Classification of Liquid Aroma Profiles Using Electronic Nose and Classical Machine Learning Methods

Binnur Saycan; Yavuz Selim Taspinar

doi:10.47134/jtsi.v3i1.5344

Authors

Binnur Saycan Selcuk University
Yavuz Selim Taspinar Selcuk University

DOI:

https://doi.org/10.47134/jtsi.v3i1.5344

Keywords:

Electronic Nose, Machine Learning, Feature Extraction, Classification, , Performance Analysis

Abstract

The identification of aroma and quality profiles in liquids such as milk, coffee, tea, and vinegar is crucial for improving product quality. Since traditional methods are time-consuming and costly, the rapid detection of volatile organic compounds (VOCs) in such liquids using sensors has gained importance in recent times. Therefore, the AI Nose Dataset 250 data set obtained from the Electronic Nose (E-Nose) system was used in this study. This dataset contains 7 features consisting of 6 chemical and environmental sensors and 5 different classes: Perfume, Air, Coffee, Tea, and Vinegar. The Naive Bayes (NB) algorithm was used along with Random Forest (RF), k-Nearest Neighbor (kNN), AdaBoost, and Decision Tree (DT) methods to classify these data. To analyze the classification performance of the models, the Confusion Matrix was used along with the metrics Accuracy, Precision, Recall, and F1 Score. The ROC Curve was used for a detailed analysis of the classification performance of the models. As a result of the training and testing of the models, classification performance close to 100% was achieved with the RF and kNN models. The highest classification performance was achieved with the RF model. When the results were examined, it was seen that the classification performance of all Machine Learning models

References

Adak, M. F. (2016). Elektronik burun verilerinin yapay zeka tabanlı algoritmalarla sınıflandırılması Sakarya Universitesi (Turkey)].

Astuti, S. D., Wicaksono, I. R., Soelistiono, S., Permatasari, P. A. D., Yaqubi, A. K., Susilo, Y., Putra, C. D., & Syahrom, A. (2024). Electronic nose coupled with artificial neural network for classifying of coffee roasting profile. Sensing and Bio-Sensing Research, 43, 100632. https://doi.org/https://doi.org/10.1016/j.sbsr.2024.100632

Borah, S., Hines, E., Leeson, M., Iliescu, D., Bhuyan, M., & Gardner, J. W. (2008). Neural network based electronic nose for classification of tea aroma. Sensing and Instrumentation for Food Quality and Safety, 2, 7-14. https://doi.org/10.1007/s11694-007-9028-7

Cascos, G., Lozano, J., Montero-Fernández, I., Marcía-Fuentes, J. A., Aleman, R. S., Ruiz-Canales, A., & Martín-Vertedor, D. (2023). Electronic nose and gas chromatograph devices for the evaluation of the sensory quality of green coffee beans. Foods, 13(1), 87.

Çetin, O., Özer, İ., Görür, K., & Temurtaş, F. (2024). Elektronik Burun ve Makine Öğrenmesi Yöntemleri Kullanılarak Gıda Aromalarının Sınıflandırılması [Classification of Food Flavours using Electronic Nose and Machine Learning Methods]. Mühendislik Bilimleri ve Araştırmaları Dergisi, 6(1), 35-41. https://doi.org/10.46387/bjesr.1405146

Dağlı, E., Büber, M., & Taspınar, Y. S. (2022). Detection of accident situation by machine learning methods using traffic announcements: the case of metropol Istanbul. International journal of applied mathematics electronics and computers, 10(3), 61-67.

İncegül, Y., Özkan, G., İncegül, A. C., & Taşdelen, K. (2022). Elektronik Burun Metal Oksit Yarı İletken Sensörlerin Gıda Analizlerinde Kullanımı [Use of Electronic Nose Metal Oxide Semiconductor Sensors in Food Analysis]. Akademik Gıda, 20(4), 454-473. https://doi.org/10.24323/akademik-gida.1224839

Iswanto, B., Muflih, A., & Baith, H. (2024). Low-Cost Electronic Nose for Robusta and Arabica Coffee Classification Using 1-D Convolutional Neural Networks. Journal of Physics: Conference Series,

Jara-Cornejo, E., Peña-Bedón, E., Torres Moya, M., Espinoza-Torres, S., Sotomayor, M. D., Picasso, G., Tuesta, J. C., López, R., & Khan, S. (2024). Electrochemical Analysis of Curcumin in Real Samples Using Intelligent Materials. Polymers, 16(3), 366.

