An Image Detection Model for Aggressive Behavior of Group Sheep.

Sheep aggression detection is crucial for maintaining the welfare of a large-scale sheep breeding environment. Currently, animal aggression is predominantly detected using image and video detection methods. However, there is a lack of lightweight network models available for detecting aggressive behavior among groups of sheep. Therefore, this paper proposes a model for image detection of aggression behavior in group sheep. The proposed model utilizes the GhostNet network as its feature extraction network, incorporating the PWConv and Channel Shuffle operations into the GhostConv module. These additional modules improve the exchange of information between different feature maps. An ablation experiment was conducted to compare the detection effectiveness of the two modules in different positions. For increasing the amount of information in feature maps of the GhostBottleneck module, we applied the Inverted-GhostBottleneck module, which introduces inverted residual structure based on GhostBottleneck. The improved GhostNet lightweight feature extraction network achieves 94.7% Precision and 90.7% Recall, and its model size is only 62.7% of YOLOv5. Our improved model surpasses the original model in performance. Furthermore, it addresses the limitation of the video detection model, which was unable to accurately locate aggressive sheep. In real-time, our improved model successfully detects aggressive behavior among group sheep.

Spatio-Temporal-Based Identification of Aggressive Behavior in Group Sheep.

In order to solve the problems of low efficiency and subjectivity of manual observation in the process of group-sheep-aggression detection, we propose a video streaming-based model for detecting aggressive behavior in group sheep. In the experiment, we collected videos of the sheep's daily routine and videos of the aggressive behavior of sheep in the sheep pen. Using the open-source software LabelImg, we labeled the data with bounding boxes. Firstly, the YOLOv5 detects all sheep in each frame of the video and outputs the coordinates information. Secondly, we sort the sheep's coordinates using a sheep tracking heuristic proposed in this paper. Finally, the sorted data are fed into an LSTM framework to predict the occurrence of aggression. To optimize the model's parameters, we analyze the confidence, batch size and skipping frame. The best-performing model from our experiments has 93.38% Precision and 91.86% Recall. Additionally, we compare our video streaming-based model with image-based models for detecting aggression in group sheep. In sheep aggression, the video stream detection model can solve the false detection phenomenon caused by head impact feature occlusion of aggressive sheep in the image detection model.

A Method to Predict CO2 Mass Concentration in Sheep Barns Based on the RF-PSO-LSTM Model.

In large-scale meat sheep farming, high CO2 concentrations in sheep sheds can lead to stress and harm the healthy growth of meat sheep, so a timely and accurate understanding of the trend of CO2 concentration and early regulation are essential to ensure the environmental safety of sheep sheds and the welfare of meat sheep. In order to accurately understand and regulate CO2 concentrations in sheep barns, we propose a prediction method based on the RF-PSO-LSTM model. The approach we propose has four main parts. First, to address the problems of data packet loss, distortion, singular values, and differences in the magnitude of the ambient air quality data collected from sheep sheds, we performed data preprocessing using mean smoothing, linear interpolation, and data normalization. Second, to address the problems of many types of ambient air quality parameters in sheep barns and possible redundancy or overlapping information, we used a random forests algorithm (RF) to screen and rank the features affecting CO2 mass concentration and selected the top four features (light intensity, air relative humidity, air temperature, and PM2.5 mass concentration) as the input of the model to eliminate redundant information among the variables. Then, to address the problem of manually debugging the hyperparameters of the long short-term memory model (LSTM), which is time consuming and labor intensive, as well as potentially subjective, we used a particle swarm optimization (PSO) algorithm to obtain the optimal combination of parameters, avoiding the disadvantages of selecting hyperparameters based on subjective experience. Finally, we trained the LSTM model using the optimized parameters obtained by the PSO algorithm to obtain the proposed model in this paper. The experimental results show that our proposed model has a root mean square error (RMSE) of 75.422 µg·m-3, a mean absolute error (MAE) of 51.839 µg·m-3, and a coefficient of determination (R2) of 0.992. The model prediction curve is close to the real curve and has a good prediction effect, which can be useful for the accurate prediction and regulation of CO2 concentration in sheep barns in large-scale meat sheep farming.

A Recognition Method of Ewe Estrus Crawling Behavior Based on Multi-Target Detection Layer Neural Network.

