FEATURE EXTRACTION AND SUPERVISED LEARNING FOR VOLATILE ORGANIC COMPOUNDS GAS RECOGNITION
DOI:
https://doi.org/10.31436/iiumej.v24i2.2832Keywords:
Machine learning, Supervised machine learning, Volatile Organic Compound, Gas Classification, Gas Detection, VOC Sensor, Feature ExtractionAbstract
The emergence of advanced technologies, particularly in the field of artificial intelligence (AI), has sparked significant interest in exploring their potential benefits for various industries, including healthcare. In the medical sector, the utilization of sensing systems has proven valuable for diagnosing pulmonary diseases by detecting volatile organic compounds (VOCs) in exhaled breath. However, the identification of the most informative and discriminating features from VOC sensor arrays remains an unresolved challenge, essential for achieving robust VOC class recognition. This research project aims to investigate effective feature extraction techniques that can be employed as discriminative features for machine learning algorithms. A preliminary dataset was used to predict VOC classification through the application of five supervised machine learning algorithms: k-Nearest Neighbors (kNN), Random Forest (RF), Support Vector Machines (SVM), Logistic Regression (LR), and Artificial Neural Networks (ANN). Ten feature extraction methods were proposed based on changes in sensor response as inputs to classify three types of gases in the dataset. The performance of each model was evaluated and compared using k-Fold cross-validation (k=10) and metrics derived from the confusion matrix. The results demonstrate that the RF model achieved the highest mean accuracy and standard deviation, with values of 0.813 ± 0.035, followed closely by kNN with 0.803 ± 0.033. Conversely, LR, SVM (kernel=Polynomial), and ANN exhibited poor performances when applied to the VOC dataset, with accuracies of 0.447 ± 0.035, 0.403 ± 0.041, and 0.419 ± 0.035, respectively. Therefore, this paper provides evidence that classifying VOC gases based on sensor responses is feasible and emphasizes the need for further research to explore sensor array analysis to enhance feature extraction techniques.
ABSTRAK: Perkembangan teknologi canggih, khususnya dalam bidang kecerdasan buatan (AI), telah mencetuskan minat yang ketara dalam menerokai manfaatnya untuk pelbagai industri, termasuk bidang kesihatan. Dalam sektor perubatan, penggunaan sistem penderiaan telah terbukti bernilai untuk mendiagnosis penyakit paru-paru dengan mengesan sebatian organik meruap (VOC) dalam nafas yang dihembus manusia. Walau bagaimanapun, pengenalpastian ciri yang paling bermaklumat dan mendiskriminasi daripada penderia VOC kekal sebagai cabaran yang tidak dapat diselesaikan, penting untuk mencapai pengiktirafan kelas VOC yang kukuh. Projek penyelidikan ini bertujuan untuk menyiasat teknik pengekstrakan ciri yang berkesan yang boleh digunakan sebagai ciri diskriminatif untuk algoritma pembelajaran mesin. Set data awal digunakan untuk meramalkan klasifikasi VOC melalui aplikasi lima algoritma pembelajaran mesin yang diselia: k-Nearest Neighbors (kNN), Random Forest (RF), Support Vector Machines (SVM), Logistic Regression (LR), dan Artificial Neural Networks (ANN). Sepuluh kaedah pengekstrakan ciri telah dicadangkan berdasarkan perubahan dalam tindak balas penderia sebagai input untuk mengklasifikasikan tiga jenis gas dalam set data. Prestasi setiap model telah dinilai dan dibandingkan menggunakan pengesahan silang k-Fold (k=10) dan metrik yang diperoleh daripada confusion matriks . Keputusan menunjukkan bahawa model RF mencapai ketepatan minima tertinggi dan sisihan piawai, dengan nilai 0.813 ± 0.035, diikuti oleh kNN dengan 0.803 ± 0.033. Sebaliknya, LR, SVM (kernel=Polinomial), dan ANN mempamerkan prestasi yang lemah apabila digunakan pada dataset VOC, dengan ketepatan masing-masing 0.447 ± 0.035, 0.403 ± 0.041 dan 0.419 ± 0.035. Oleh itu, kertas kerja ini memberikan bukti bahawa mengklasifikasikan gas VOC berdasarkan tindak balas penderia adalah boleh dilaksanakan dan menekankan keperluan untuk penyelidikan lanjut untuk meneroka analisis tatasusunan penderia untuk meningkatkan teknik pengekstrakan ciri.
