Search

ObjectiveThe detection of lameness in dairy cows is an important issue that needs to be solved urgently in the process of large-scale dairy farming. Timely detection and effective intervention can reduce the culling rate of young dairy cows, which has important practical significance for increasing the milk production of dairy cows and improving the economic benefits of pastures. Due to the low efficiency and low degree of automation of traditional manual detection and contact sensor detection, the mainstream cow lameness detection method is mainly based on computer vision. The detection perspective of existing computer vision-based cow lameness detection methods is mainly side view, but the side view perspective has limitations that are difficult to eliminate. In the actual detection process, there are problems such as cows blocking each other and difficulty in deployment. The cow lameness detection method from the top view will not be difficult to use on the farm due to occlusion problems. The aim is to solve the occlusion problem under the side view.MethodsIn order to fully explore the movement undulations of the trunk of the cow and the movement information in the time dimension during the walking process of the cow, a cow lameness detection method was proposed from a top view based on fused spatiotemporal flow features. By analyzing the height changes of the lame cow in the depth video stream during movement, a spatial stream feature image sequence was constructed. By analyzing the instantaneous speed of the lame cow's body moving forward and swaying left and right when walking, optical flow was used to capture the instantaneous speed of the cow's movement, and a time flow characteristic image sequence was constructed. The spatial flow and time flow features were combined to construct a fused spatiotemporal flow feature image sequence. Different from traditional image classification tasks, the image sequence of cows walking includes features in both time and space dimensions. There would be a certain distinction between lame cows and non-lame cows due to their related postures and walking speeds when walking, so using video information analysis was feasible to characterize lameness as a behavior. The video action classification network could effectively model the spatiotemporal information in the input image sequence and output the corresponding category in the predicted result. The attention module Convolutional Block Attention Module (CBAM) was used to improve the PP-TSMv2 video action classification network and build the Cow-TSM cow lameness detection model. The CBAM module could perform channel weighting on different modes of cows, while paying attention to the weights between pixels to improve the model's feature extraction capabilities. Finally, cow lameness experiments were conducted on different modalities, different attention mechanisms, different video action classification networks and comparison of existing methods. The data was used for cow lameness included a total of 180 video streams of cows walking. Each video was decomposed into 100‒400 frames. The ratio of the number of video segments of lame cows and normal cows was 1:1. For the feature extraction of cow lameness from the top view, RGB images had less extractable information, so this work mainly used depth video streams.Results and DiscussionsIn this study, a total of 180 segments of cow image sequence data were acquired and processed, including 90 lame cows and 90 non-lame cows with a 1:1 ratio of video segments, and the prediction accuracy of automatic detection method for dairy cow lameness based on fusion of spatiotemporal stream features reaches 88.7%, the model size was 22 M, and the offline inference time was 0.046 s. The prediction accuracy of the common mainstream video action classification models TSM, PP-TSM, SlowFast and TimesFormer models on the data set of automatic detection method for dairy cow lameness based on fusion of spatiotemporal stream features reached 66.7%, 84.8%, 87.1% and 85.7%, respectively. The comprehensive performance of the improved Cow-TSM model in this paper was the most. At the same time, the recognition accuracy of the fused spatiotemporal flow feature image was improved by 12% and 4.1%, respectively, compared with the temporal mode and spatial mode, which proved the effectiveness of spatiotemporal flow fusion in this method. By conducting ablation experiments on different attention mechanisms of SE, SK, CA and CBAM, it was proved that the CBAM attention mechanism used has the best effect on the data of automatic detection method for dairy cow lameness based on fusion of spatiotemporal stream features. The channel attention in CBAM had a better effect on fused spatiotemporal flow data, and the spatial attention could also focus on the key spatial information in cow images. Finally, comparisons were made with existing lameness detection methods, including different methods from side view and top view. Compared with existing methods in the side-view perspective, the prediction accuracy of automatic detection method for dairy cow lameness based on fusion of spatiotemporal stream features was slightly lower, because the side-view perspective had more effective cow lameness characteristics. Compared with the method from the top view, a novel fused spatiotemporal flow feature detection method with better performance and practicability was proposed.ConclusionsThis method can avoid the occlusion problem of detecting lame cows from the side view, and at the same time improves the prediction accuracy of the detection method from the top view. It is of great significance for reducing the incidence of lameness in cows and improving the economic benefits of the pasture, and meets the needs of large-scale construction of the pasture.