There are some problems with estrus detection in ewes in large-scale meat sheep farming: mainly, the manual detection method is labor-intensive and the contact sensor detection method causes stress reactions in ewes. To solve the abovementioned problems, we proposed a multi-objective detection layer neural network-based method for ewe estrus crawling behavior recognition. The approach we proposed has four main parts. Firstly, to address the problem of mismatch between our constructed ewe estrus dataset and the YOLO v3 anchor box size, we propose to obtain a new anchor box size by clustering the ewe estrus dataset using the K-means++ algorithm. Secondly, to address the problem of low model recognition precision caused by small imaging of distant ewes in the dataset, we added a 104 × 104 target detection layer, making the total target detection layer reach four layers, strengthening the model's ability to learn shallow information and improving the model's ability to detect small targets. Then, we added residual units to the residual structure of the model, so that the deep feature information of the model is not easily lost and further fused with the shallow feature information to speed up the training of the model. Finally, we maintain the aspect ratio of the images in the data-loading module of the model to reduce the distortion of the image information and increase the precision of the model. The experimental results show that our proposed model has 98.56% recognition precision, while recall was 98.04%, F1 value was 98%, mAP was 99.78%, FPS was 41 f/s, and model size was 276 M, which can meet the accurate and real-time recognition of ewe estrus behavior in large-scale meat sheep farming.

Discrimination of Minced Mutton Adulteration Based on Sized-Adaptive Online NIRS Information and 2D Conventional Neural Network.

Single-probe near-infrared spectroscopy (NIRS) usually uses different spectral information for modelling, but there are few reports about its influence on model performance. Based on sized-adaptive online NIRS information and the 2D conventional neural network (CNN), minced samples of pure mutton, pork, duck, and adulterated mutton with pork/duck were classified in this study. The influence of spectral information, convolution kernel sizes, and classifiers on model performance was separately explored. The results showed that spectral information had a great influence on model accuracy, of which the maximum difference could reach up to 12.06% for the same validation set. The convolution kernel sizes and classifiers had little effect on model accuracy but had significant influence on classification speed. For all datasets, the accuracy of the CNN model with mean spectral information per direction, extreme learning machine (ELM) classifier, and 7 × 7 convolution kernel was higher than 99.56%. Considering the rapidity and practicality, this study provides a fast and accurate method for online classification of adulterated mutton.

Experimental study on microstructure and mechanical properties of stalk for Glycyrrhiza Glabra.

In this paper, a year-old stalk of Glycyrrhiza glabra was used as the research object. The electronic universal testing machine was used to test the mechanical properties of shearing and bending. The microstructure of the stalk of Glycyrrhiza glabra was observed with a microscope. Mechanical test research indicated that the shearing process included an elastic phase, a yield phase, and a plastic deformation phase. The bending process was divided into elastic deformation stage and plastic deformation stage. In addition, the shearing force, shearing energy, bending force and bending energy all increased with the increase in diameter. As the water content increased, the shearing force and bending force decreased at first, reached the minimum when the water content was about 45%, and then had an upward trend. The shearing energy increased with the water content, and the bending energy, decreased with the water content. The two test factors were statistically significant for both shearing and bending properties. The microscopic test results showed that the phloem, fiber, and pith constitute the microstructure of the licorice stalk. The linear regression model could reflect the correlation between the cross-sectional area of each part and the shearing force and bending force (P < 0.05). Through analysis, it was concluded that the change of the cross-sectional area of the stalk microstructure had an important influence on the mechanical properties of shearing and bending. The results can provide theoretical basis for the design of Glycyrrhiza Glabra stalk harvesting, crushing and processing equipment.

Allicin Regulates Energy Homeostasis through Brown Adipose Tissue.

Brown adipose tissue (BAT) is a promising potential therapeutic target for the treatment of obesity and related metabolic diseases. Allicin, a natural product in garlic, has multiple biological and pharmacological functions. However, the role of allicin in the regulation of metabolic organs, particularly BAT activation, has not been well studied. Here, we show that allicin imparts a significant effect by inhibiting body weight gain, decreasing adiposity, maintaining glucose homeostasis, improving insulin resistance, and ameliorating hepatic steatosis in obese mice. These observations strongly correlate with the activation of BAT. Notably, allicin plays a role in BAT activation, which may partly contribute to the Sirt1-PGC1α-Tfam pathway. In addition, allicin can significantly increase the succinylation levels of UCP1 in BAT by inhibiting sirt5, whereas excess allicin induces autophagy/mitophagy and mitochondrial dysfunction. Thus, our findings point to allicin as a promising therapeutic approach for the treatment of obesity and metabolic disorders.

