Advances in Audio Classification and Artificial Intelligence for Respiratory Health and Welfare Monitoring in Swine

作者：M. Sharifuzzaman, Hongseok Mun, E. Lagua, M. Hasan, Jin-Gu Kang, Young-Hwa Kim, Ahsan Mehtab, Hae-Rang Park, Chul-Ju Yang · 发表于：Biology · 年份：2026 · DOI：10.3390/biology15020177 · 被引用次数：3 · 研究领域：Medicine

Simple Summary Respiratory diseases are a major challenge in pig farming and can cause serious economic losses if not detected early. Traditional diagnosis relies on visual inspection and laboratory testing, which are time-consuming and often identify problems only after disease has spread. In recent years, artificial intelligence (AI)-based sound analysis has emerged as a promising, non-invasive approach for monitoring pig health by automatically detecting changes in vocalizations such as coughing. This review summarizes recent advances in audio-based monitoring systems for respiratory disease detection and behavior monitoring in pigs, covering microphone technologies, signal processing techniques, machine learning and deep learning models, and on-farm deployment using edge and embedded devices. The strengths, limitations, and practical challenges of current systems are discussed, along with future opportunities for improving accuracy, robustness, and real-time application. AI-driven acoustic monitoring has strong potential to support early disease detection, improve animal welfare, and enhance decision making in modern pig production.