ObjectiveReal-time monitoring of cow ruminant behavior is of paramount importance for promptly obtaining relevant information about cow health and predicting cow diseases. Currently, various strategies have been proposed for monitoring cow ruminant behavior, including video surveillance, sound recognition, and sensor monitoring methods. However, the application of edge device gives rise to the issue of inadequate real-time performance. To reduce the volume of data transmission and cloud computing workload while achieving real-time monitoring of dairy cow rumination behavior, a real-time monitoring method was proposed for cow ruminant behavior based on edge computing.MethodsAutonomously designed edge devices were utilized to collect and process six-axis acceleration signals from cows in real-time. Based on these six-axis data, two distinct strategies, federated edge intelligence and split edge intelligence, were investigated for the real-time recognition of cow ruminant behavior. Focused on the real-time recognition method for cow ruminant behavior leveraging federated edge intelligence, the CA-MobileNet v3 network was proposed by enhancing the MobileNet v3 network with a collaborative attention mechanism. Additionally, a federated edge intelligence model was designed utilizing the CA-MobileNet v3 network and the FedAvg federated aggregation algorithm. In the study on split edge intelligence, a split edge intelligence model named MobileNet-LSTM was designed by integrating the MobileNet v3 network with a fusion collaborative attention mechanism and the Bi-LSTM network.Results and DiscussionsThrough comparative experiments with MobileNet v3 and MobileNet-LSTM, the federated edge intelligence model based on CA-MobileNet v3 achieved an average Precision rate, Recall rate, F1-Score, Specificity, and Accuracy of 97.1%, 97.9%, 97.5%, 98.3%, and 98.2%, respectively, yielding the best recognition performance.ConclusionsIt is provided a real-time and effective method for monitoring cow ruminant behavior, and the proposed federated edge intelligence model can be applied in practical settings.

Pig welfare is closely related to the economical production of pig farms. With regard to pig welfare assessment, pig sounds are significant indicators, which can reflect the quality of the barn environment, the physical condition and the health of pigs. Therefore, pig sound analysis is of high priority and necessary. In this review, the relationship between pig sound and welfare was analyzed. Three kinds of pig sounds are closely related to pig welfare, including coughs, screams, and grunts. Subsequently, both wearable and non-contact sensors were briefly described in two aspects of advantages and disadvantages. Based on the advantages and feasibility of microphone sensors in contactless way, the existing techniques for processing pig sounds were elaborated and evaluated for further in-depth research from three aspects: sound recording and labeling, feature extraction, and sound classification. Finally, the challenges and opportunities of pig sound research were discussed for the ultimate purpose of precision livestock farming (PLF) in four ways: concerning sound monitoring technologies, individual pig welfare monitoring, commercial applications and pig farmers. In summary, it was found that most of the current researches on pig sound recognition tasks focused on the selection of classifiers and algorithm improvement, while fewer research was conducted on sound labeling and feature extraction. Meanwhile, pig sound recognition faces some challenging problems, involving the difficulty in obtaining the audio data from different pig growth stages and verifying the developed algorithms in a variety of pig farms. Overall, it is suggested that technologies involved in the automatic identification process should be explored in depth. In the future, strengthen cooperation among cross-disciplinary experts to promote the development and application of PLF is also nessary.

Somatic cell count detection is the daily work of dairy farms to monitor the health of cows. The feasibility of applying near-infrared spectroscopy to somatic cell count detection was researched in this paper. Milk samples with different somatic cell counts were collected and preprocessing methods were studied. Variable selection algorithm based on hybrid strategy and modelling method based on ensemble learning were explored for somatic cell count detection. Detection model was used to diagnose subclinical mastitis and the results showed that near-infrared spectroscopy could be a tool to realize rapid detection of somatic cell count in milk. [ABSTRACT FROM AUTHOR]