Downloads
Metrics
References
Krisher S, Riley A, Mehta K. (2014) Designing breathalyser technology for the developing world: How a single breath can fight the double disease burden. Journal of Medical Engineering and Technology, 38(3), 156–163. doi:10.3109/03091902.2014.890678. DOI: https://doi.org/10.3109/03091902.2014.890678
Dragonieri S, Pennazza G, Carratu P, and Resta O. (2017) Electronic Nose Technology in Respiratory Diseases. Lung, 195 (2):157–165. doi:10.1007/s00408-017-9987-3. DOI: https://doi.org/10.1007/s00408-017-9987-3
Thriumani R, Zakaria A, Hashim YZH, Jeffree AI, Helmy KM, Kamarudin LM, Omar MI, Shakaff AYM, Adom AH, Persaud KC. (2018) A study on volatile organic compounds emitted by in-vitro lung cancer cultured cells using gas sensor array and SPME-GCMS. BMC Cancer, 18:362 doi:10.1186/s12885-018-4235-7. DOI: https://doi.org/10.1186/s12885-018-4235-7
Chen C, Lin W, Yang H. (2020) Diagnosis of ventilator-associated pneumonia using electronic nose sensor array signals: solutions to improve the application of machine learning in respiratory research. Respiratory Research, 21:45. doi:10.1186/s12931-020-1285-6. DOI: https://doi.org/10.1186/s12931-020-1285-6
Hu W, Wan L, Jian Y, Ren C, Jin K, Su X, Bai X, Haick H, Yao M, Wu W. (2018) Electronic Noses: From Advanced Materials to Sensors Aided with Data Processing. Advanced Materials Technologies, 4(2),1-38. doi: 10.1002/admt.201800488. DOI: https://doi.org/10.1002/admt.201800488
Yan J, Guo X, Duan S, Jia P, Wang L, Peng C, Zhang S. (2015) Electronic Nose Feature Extraction Methods: A Review. Sensors, 15, 27804-27831. doi:10.3390/s151127804 27804–27831. DOI: https://doi.org/10.3390/s151127804
Zulkhairi MA, Mustafah YM, Abidin ZZ, Zaki HFM, Rahman HA. (2019) Car Detection Using Cascade Classifier on Embedded Platform. 7th International Conference on Mechatronics Engineering (ICOM), Putrajaya, Malaysia, pp. 1-3, doi: 10.1109/ICOM47790.2019.8952064. DOI: https://doi.org/10.1109/ICOM47790.2019.8952064
Ansari AQ, Khusro A, Ansari MR. (2016) Performance evaluation of classifier techniques to discriminate odors with an E-Nose. 12th IEEE International Conference Electronics, Energy, Environment, Communication, Computer, Control: (E3-C3), INDICON, 2325-9418. doi:10.1109/INDICON.2015.7443838. DOI: https://doi.org/10.1109/INDICON.2015.7443838
Yi Z, Li C. (2019) Anti-Drift in Electronic Nose via Dimensionality Reduction: A Discriminative Subspace Projection Projection Approach. IEEE Access, 7, 170087–170095. doi:10.1109/ACCESS.2019.2955712. DOI: https://doi.org/10.1109/ACCESS.2019.2955712
Vergara A, Vembu S, Ayhan T, Ryan MA, Homer ML, Huerta R. (2012) Chemical gas sensor drift compensation using classifier ensembles. Sensors and Actuators, B: Chemical, 166–167, 320–329. doi: 10.1016/j.snb.2012.01.074. DOI: https://doi.org/10.1016/j.snb.2012.01.074
