Assessment of reproductive and growth performance of pigs on commercial swine farms in southern Kyushu, Japan

Combined spectral and speech features for pig speech recognition

The sound of the pig is one of its important signs, which can reflect various states such as hunger, pain or emotional state, and directly indicates the growth and health status of the pig. Existing speech recognition methods usually start with spectral features. The use of spectrograms to achieve classification of different speech sounds, while working well, may not be the best approach for solving such tasks with single-dimensional feature input. Based on the above assumptions, in order to more accurately grasp the situation of pigs and take timely measures to ensure the health status of pigs, this paper proposes a pig sound classification method based on the dual role of signal spectrum and speech. Spectrograms can visualize information about the characteristics of the sound under different time periods. The audio data are introduced, and the spectrogram features of the model input as well as the audio time-domain features are complemented with each other and passed into a pre-designed parallel network structure. The network model with the best results and the classifier were selected for combination. An accuracy of 93.39% was achieved on the pig speech classification task, while the AUC also reached 0.99163, demonstrating the superiority of the method. This study contributes to the direction of computer vision and acoustics by recognizing the sound of pigs. In addition, a total of 4,000 pig sound datasets in four categories are established in this paper to provide a research basis for later research scholars.

Productivity analysis of 70 farrow-to-finish swine farms in Japan from 2013 to 2018

Improving productivity is an urgent issue in the swine industry if it is to compete internationally. However, lack of data about recent productivity transition obstructs stakeholder planning. This study investigated the yearly productivity trends among farrow-to-finish swine farms in Japan using annual productivity data from 2013–2018 obtained for 70 farms in Japan. The productivity parameters analyzed were pigs born alive per litter (PBA), preweaning mortality (PRWM), pigs weaned per litter (PWL), litters per mated female per year (LMFY), pigs weaned per mated female per year (PWMFY), post-weaning mortality (POWM) and marketed pigs per mated female per year (MP). Data were classified into three groups based on the size of the average female inventory and compared among groups. Results presented the mean PBA increased continuously over the 6-year period (P<0.001), and the PWL, PWMFY, and MP means began increasing after 2015 (P<0.001). These upward trends were particularly remarkable on large farms. The mean PRWM increased sharply in 2014, thus inhibiting the increases in PWL, PWMFY, and MP for the same year. The LMFY and POWM means did not change during the study period. Altogether, productivity in Japan improved markedly during the study period, indicating highly prolific sows were well utilized with suitable breeding techniques among farmers these days. Continued genetic improvement and sow management would aid further development in Japan.

Quantitative relationship between the number of cross-fostering piglets and subsequent productivity of sows on commercial swine farms

The present study aimed to investigate the quantitative relationship between the number of cross-fostering (CF) piglets and subsequent productivity of sows. Data were obtained from seven commercial farms including 41,086 farrowing records. Sows were divided into those that fostered out three or more piglets (CF ≥ 3-), fostered out one or two piglets (CF1-2-), did not do CF (NCF), fostered in one or two piglets (CF1-2+), and fostered in three or more piglets (CF ≥ 3+). CF ≥ 3- sows had the lowest number of piglets weaned and the highest preweaning mortality rate, whereas CF ≥ 3+ sows had the second-lowest number of piglets weaned and the second-highest preweaning mortality rate (p < .05). The number of piglets weaned and preweaning mortality rate did not differ among CF1-2-, NCF, and CF1-2+ sows. CF ≥ 3+ sows had the lowest farrowing rate (p < .05). The number of piglets born alive at the subsequent parity was highest for CF ≥ 3- sows (p < .05), followed in order by CF1-2-, NCF, CF1-2+, and CF ≥ 3+ sows (p < .05). In summary, CF1-2- and CF1-2+ sows showed no decreases in productivity compared with NCF sows, whereas CF ≥ 3- and CF ≥ 3+ sows had reduced productivity.