2020 Volume 25 Issue 2 Pages 49-56
With the increase in the sizes of the farms in Japan’s livestock industry, managing individual animals has become quite difficult. Under such circumstances, disease detection becomes complicated, and the delay of detection increases the spread and severity of the disease. The purpose of this study is to establish an early detection system to identify respiratory diseases in pigs using body-conducted sound (BCS). Biological information such as respiratory sounds and heartbeat is necessary to properly determine the occurrence of disease. Therefore, a bio-information monitoring method for the disease-detection systems, which extracts periodic components in body-conducted sounds using independent component analysis (ICA) and adaptive signal processing (ALE), is proposed. Furthermore, significant differences were found through the analysis of BCS acoustics before and after inoculations in zero crossing and mel-frequency cepstral coefficient acoustic features, which are features of BCS when a pig has a respiratory disease. Therefore, it is suggested that early detection of respiratory diseases can be achieved by assessing these acoustic features.