Jiménez-López, I., Molina-Quiroga, J., & Gutiérrez, J. M. (2023). Classification of Teas Using Different Feature Extraction Methods from Signals of a Lab-Made Electronic Nose. Engineering Proceedings, 48(1), 20.

Koklu, M., Cinar, I., Taspinar, Y. S., & Kursun, R. (2022, June). Identification of sheep breeds by CNN-based pre-trained InceptionV3 model. In 2022 11th Mediterranean Conference on Embedded Computing (MECO) (pp. 01-04). IEEE.

Krishna, S. N. (2025). AI Nose Dataset 250. In: Kaggle.

Lu, T., Shi, G., Own, A., Qu, Y., Li, Y., Adiraju, A., & Kanoun, O. (2024). Portable Metal Oxide E-Nose Based on Machine Learning for Multiple Beverage Classification. 2024 International Workshop on Impedance Spectroscopy (IWIS),

Romani, S., Cevoli, C., Fabbri, A., Alessandrini, L., & Dalla Rosa, M. (2012). Evaluation of coffee roasting degree by using electronic nose and artificial neural network for off‐line quality control. Journal of food science, 77(9), C960-C965.

Sanislav, T., Mois, G. D., Zeadally, S., Folea, S., Radoni, T. C., & Al-Suhaimi, E. A. (2025). A comprehensive review on sensor-based electronic nose for food quality and safety. Sensors, 25(14), 4437.

Sen, H. F., & Taspinar, Y. S. (2024, December). Body Performance Analysis with Machine Learning and ANOVA Methods. In 2024 21st International Conference on Mechatronics-Mechatronika (ME) (pp. 1-6). IEEE.

Sen, H. F., & Taspinar, Y. S. (2025, May). Obesity Prediction Using Machine Learning Methods: Performance Analysis of DT, RF, and ANN Models. In 2025 7th International Congress on Human-Computer Interaction, Optimization and Robotic Applications (ICHORA) (pp. 1-6). IEEE.

Susanti, R., Zaini, Z., Hidayat, A., Alfitri, N., & Rusydi, M. I. (2023). Identification of Coffee Types Using an Electronic Nose with the Backpropagation Artificial Neural Network. JOIV: International Journal on Informatics Visualization, 7(3), 659-664.

Taspinar, Y. S., Koklu, M., & Altin, M. (2021). Classification of flame extinction based on acoustic oscillations using artificial intelligence methods. Case Studies in Thermal Engineering, 28, 101561.

Taspinar, Y. S., Koklu, M., & Altin, M. (2022). Acoustic-driven airflow flame extinguishing system design and analysis of capabilities of low frequency in different fuels. Fire technology, 58(3), 1579-1597.

Taspinar, Y. S. (2023). Light weight convolutional neural network and low-dimensional images transformation approach for classification of thermal images. Case Studies in Thermal Engineering, 41, 102670.

Taspinar, Y. S. (2025). Machine Learning-Driven E-Nose-Based Diabetes Detection: Sensor Selection and Feature Reduction Study. Sensors, 25(21), 6607.

Taspinar, Y. S., Cinar, I., & Koklu, M. (2022). Classification by a stacking model using CNN features for COVID-19 infection diagnosis. Journal of X-ray science and technology, 30(1), 73-88.

Wang, J., Zhang, C., Chang, M., He, W., Lu, X., Fei, S., & Lu, G. (2021). Optimization of electronic nose sensor array for tea aroma detecting based on correlation coefficient and cluster analysis. Chemosensors, 9(9), 266.

Wei, G., Dan, M., Zhao, G., & Wang, D. (2023). Recent advances in chromatography-mass spectrometry and electronic nose technology in food flavor analysis and detection. Food Chemistry, 405, 134814. https://doi.org/https://doi.org/10.1016/j.foodchem.2022.134814

Ye, Z., Liu, Y., & Li, Q. (2021). Recent progress in smart electronic nose technologies enabled with machine learning methods. Sensors, 21(22), 7620.