Abstract
Effective livestock management has become essential owing to an aging workforce and the growth of large-scale farming operations in the agricultural industry. Conventional monitoring methods, primarily reliant on manual observation, are increasingly reaching their limits, necessitating the development of innovative automated solutions. This study developed a system, termed mixed-ELAN, for real-time sow and piglet behavior detection using an extended ELAN architecture with diverse kernel sizes. The standard convolution operations within the ELAN framework were replaced with MixConv using diverse kernel sizes to enhance feature learning capabilities. To ensure high reliability, a performance evaluation of all techniques was conducted using a k-fold cross-validation (k = 3). The proposed architecture was applied to YOLOv7 and YOLOv9, yielding improvements of 1.5% and 2%, with mean average precision scores of 0.805 and 0.796, respectively, compared with the original models. Both models demonstrated significant performance improvements in detecting behaviors critical for piglet growth and survival, such as crushing and lying down, highlighting the effectiveness of the proposed architecture. These advances highlight the potential of AI and computer vision in agriculture, as well as the system's benefits for improving animal welfare and farm management efficiency. The proposed architecture enhances the real-time monitoring and understanding of livestock behavior, establishing improved benchmarks for smart farming technologies and enabling further innovation in livestock management.