Liu B, Huang Y, Kam KW, Cheung WF, Zhao N, Zheng B. (2019) Functionalized graphene-based chemiresistive electronic nose for discrimination of disease-related volatile organic compounds. Biosensors and Bioelectronics: X, 1, 100016. doi: 10.1016/j.biosx.2019.100016. DOI: https://doi.org/10.1016/j.biosx.2019.100016
Gargiulo V, Alfano B, Capua RD, Alfè M, Vorokhta M, Polichetti T, Massera E, Miglietta ML, Schiattarella C, Francia GD. (2018) Graphene-like layers as promising chemiresistive sensing material for detection of alcohols at low concentration. Journal of Applied Physics, 123, 024503. doi:10.1063/1.5000914. DOI: https://doi.org/10.1063/1.5000914
Lu G, Ocola LE, Chen J. (2009) Reduced graphene oxide for room-temperature gas sensors. Nanotechnology, 20, 445502, 1-9. doi:10.1088/0957-4484/20/44/445502. DOI: https://doi.org/10.1088/0957-4484/20/44/445502
Lee K, Yoo YK, Chae MS, Hwang KS, Lee J, Kim H, Hur D, Jeong HL. (2019) Highly selective reduced graphene oxide (rGO) sensor based on a peptide aptamer receptor for detecting explosives. Sci Rep, 9, 10297. Scientific Reports, 9. doi:10.1038/s41598-019-45936-z. DOI: https://doi.org/10.1038/s41598-019-45936-z
Tian W, Liu X, Yu W. (2018) Research progress of gas sensor based on graphene and its derivatives: A review. Applied Sciences (Switzerland), 8(7). doi:10.3390/app8071118. DOI: https://doi.org/10.3390/app8071118
Lee SP. (2017) Electrodes for Semiconductor Gas Sensors. Sensors, 17, 683; doi:10.3390/s17040683. DOI: https://doi.org/10.3390/s17040683
Wang C, Yin L, Zhang L, Xiang D, Gao R. (2010) Metal Oxide Gas Sensors: Sensitivity and Influencing Factors. Sensors, 10, 2088-2106. doi:10.3390/s100302088. DOI: https://doi.org/10.3390/s100302088
Baharuddin AA, Ang BC, Hoong Y, Haseeb ASMA, Wong YC. (2019) Materials Science in Semiconductor Processing Advances in chemiresistive sensors for acetone gas detection. Materials Science in Semiconductor Processing, 103, 104616. doi: 10.1016/j.mssp.2019.104616. DOI: https://doi.org/10.1016/j.mssp.2019.104616
Amiri V, Roshan H, Mirzaei A, Neri G, Ayesh AI. (2020) Nanostructured Metal Oxide-Based Acetone Gas Sensors: A Review. Sensors, 20, 3096. doi:10.3390/s20113096. DOI: https://doi.org/10.3390/s20113096
Norizan MN, Zulaikha S, Demon N, Halim NA. (2021) The frontiers of functionalized graphene-based nanocomposites as chemical sensors. Nanotechnology Reviews, 10: 330-369. doi:10.1515/ntrev-2021-0030. DOI: https://doi.org/10.1515/ntrev-2021-0030
James F, Fiorido T, Bendahan M, Aguir K. (2017) Comparison between MOX sensors for low VOCs concentrations with interfering gases ALLSENSORS, pp.39-40.
