Classified & regression data set

In areas where livestock is bred, there is a demand for accurate, real-time, and stable monitoring of ammonia concentration in the breeding environment. Existing electronic nose systems, however, struggle with slow response times and limited detection accuracy. This paper introduces a novel solution: an active pumping ammonia detection system using artificial olfaction based on a biomimetic chamber. We analyzed the biomimetic chamber’s structure and the sensor array's surface airflow to determine the system’s sensing units. The system employs an electronic nose to detect ammonia and ethanol gases in a circulating airflow within a closed box. The captured signals underwent processing, followed by the application of classification and regression models for data prediction. Our results suggest that this system, leveraging the biomimetic chamber, offers rapid gas detection response times. Incorporating a backpropagation (BP) neural network algorithm, it realizes high classification prediction accuracy, with a determination coefficient R² value of 0.99 for single-output regression and over 0.98 for multi-output regression predictions. These outcomes demonstrate the system’s effectiveness in accurately detecting ammonia emitted during livestock fermentation, meeting the ammonia detection requirements of breeding farms.