Investigation of Odor from Surface Water Intensity Based on Pressure Variations Using an Intelligent Classification Approach

This article presents an investigation of odor intensity in surface water based on pressure variations using an intelligent classification approach. The study aims to develop a reliable method for assessing odor levels in water bodies, which can have significant implications for environmental monitoring and management. A dataset of pressure variations and corresponding odor intensity levels was collected and used to train a k-nearest neighbors (k-NN) classifier. The performance of the classifier was evaluated, and real-time simulations were conducted to demonstrate the applicability of the proposed method. The results show promising sensitivity in odor intensity classification, suggesting the potential of the proposed approach in practical odor monitoring systems. The high sensitivity (75.00%) indicates that the model can correctly identify a significant portion of actual positive cases, which is crucial in odor monitoring systems. Additionally, achieving the highest F1 Score (0.69) further reinforces the effectiveness of the model, as the F1 Score considers both precision and recall. A high F1 Score indicates a good balance between correctly identifying positive cases (precision) and capturing all positive cases (recall). With k = 2 being the chosen value, it suggests that the model performs optimally when considering only the two nearest neighbors for classification. This decision strikes a good balance between robustness, sensitivity, and overall classification accuracy.