To improve the classification of pig vocalization using vocal signals and improve recognition accuracy, a pig vocalization classification method based on multi-feature fusion is proposed in this study. With the typical vocalization of pigs in large-scale breeding houses as the research object, short-time energy, frequency centroid, formant frequency and first-order difference, and Mel frequency cepstral coefficient and first-order difference were extracted as the fusion features. These fusion features were improved using principal component analysis. A pig vocalization classification model with a BP neural network optimized based on the genetic algorithm was constructed. The results showed that using the improved features to recognize pig grunting, squealing, and coughing, the average recognition accuracy was 93.2%; the recognition precisions were 87.9%, 98.1%, and 92.7%, respectively, with an average of 92.9%; and the recognition recalls were 92.0%, 99.1%, and 87.4%, respectively, with an average of 92.8%, which indicated that the proposed pig vocalization classification method had good recognition precision and recall, and could provide a reference for pig vocalization information feedback and automatic recognition.

The H9N2 avian influenza virus has become one of the dominant subtypes of avian influenza virus in poultry and has been significantly harmful to chickens in China, with great economic losses in terms of reduced egg production or high mortality by co-infection with other pathogens. A prediction of H9N2 status based on easily available production data with high accuracy would be important and essential to prevent and control H9N2 outbreaks in advance. This study developed a machine learning framework based on the XGBoost classification algorithm using 3 months’ laying rates and mortalities collected from three H9N2-infected laying hen houses with complete onset cycles. A framework was developed to automatically predict the H9N2 status of individual house for future 3 days (H9N2 status + 0, H9N2 status + 1, H9N2 status + 2) with five time frames (day + 0, day − 1, day − 2, day − 3, day − 4). It had been proven that a high accuracy rate > 90%, a recall rate > 90%, a precision rate of >80%, and an area under the curve of the receiver operator characteristic ≥ 0.85 could be achieved with the prediction models. Models with day + 0 and day − 1 were highly recommended to predict H9N2 status + 0 and H9N2 status + 1 for the direct or auxiliary monitoring of its occurrence and development. Such a framework could provide new insights into predicting H9N2 outbreaks, and other practical potential applications to assist in disease monitor were also considerable.

Ammonia (NH₃) concentrations in summer were continuously monitored from three typical laying hen houses of CC (conventional cage), AV (aviary), and NM (natural mating colony cage) with manure belt systems in North China Plain to quantify their emission levels, to characterize the diurnal variations, and to investigate the impact of environmental factors. Diurnal profiles were acquired by hourly measurements, and the effect of environmental factors on NH₃ emissions was presented by correlation analysis. The results showed that house-level NH₃ emissions in summer were the highest in the NM at 27.16 ± 13.12 mg/h·hen, followed by the AV at 4.08 ± 3.23 mg/h·hen and the CC at 3.43 ± 1.46 mg/h·hen within a complete manure removal cycle, which were significantly affected by manure accumulation inside the houses. After manure removal, NH₃ concentrations were reduced by 64.29%, 28.57%, and 35.71% in CC, AV, and NM, and consequently their emissions were lowered by 67.12%, 71.36%, and 55.69%, respectively. It was suggested that the manure should not be stored on the belt for more than 4 days in NM. A positive impact of indoor and outdoor temperature and ventilation rate on NH₃ emissions from AV and NM were found, while indoor and outdoor relative humidity had a negative effect. However, the above five factors did not significantly affect the emissions from CC.

To find an environmentally friendly and energy efficient alternative to acidic detergent for a milking system clean-in-place (CIP) process, this study investigated the feasibility of applying slightly acidic electrolyzed water (SAEW) alone to wash the system by cleaning soiled stainless steel (304) pipes, rubber gaskets, and PVC milk hoses, which were used in the milking system. The results showed that SAEW with appropriate parameters could achieve the same or even better hygienic effects compared with commercial detergent. Using response surface models, the SAEW parameters required to clean stainless steel were optimized at 9.9 min for the treatment time, 37.8 °C for the water temperature, and 60 mg/L for the available chlorine concentration; and were 14.4 min, 29.6 °C, and 60 mg/L for rubber gasket and PVC samples, respectively. After washing with the optimized parameter combination, bacteria and adenosine triphosphate on the three materials were almost non-detectable, indicating that SAEW has the potential to replace acidic detergents in CIP milking systems.