Analysis and Comparison of New-Born Calf Standing and Lying Time Based on Deep Learning.

Standing and lying are the fundamental behaviours of quadrupedal animals, and the ratio of their durations is a significant indicator of calf health. In this study, we proposed a computer vision method for non-invasively monitoring of calves' behaviours. Cameras were deployed at four viewpoints to monitor six calves on six consecutive days. YOLOv8n was trained to detect standing and lying calves. Daily behavioural budget was then summarised and analysed based on automatic inference on untrained data. The results show a mean average precision of 0.995 and an average inference speed of 333 frames per second. The maximum error in the estimated daily standing and lying time for a total of 8 calf-days is less than 14 min. Calves with diarrhoea had about 2 h more daily lying time (p < 0.002), 2.65 more daily lying bouts (p < 0.049), and 4.3 min less daily lying bout duration (p = 0.5) compared to healthy calves. The proposed method can help in understanding calves' health status based on automatically measured standing and lying time, thereby improving their welfare and management on the farm.

Classification models for Tobacco Mosaic Virus and Potato Virus Y using hyperspectral and machine learning techniques.

Tobacco Mosaic Virus (TMV) and Potato Virus Y (PVY) pose significant threats to crop production. Non-destructive and accurate surveillance is crucial to effective disease control. In this study, we propose the adoption of hyperspectral and machine learning technologies to discern the type and severity of tobacco leaves affected by PVY and TMV infection. Initially, we applied three preprocessing methods - Multivariate Scattering Correction (MSC), Standard Normal Variate (SNV), and Savitzky-Golay smoothing filter (SavGol) - to corrected the leaf full-length spectral sheet data (350-2500nm). Subsequently, we employed two classifiers, support vector machine (SVM) and random forest (RF), to establish supervised classification models, including binary classification models (healthy/diseased leaves or PVY/TMV infected leaves) and six-class classification models (healthy and various severity levels of diseased leaves). Based on the core evaluation index, our models achieved accuracies in the range of 91-100% in the binary classification. In general, SVM demonstrated superior performance compared to RF in distinguishing leaves infected with PVY and TMV. Different combinations of preprocessing methods and classifiers have distinct capabilities in the six-class classification. Notably, SavGol united with SVM gave an excellent performance in the identification of different PVY severity levels with 98.1% average precision, and also achieved a high recognition rate (96.2%) in the different TMV severity level classifications. The results further highlighted that the effective wavelengths captured by SVM, 700nm and 1800nm, would be valuable for estimating disease severity levels. Our study underscores the efficacy of integrating hyperspectral technology and machine learning, showcasing their potential for accurate and non-destructive monitoring of plant viral diseases.

Grazing Sheep Behaviour Recognition Based on Improved YOLOV5.

Fundamental sheep behaviours, for instance, walking, standing, and lying, can be closely associated with their physiological health. However, monitoring sheep in grazing land is complex as limited range, varied weather, and diverse outdoor lighting conditions, with the need to accurately recognise sheep behaviour in free range situations, are critical problems that must be addressed. This study proposes an enhanced sheep behaviour recognition algorithm based on the You Only Look Once Version 5 (YOLOV5) model. The algorithm investigates the effect of different shooting methodologies on sheep behaviour recognition and the model's generalisation ability under different environmental conditions and, at the same time, provides an overview of the design for the real-time recognition system. The initial stage of the research involves the construction of sheep behaviour datasets using two shooting methods. Subsequently, the YOLOV5 model was executed, resulting in better performance on the corresponding datasets, with an average accuracy of over 90% for the three classifications. Next, cross-validation was employed to verify the model's generalisation ability, and the results indicated the handheld camera-trained model had better generalisation ability. Furthermore, the enhanced YOLOV5 model with the addition of an attention mechanism module before feature extraction results displayed a mAP@0.5 of 91.8% which represented an increase of 1.7%. Lastly, a cloud-based structure was proposed with the Real-Time Messaging Protocol (RTMP) to push the video stream for real-time behaviour recognition to apply the model in a practical situation. Conclusively, this study proposes an improved YOLOV5 algorithm for sheep behaviour recognition in pasture scenarios. The model can effectively detect sheep's daily behaviour for precision livestock management, promoting modern husbandry development.

Research on Six-Axis Sensor-Based Step-Counting Algorithm for Grazing Sheep.

