<![CDATA[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]]>
Copyrights © 2026