Simple Summary: Dairy cow behavior detection is of great significance for cattle health management. Through the detection of the four behaviors of dairy cows—standing, lying, eating, and drinking—we can gain valuable insights into the well-being of cows. For example, hoof disease can increase the amount of time a cow lies down, and digestive system issues can cause a decrease in food intake. Visual inspection of cow behavior can keep track of changes in cow behavior, and non-invasive detection can reduce cow discomfort and improve animal welfare. In this study, we employed computer vision-based deep learning techniques for the detection of cow behavior, and experimental results demonstrated its promising application in real farm settings. Dairy cow behavior carries important health information. Timely and accurate detection of behaviors such as drinking, feeding, lying, and standing is meaningful for monitoring individual cows and herd management. In this study, a model called Res-DenseYOLO is proposed for accurately detecting the individual behavior of dairy cows living in cowsheds. Specifically, a dense module was integrated into the backbone network of YOLOv5 to strengthen feature extraction for actual cowshed environments. A CoordAtt attention mechanism and SioU loss function were added to enhance feature learning and training convergence. Multi-scale detection heads were designed to improve small target detection. The model was trained and tested on 5516 images collected from monitoring videos of a dairy cowshed. The experimental results showed that the performance of Res-DenseYOLO proposed in this paper is better than that of Fast-RCNN, SSD, YOLOv4, YOLOv7, and other detection models in terms of precision, recall, and mAP metrics. Specifically, Res-DenseYOLO achieved 94.7% precision, 91.2% recall, and 96.3% mAP, outperforming the baseline YOLOv5 model by 0.7%, 4.2%, and 3.7%, respectively. This research developed a useful solution for real-time and accurate detection of dairy cow behaviors with video monitoring only, providing valuable behavioral data for animal welfare and production management. [ABSTRACT FROM AUTHOR]

Simple Summary: Our objective is to establish an in vitro rumen fermentation model that can dynamically simulate the fermentation process of various total mixed ration (TMR) diets in the rumen of dairy cows, enabling a quantitative investigation of rumen methane and rumen acetic acid concentrations. The models were assessed for their prediction accuracy and precision, while the independent verification experiments confirmed the models' generalization ability across different total mixed ration (TMR) ratios (C:F). These results show that in vitro rumen models constructed by machine learning methods can be used as a tool to quantify rumen fermentation parameters (methane and acetic acid) and guide the dietary structure optimization of dairy cows. The aim of this study is to identify an alternative approach for simulating the in vitro fermentation and quantifying the production of rumen methane and rumen acetic acid during the rumen fermentation process with different total mixed rations. In this experiment, dietary nutrient compositions (neutral detergent fiber (NDF), acid detergent fiber (ADF), crude protein (CP), and dry matter (DM)) were selected as input parameters to establish three prediction models for rumen fermentation parameters (methane and acetic acid): an artificial neural network model, a genetic algorithm-bp model, and a support vector machine model. The research findings show that the three models had similar simulation results that aligned with the measured data trends (R2 ≥ 0.83). Additionally, the root mean square errors (RMSEs) were ≤1.85 mL/g in the rumen methane model and ≤2.248 mmol/L in the rumen acetic acid model. Finally, this study also demonstrates the models' capacity for generalization through an independent verification experiment, as they effectively predicted outcomes even when significant trial factors were manipulated. These results suggest that machine learning-based in vitro rumen models can serve as a valuable tool for quantifying rumen fermentation parameters, guiding the optimization of dietary structures for dairy cows, rapidly screening methane-reducing feed options, and enhancing feeding efficiency. [ABSTRACT FROM AUTHOR]

To reveal the influence of freeze–thaw cycles (FTCs) on soil carbon and nitrogen changes, six typical soils in Northeast China were selected as the research objects to conduct a FTC simulation test in an artificial climate chamber. Three soil volumetric water contents (10%, 20%, 30%) and eight FTCs (0, 2, 4, 6, 8, 10, 15, 20) were set. The results showed that the soil organic carbon (SOC) and microbial biomass carbon (MBC) contents of different soil types under the FTCs initially exhibited a downward and then an upward trend, while the dissolved organic carbon (DOC) content exhibited an upward and then a downward trend. Otherwise, the fourth and sixth FTCs were the key points of change. The SOC, MBC and DOC contents in paddy fields were higher than those in dry fields, showing upward and then downward trends spatially from northeast to southwest. The SOC and MBC contents in each soil type were the highest at the 20% water content, and the DOC content gradually increased with increasing water content. The ammonium nitrogen (NH4+‐N) content in different soil types at different water contents under the FTCs showed an upward trend first, then a downward trend and finally an upward trend. The NH4+‐N content in paddy fields was higher than that in dry fields. The nitrate nitrogen (NO3‒‐N) content showed a downward trend first, then an upward trend and finally a downward trend. The NO3‒‐N content in dry fields was higher than that in paddy fields. The NH4+‐N contents in the three soil types on the Sanjiang Plain were significantly higher than those on the Songnen Plain. The NH4+‐N and NO3‒‐N contents showed upward trends with increasing water content, but the differences were not significant. The results have implications for the study of different types of soils and provide references for research on the mechanism of soil carbon and nitrogen transformation in typical farming areas in Northeast China. [ABSTRACT FROM AUTHOR]