PCBP2 Modulates Neural Apoptosis and Astrocyte Proliferation After Spinal Cord Injury.

PCBP2, a member of the poly(C)-binding protein (PCBP) family, plays a pivotal role in posttranscriptional and translational regulation by interacting with single-stranded poly(C) motifs in target mRNAs. It is reported that several PCBP family members are involved in human malignancies. However, the distribution and function of PCBP2 in the central nervous system (CNS) remain unclear. In this study, we performed an acute spinal cord injury (SCI) model in adult rats and investigated the dynamic changes of PCBP2 expression in the spinal cord. Western blot and immunohistochemistry analysis revealed that PCBP2 presented in normal spinal cord. It gradually increased, reached a peak at 3 day, and then declined to basal levels at 14 days after SCI. We observed that the expression of PCBP2 was enhanced in the gray and white matter. Immunofluorescence indicated that PCBP2 was located in the neurons and astrocytes. Moreover, colocalization of PCBP2/active caspase-3 was detected in neurons, and colocalization of PCBP2/proliferating cell nuclear antigen was detected in astrocytes after SCI. These results indicated that PCBP2 might play an important role in neuronal apoptosis and astrocyte proliferation. In vitro, PCBP2-specific siRNA-transfected neuron showed significantly decrease of neuronal apoptosis and expression of cell cycle related proteins following glutamate stimulation. Meanwhile, PCBP2 knockdown also reduced primary astrocytes proliferation. All above indicated that PCBP2 might play a crucial role in cell proliferation and apoptosis. Collectively, our data suggested that PCBP2 might play important roles in CNS pathophysiology after SCI.

Expression of CDc6 after acute spinal cord injury in adult rats.

The cell division cycle 6 (CDc6) protein has been primarily investigated as a component of the pre-replicative complex for the initiation of DNA replication. Some studies have shown that CDc6 played a critical role in the development of human carcinoma. However, the expression and roles of CDc6 in the central nervous system remain unknown. We have performed an acute spinal cord injury (SCI) model in adult rats and investigated the dynamic changes of CDc6 expression in spinal cord. Western blot have found that CDc6 protein levels first significantly increase, reach a peak at day 3, and then gradually return to normal level at day 14 after SCI. Double immunofluorescence staining showed that CDc6 immunoreactivity was found in neurons, astrocytes, and microglia. Additionally, colocalization of CDc6/active caspase-3 has been detected in neurons and colocalization of CDc6/proliferating cell nuclear antigen has been detected in astrocytes and microglial. In vitro, CDc6 depletion by short interfering RNA inhibits astrocyte proliferation and reduces cyclin A and cyclin D1 protein levels. CDc6 knockdown also decreases neuronal apoptosis. We speculate that CDc6 might play crucial roles in CNS pathophysiology after SCI.

TCTP Expression After Rat Spinal Cord Injury: Implications for Astrocyte Proliferation and Migration.

Translationally controlled tumor protein (TCTP) is a ubiquitous and highly conserved protein which plays a role in cell proliferation and growth, apoptosis, and cell cycle regulation. However, its expression and function in spinal cord injury (SCI) are still unknown. Here, we demonstrated that expression of TCTP was dynamic changed after acute spinal cord injury. Our results showed that TCTP gradually increased, reached a peak at 3 day, and then declined to basal levels at 14 days after spinal cord injury. Upregulation of TCTP was accompanied with an increase in the levels of proliferation proteins such as PCNA. Immunofluorescent labeling also showed that TCTP located in astrocytes and traumatic SCI induced TCTP colocalizated with PCNA. These results indicated that TCTP might play an important role in astrocyte proliferation. To further probe the role of TCTP, TCTP-specific siRNA-transfected astrocytes showed significant decrease of primary astrocyte proliferation. Surprisingly, TCTP knockdown also reduced primary astrocyte migration, as the reorganization of microtubules and F-actin was disturbed after siRNA transfection. All above indicated that TCTP might play a crucial role in astrocyte proliferation and migration. Collectively, our data suggested that TCTP might play important roles in CNS pathophysiology after SCI.