halaman penulis.

  • Politeknik Negeri Bandung
  • Afiliasi tidak diketahui
  • Organisasi berbeda
  • Organisasi sama
  • Afiliasi tidak diketahui
  • Garis lebih tebal = lebih banyak artikel bersama · lingkaran lebih besar = lebih banyak artikel
Tampilkan sebagai tabel
Rekan penulisOrganisasiArtikel bersama
Alfiana AdhitasariPoliteknik Negeri Bandung1
Rony SihombingPoliteknik Negeri Bandung1
Tifa ParamithaPoliteknik Negeri Bandung1
Ghaniari PutriPoliteknik Negeri Bandung1
Khumaira Maulani WijayaPoliteknik Negeri Bandung1

Afiliasi berasal dari OpenAlex; metadata OAI-PMH jurnal tidak memuatnya. Penulis tanpa ID OpenAlex dicocokkan berdasarkan nama, sehingga dua orang bisa tergabung atau satu orang bisa terpisah.

Sumber metadata: OpenAlex API (jurnal SINTA, ADR 0048) https://openalex.org/S4210175326, pertama di-harvest 20 Nov 2026, terakhir terlihat 20 Nov 2026.
Metadata asli (oai_dc)
<oai_dc:dc xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/"><dc:title xml:lang="en">Predictive Modeling of Carbon Monoxide with MOS Sensors and Machine Learning: A Potential Tool for Process Safety Improvement</dc:title><dc:creator>Hermin Kartika Sari</dc:creator><dc:creator>Thomas Oka Pratama</dc:creator><dc:creator>Yohana Fransiska Ferawati</dc:creator><dc:creator>Gita Nur Sajida</dc:creator><dc:creator>Gustin Mustika Krista</dc:creator><dc:creator>Teguh Taufiqurohim</dc:creator><dc:creator>Shoerya Shoelarta</dc:creator><dc:subject>carbon monoxide detection</dc:subject><dc:subject>metal oxide gas sensors</dc:subject><dc:subject>gas sensor arrays</dc:subject><dc:subject>feature selection</dc:subject><dc:subject>random forest regression</dc:subject><dc:subject>recursive feature elimination</dc:subject><dc:subject>mutual information</dc:subject><dc:subject>relative humidity effects</dc:subject><dc:subject>low-cost gas sensing</dc:subject><dc:subject>process safety</dc:subject><dc:subject>occupational safety</dc:subject><dc:subject>real-time gas monitoring</dc:subject><dc:description xml:lang="en">Carbon monoxide (CO) is a toxic, odorless gas commonly present in industrial processes and poses serious risks to occupational safety and health. This study proposes an optimized machine-learning-based approach to predict CO concentration using metal-oxide semiconductor (MOS) sensor arrays. The model was trained and evaluated on a public dataset comprising 650 time-series measurements from 14 thermally modulated MOS sensors, tested across CO concentrations ranging from 0 to 8.9 ppm under dynamic relative humidity (15%–75%). To optimize computational efficiency and mitigate multicollinearity, a multi-method feature selection strategy that combines Random Forest importance, Recursive Feature Elimination (RFE), and Mutual Information (MI) was implemented, successfully isolating sensors R10, R11, and R13 as the most robust predictors. A Random Forest Regression model, optimized via grid search and validated through five-fold cross-validation, was subsequently developed. The proposed framework demonstrated high predictive accuracy, achieving an R² of 0.884, Root Mean Square Error (RMSE) of 2.189 ppm, Mean Absolute Error (MAE) of 1.215 ppm, and Symmetric Mean Absolute Percentage Error (SMAPE) of 34.27%. These results highlight the potential of combining low-cost, feature-optimized MOS sensor arrays with ensemble machine learning for accurate, real-time gas monitoring. The framework provides a computationally efficient decision-support tool for the early detection of hazardous CO levels, contributing to safer process environments.</dc:description><dc:publisher>Andalas University</dc:publisher><dc:date>2026-03-29</dc:date><dc:type>info:eu-repo/semantics/article</dc:type><dc:identifier>https://doi.org/10.25077/jnte.v15n1.1390.2026</dc:identifier><dc:identifier>10.25077/jnte.v15n1.1390.2026</dc:identifier><dc:source>Jurnal Nasional Teknik Elektro; (2026)</dc:source><dc:source>2302-2949</dc:source><dc:source>2407-7267</dc:source><dc:language>en</dc:language><dc:rights>https://creativecommons.org/licenses/by-nc-sa/4.0/</dc:rights></oai_dc:dc>