Simple Summary: Methane and volatile fatty acids are important products of rumen fermentation in dairy cows. Quantitative research on them is of great significance for environmental protection and animal production. The aim of this study was to develop a prediction model using the stacking ensemble learning method and predict the production of rumen fermentation products based on the nutrient level of the diet. The results show that the stacking model has good performance in terms of prediction accuracy. The model proposed in this study can be used as a guideline to optimize diet compositions and improve feeding efficiency. Volatile fatty acids (VFAs) and methane are the main products of rumen fermentation. Quantitative studies of rumen fermentation parameters can be performed using in vitro techniques and machine learning methods. The currently proposed models suffer from poor generalization ability due to the small number of samples. In this study, a prediction model for rumen fermentation parameters (methane, acetic acid (AA), and propionic acid (PA)) of dairy cows is established using the stacking ensemble learning method and in vitro techniques. Four factors related to the nutrient level of total mixed rations (TMRs) are selected as inputs to the model: neutral detergent fiber (NDF), acid detergent fiber (ADF), crude protein (CP), and dry matter (DM). The comparison of the prediction results of the stacking model and base learners shows that the stacking ensemble learning method has better prediction results for rumen methane (coefficient of determination ( R 2 ) = 0.928, root mean square error (RMSE) = 0.968 mL/g), AA ( R 2 = 0.888, RMSE = 1.975 mmol/L) and PA ( R 2 = 0.924, RMSE = 0.74 mmol/L). And the stacking model simulates the variation of methane and VFAs in relation to the dietary fiber content. To demonstrate the robustness of the model in the case of small samples, an independent validation experiment was conducted. The stacking model successfully simulated the transition of rumen fermentation type and the change of methane content under different concentrate-to-forage (C:F) ratios of TMR. These results suggest that the rumen fermentation parameter prediction model can be used as a decision-making basis for the optimization of dairy cow diet compositions, rapid screening of methane emission reduction, feed beneficial to dairy cow health, and improvement of feed utilization. [ABSTRACT FROM AUTHOR]

The precise detection of pig cough is a crucial step for establishing an early warning system for pig respiratory diseases. With regard to high precision pig cough recognition, feature extraction and selection are of importance. However, few studies have investigated both acoustic and visual features of pig vocalisations as input features. In this paper, we proposed a novel feature fusion method which fusing acoustic and visual features to achieve an enhanced pig cough recognition rate. We firstly extracted acoustic features from audio signals, including root-mean-square energy (RMS), mel-frequency cepstral coefficients (MFCCs), zero-crossing rates (ZCRs), spectral centroid, spectral roll-off, spectral flatness, spectral bandwidth and chroma. Then, constant-Q transform (CQT) spectrograms were employed to extract visual features involving local binary pattern (LBP) and histogram of gradient (HOG). Subsequently, a hybrid feature set was created by combining acoustic and visual features. In this stage, Pearson correlation coefficient (PCC), recursive feature elimination based on random forest (RF-RFE) and principal component analysis (PCA) were exploited for dimensionality reduction. Finally, support vector machine (SVM), random forest (RF) and k-nearest neighbours (KNN) classifiers were used to conduct a performance evaluation. It is shown that the fused acoustic features (Acoustic) combined with LBP and HOG (A-LH) achieved 96.45% pig cough accuracy. The results reveal that the fusion feature set outperforms acoustic and visual features alone. [Display omitted] • Both acoustic and visual features were investigated for pig cough. • A hybrid feature vector created by early feature fusion enhanced recognition performance of pig cough. • Feature selection and extraction were employed to choose the optimal feature set. • The proposed method reached an accuracy of 96.45%. [ABSTRACT FROM AUTHOR]