Phillips CO, Syed Y, Parthaláin NM, Zwiggelaar R, Claypole TC, Lewis KE. (2012) Machine learning methods on exhaled volatile organic compounds for distinguishing COPD patients from healthy controls. Journal of Breath Research, 6(3). doi: 10.1088/1752-7155/6/3/036003. DOI: https://doi.org/10.1088/1752-7155/6/3/036003
Yan J, Tian F, He Q, Shen, Y. (2012) Feature Extraction from Sensor Data for Detection of found Pathogen Based on Electronic Nose. Sensors and Materials, 24(2), 57–73. DOI: https://doi.org/10.18494/SAM.2012.734
Feng S, Farha F, Li Q, Wan Y, Xu Y, Zhang T, Ning H. (2019) Review on smart gas sensing technology. Sensors (Switzerland), 19(17), 1–22. doi:10.3390/s19173760. DOI: https://doi.org/10.3390/s19173760
Hashoul D, Haick H. (2019) Sensors for detecting pulmonary diseases from exhaled breath. European Respiratory Review, 28(152). doi:10.1183/16000617.0011-2019. DOI: https://doi.org/10.1183/16000617.0011-2019
Xu Y, Zhao X, Chen Y, Yang Z. (2019) Research on a mixed gas classification algorithm based on extreme random trees. Applied Sciences (Switzerland), 9(9). doi:10.3390/app9091728. DOI: https://doi.org/10.3390/app9091728
Thorson J, Collier-Oxandale A, Hannigan M. (2019) Using A Low-Cost Sensor Array and Machine Mixtures and Identify Likely Sources. Sensors, 19, 3723. doi:10.3390/s19173723. DOI: https://doi.org/10.3390/s19173723
Tombel NSM, Badaruddin SAM, Yakin FSM, Zaki HFM, Syono MI (2021) Detection of low PPM of volatile organic compounds using nanomaterial functionalized reduced graphene oxide sensor. AIP Conference Proceedings, 2368 vol. 020004. doi.org/10.1063/5.0057775. DOI: https://doi.org/10.1063/5.0057775
Smolinska A. (2014) Current breathomics - A review on data pre-processing techniques and machine learning in metabolomics breath analysis. Journal of Breath Research, 8, 027105: 22. doi:10.1088/1752-7155/8/2/027105. DOI: https://doi.org/10.1088/1752-7155/8/2/027105
Das S, Jayaraman V. (2014) Progress in Materials Science SnO2: A comprehensive review in structures and gas sensors. Progress in Materials Science, 66, pp. 112-255. doi: 10.1016/j.pmatsci.2014.06.003. DOI: https://doi.org/10.1016/j.pmatsci.2014.06.003
Maity A, Raychaudhuri AK, Ghosh B. (2019) High sensitivity NH3 gas sensor with electrical readout made on paper with prevoskite halide as sensor material. Scientific Report, 9, 7777. doi: 10.1038/s41598-019-43961-6. DOI: https://doi.org/10.1038/s41598-019-43961-6
Webb AR (2002) Statistical Pattern Recognition Statistical Pattern Recognition Second Edition. John Wiley & Sons,Ltd, vol. 9. DOI: https://doi.org/10.1002/0470854774
Bastuck M. (2019) Improving the Performance of Gas Sensor Systems with Advanced Data Evaluation, Operation and Calibration Methods. Linköping University Electronic Press, 298. DOI: https://doi.org/10.3384/diss.diva-159106
Kong C, Zhao S, Weng X, Liu C, Guan R, Chang Z. (2019) Weighted Summation: Feature Extraction of Farm Pigsty Data for Electronic Nose. IEEE Access, vol. 7, pp. 96732-96742. doi:10.1109/access.2019.2929526. DOI: https://doi.org/10.1109/ACCESS.2019.2929526
Allwright S. (2022) How to interpret AUC score. Retrieved from https://stephenallwright.com/interpret-auc-score/.
Nyssa SSC, XueVZ, Justin TN, V. R. Saran KC, Raia CF, Michael JL, Thomas LW, Mike F, Gregory JS, Philippe B, Christopher JH, Steven JK. (2022) Machine Learning-Based Rapid Detection of Volatile Organic Compounds in a Graphene Electronic Nose. ACS Nano 2022 16 (11), 19567-19583. doi: 10.1021/acsnano.2c10240. DOI: https://doi.org/10.1021/acsnano.2c10240
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2023 IIUM Press
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.