In order to solve the problem of low recognition accuracy of traditional pig sound recognition methods, deep neural network (DNN) and Hidden Markov Model (HMM) theory were used as the basis of pig sound signal recognition in this study. In this study, the sounds made by 10 landrace pigs during eating, estrus, howling, humming and panting were collected and preprocessed by Kalman filtering and an improved endpoint detection algorithm based on empirical mode decomposition-Teiger energy operator (EMD-TEO) cepstral distance. The extracted 39-dimensional mel-frequency cepstral coefficients (MFCCs) were then used as a dataset for network learning and recognition to build a DNN- and HMM-based sound recognition model for pig states. The results show that in the pig sound dataset, the recognition accuracy of DNN-HMM reaches 83%, which is 22% and 17% higher than that of the baseline models HMM and GMM-HMM, and possesses a better recognition effect. In a sub-dataset of the publicly available dataset AudioSet, DNN-HMM achieves a recognition accuracy of 79%, which is 8% and 4% higher than the classical models SVM and ResNet18, respectively, with better robustness.

(1) Background: Antibiotics are frequently used on farm animals, making animal husbandry a relatively large source of antibiotic pollution of the environment. The present study aims to isolate and acclimatize antibiotic-degrading bacterial strains for penicillin V potassium (PVK) from the contaminated soil of a pig farm. (2) Methods: Bacterial strains were isolated and acclimatized by continuous enrichment of cultures with PVK as the sole carbon source. The antibiotic susceptibility test, thiol mercury salt ultraviolet spectrophotometry (TMSUS), morphological observations, and 16S rDNA sequence analysis were used to identify and characterize the isolated strains. (3) Results: Four bacterial isolates (denoted as LM-1, LM-2, LM-3, LM-4) were obtained, and two of them (LM-1, LM-2) with the highest degradation rates were identified to belong to the same genera as Bacillus. These two isolates were found to be resistant to PVK antibiotic in an antibiotic sensitivity test. The TMSUS indicated that the strains LM-1 and LM-2 had good performance in PVK degradation (68% for LM-1, 66% for LM-2 in 48 h) when the initial PVK concentration was about 100 μg/mL. (4) Conclusions: Two bacterial strains isolated from the soil on a pig farm are effective in degrading PVK and can be potentially used for bioremediation of PVK antibiotic-contaminated soils.

(1) Objective: The objective of this study was to screen amoxicillin (AMX)-degrading bacterial strains in pig manure and optimize the fermentation conditions for these strains to achieve high fermentation rate, which can provide an effective way for the practical application of bacterial strains as antibiotic-degrading bacterial in treating livestock waste for antibiotic residues. (2) Methods: Antibiotic susceptibility tests and high-performance liquid chromatography tandem mass spectrometry (HPLC-MS/MS) were employed to screen AMX-degrading bacterial strains in pig manure. The culture conditions were optimized for AMX-degrading bacterial strains using Plackeet–Burman design (PBD), the steepest ascent design, and the response surface methods, coupled with the Box–Behnken design (BBD). The effects of culture time, temperature, rotator (mixing) speed, inoculum level, and initial pH value on the growth of AMX-degrading strains were investigated. Experimental data obtained from BBD were utilized to generate a second-order polynomial regression model for evaluating the effects of the tested variables on the optical density at 600 nm (OD₆₀₀) of culture solutions as the growth indicator for the screened AMX-degrading strains. (3) Results: The initial pH, culture time, and the inoculum level had significant effects on the OD₆₀₀ value (growth) of the screened AMX-degrading strains. The initial pH value was found to be the most critical factor influencing the growth of bacteria. The optimized culture condition for the bacterial growth determined by the response surface methodology was: the initial pH of 6.9, culture time of 52 h, and inoculum level of 2%. The average OD value of 12 different fermentation conditions in the initial fermentation tests in this study was 1.72 and the optimization resulted in an OD value of 3.00. The verification experiment resulted in an OD value of 2.94, which confirmed the adequacy of the optimization model for the determining the optimal culture condition. (4) Conclusions: The growth of the screened strain of AMX-degrading bacteria could be optimized by changing the fermentation conditions. The optimization could be achieved by using the Box–Behnken response surface method and Plackett–Burman experimental design.

Hydrothermal liquefaction (HTL) is one of the most promising technologies for biofuel production. The preparation and application of catalysts for HTL have been the research focus in recent years. In this study, a new synergistic catalytic process strategy is proposed. CuO-CeO₂/γ-Al₂O₃ was used as an in situ hydrogen donor catalyst and Ni-Co/SAPO-34 was synthesized for hydroprocessing to improve bio-oil production process. The results of XRD and XPS demonstrated that the metal components were well supported on the catalyst. When the two catalysts were mixed, the yield of bio-oil increased from 51.00% to 64.51%, the carbon recovery rate raised from 69.53% to 88.18%, the energy recovery rate grew from 63.42% to 80.22%, and the S content is relatively reduced by 83.3%. Also, TG analysis showed that the content of light components in bio-oil increased. Moreover, the hydrocarbons and alcohols were observed to a higher proportion from the GC-MS analysis. This new method still has high catalytic activity after repeated use for five times. This study provides a new idea for preparing higher yield and superior quality bio-oil.

The existing algorithms for identifying and tracking pigs in barns generally have a large number of parameters, relatively complex networks and a high demand for computational resources, which are not suitable for deployment in embedded-edge nodes on farms. A lightweight multi-objective identification and tracking algorithm based on improved YOLOv5s and DeepSort was developed for group-housed pigs in this study. The identification algorithm was optimized by: (i) using a dilated convolution in the YOLOv5s backbone network to reduce the number of model parameters and computational power requirements; (ii) adding a coordinate attention mechanism to improve the model precision; and (iii) pruning the BN layers to reduce the computational requirements. The optimized identification model was combined with DeepSort to form the final Tracking by Detecting algorithm and ported to a Jetson AGX Xavier edge computing node. The algorithm reduced the model size by 65.3% compared to the original YOLOv5s. The algorithm achieved a recognition precision of 96.6%; a tracking time of 46 ms; and a tracking frame rate of 21.7 FPS, and the precision of the tracking statistics was greater than 90%. The model size and performance met the requirements for stable real-time operation in embedded-edge computing nodes for monitoring group-housed pigs.

To achieve high-speed quantitative hole sowing of rice using an unmanned aerial vehicle (UAV), this study proposes an agricultural UAV pneumatic hole sowing system suitable for high-speed quantitative hole sowing. This system is based on pelletizing rice seeds. A pneumatic seed distribution system based on the Venturi effect was designed, with a seed feeding device that employs a computational fluid dynamics–discrete element method (CFD-DEM) coupled simulation method to construct a gas–solid two-phase flow simulation model that simulates actual field sowing conditions and analyzes seed transport characteristics. Using the seed feeding device blending chamber height, expansion section cone angle, and inlet airflow velocity as experimental factors, and evaluating seed distribution statistics based on the hole formation ratio(HFR) and hole spacing coefficient of variation (HSCV), the study achieved a comprehensive statistical analysis of seed distribution patterns. The Box–Behnken orthogonal experiment optimized the structural parameters of the seed feeding device, determining the optimal airflow velocity during seeding. The optimized parameter combination yielded a blending chamber height of 15.59 mm, an expansion section cone angle of 22.20°, and an inlet airflow velocity of 19.67 m/s, corresponding to an HFR of 84.66% and an HSCV of 6.95%. Field trials validated an HFR of 86.25% and an HSCV of 6.83%. This study provides theoretical and technical support for the design of high-speed hole -sowing equipment for rice using a UAV.