A specific variable selection method was proposed based on a three-step hybrid strategy for near-infrared spectral analysis. By analyzing functions of each step and characteristics of various variable selection methods, synergy interval partial least squares, iterative variable subset optimization, and bootstrapping soft shrinkage were chosen for three steps. To test the effect of the three-step hybrid method, it was applied to corn and soil spectral data and compared to other common methods. Results for oil content in corn data showed that the three-step hybrid variable selection method selected 1% variables of full spectrum, calibration determination coefficient, and prediction determination coefficient reached 0.998 and 0.993 where the explained variance was increased by 27.30%. It could effectively extract variables related to the tested substance and provide a new variable selection method for near-infrared spectral analysis. [ABSTRACT FROM AUTHOR]

Detection of additives in milk is important, especially preservatives. Potassium sorbate was taken as an example to study the feasibility of hyperspectral imaging as a rapid detection tool for preservatives in milk. Samples with different concentrations of potassium sorbate were divided into four groups. Pretreatment and variable selection methods were studied based on the support vector machine model. The model with standard normalized variable pretreatment and competitive adaptive reweighted sampling variable selection had the best performance. Testing set accuracy for different groups from low concentration to high concentration were 92.16%, 95.7%, 99.46%, and 98.33%. Hyperspectral imaging can be a rapid detection tool for potassium sorbate in milk. [ABSTRACT FROM AUTHOR]

With the development of computer and IT technologies, enterprise management has gradually become information-based management. Moreover, due to poor technical competence and non-uniform management, most breeding enterprises show a lack of organisation in data collection and management. In addition, low levels of efficiency result in increasing production costs. This paper adopts ‘struts2’ in order to construct an information-based management system for standardised and normalised management within the process of production in beef cattle breeding enterprises. We present a radio-frequency identification system by studying multiple-tag anti-collision via a dynamic grouping ALOHA algorithm. This algorithm is based on the existing ALOHA algorithm and uses an improved packet dynamic of this algorithm, which is characterised by a high-throughput rate. This new algorithm can reach a throughput 42% higher than that of the general ALOHA algorithm. With a change in the number of tags, the system throughput is relatively stable. [ABSTRACT FROM AUTHOR]

In Hei Longjiang Province of China, ten million tons of soybean straws are produced every year, most of which are burned or discarded. The comprehensive utilization rate is less than 5 %. However, as a kind of high-quality raw material resources, the soybean straw is the main material when producing fuel ethanol and biodiesel. The traditional chemical detection technology was always applied to test the quality of straws' internal components, which needs long time and high cost. Therefore, this research adopted near-infrared spectroscopy technology to establish models to achieve rapid detection of straw's internal components. One hundred and fifty-two samples of straw were collected within Heilongjiang Province, and the main ingredients, lignin and hemicellulose, were chosen as the research objects. K-stone method is used to divide into calibration and validation sets. The correlation coefficient is adopted to select and validate characteristic bands. After removal of the abnormal sample by concentration of residual method, the emphasis is put on the effect of removal of spectrum noise by applying the wavelet transform. The experimental results are that the model has good stability under the full spectrum band 4000-12,000 cm. After the removal of 3 lignin and 3 hemicellulose samples, respectively, the R of calibration set of lignin and hemicellulose models increased significantly, from 0.5836436 and 0.4994598 to 0.6994097 and 0.6943559, respectively. However, after the 5-layer decomposition of DB2 wavelet, the R increased to 0.8075574 and 0.8214309 separately. The validation set's root mean square error prediction (RMSEP) fell from 0.7738772 and 0.3069899 to 0.5979685 and 0.2761462. After the conversion, the relative standard deviations (RSD) are 1.92 and 1.86 %, respectively. Unknown samples can be real-time predicted in short times after building the model, and the prediction process needs only 1960s. The experiments show that it is feasible to employ near-infrared spectroscopy method for rapid detection of straw components, which provides a new method to detect the straw ingredients rapidly in the future. [ABSTRACT FROM AUTHOR]