Step counting is an effective method to assess the activity level of grazing sheep. However, existing step-counting algorithms have limited adaptability to sheep walking patterns and fail to eliminate false step counts caused by abnormal behaviors. Therefore, this study proposed a step-counting algorithm based on behavior classification designed explicitly for grazing sheep. The algorithm utilized regional peak detection and peak-to-valley difference detection to identify running and leg-shaking behaviors in sheep. It distinguished leg shaking from brisk walking behaviors through variance feature analysis. Based on the recognition results, different step-counting strategies were employed. When running behavior was detected, the algorithm divided the sampling window by the baseline step frequency and multiplied it by a scaling factor to accurately calculate the number of steps for running. No step counting was performed for leg-shaking behavior. For other behaviors, such as slow and brisk walking, a window peak detection algorithm was used for step counting. Experimental results demonstrate a significant improvement in the accuracy of the proposed algorithm compared to the peak detection-based method. In addition, the experimental results demonstrated that the average calculation error of the proposed algorithm in this study was 6.244%, while the average error of the peak detection-based step-counting algorithm was 17.556%. This indicates a significant improvement in the accuracy of the proposed algorithm compared to the peak detection method.

A new potential risk: The impacts of Klebsiella pneumoniae infection on the histopathology, transcriptome and metagenome of Chinese mitten crab (Eriocheir sinensis).

Klebsiella pneumoniae is a common conditional pathogen found in natural soil water sources and vegetation and can infect invertebrates, vertebrates, and plants. In this study, we isolated K. pneumoniae from the hepatopancreas of the Chinese mitten crab (Eriocheir sinensis) for the first time and then we analysed its effects of on the histopathological changes, the transcriptome of the hepatopancreas, and the gut microbiota of this crab species. The findings of this study showed that K. pneumoniae infection has led to significant structural changes in the hepatopancreas, such as the production of vacuolated tissue structures, disorganized cell arrangement, and lysis of some hepatopancreatic cells. Also, the infection caused activation of the antioxidant-related enzymes such as SOD and CAT by inducing oxidative stress. The transcriptome of the hepatopancreas identified 10,940 differentially expressed genes (DEGs) in the susceptible (SG) groups and control (CG) groups, and 8495 DEGs in the SG groups and anti-infective (AI) groups. The KEGG pathway revealed upregulated DEGs caused by K. pneumoniae infection that involved in the immune response and apoptotic functional pathways, and also downregulated DEGs involved in the digestive absorption, metabolic, and biosynthetic signaling pathways. Meanwhile, metagenics sequencing revealed that at the phylum, class, order, family, and genus levels, K. pneumoniae infection altered the composition of the gut microbiota of E. sinensis, through increasing the abundance of Prolixibacteraceae, Enterobacterales, and Roseimarinus and decreasing the abundance of Alphaproteobacteria. The flora structure has also been changed between the SG and AI groups, with the abundance of Firmicutes, Erysipelotrichales, and Erysipelotrichaceae that were significantly decreased in the SG groups than in the AI groups. But, the abundance of Acinetobacter was considerably higher than in the AI group. In summary, K. pneumoniae infection induced oxidative stress in E. sinensis, triggered changes in immune-related gene expression, and caused structural changes in the gut microbiota. This study provides data to support the analysis of bacterial infection probes in several crustacean species.

Behavior Classification and Analysis of Grazing Sheep on Pasture with Different Sward Surface Heights Using Machine Learning.

Behavior classification and recognition of sheep are useful for monitoring their health and productivity. The automatic behavior classification of sheep by using wearable devices based on IMU sensors is becoming more prevalent, but there is little consensus on data processing and classification methods. Most classification accuracy tests are conducted on extracted behavior segments, with only a few trained models applied to continuous behavior segments classification. The aim of this study was to evaluate the performance of multiple combinations of algorithms (extreme learning machine (ELM), AdaBoost, stacking), time windows (3, 5 and 11 s) and sensor data (three-axis accelerometer (T-acc), three-axis gyroscope (T-gyr), and T-acc and T-gyr) for grazing sheep behavior classification on continuous behavior segments. The optimal combination was a stacking model at the 3 s time window using T-acc and T-gyr data, which had an accuracy of 87.8% and a Kappa value of 0.836. It was applied to the behavior classification of three grazing sheep continuously for a total of 67.5 h on pasture with three different sward surface heights (SSH). The results revealed that the three sheep had the longest walking, grazing and resting times on the short, medium and tall SHH, respectively. These findings can be used to support grazing sheep management and the evaluation of production performance.

Classification and Analysis of Multiple Cattle Unitary Behaviors and Movements Based on Machine Learning Methods.

The behavior of livestock on farms is the primary representation of animal welfare, health conditions, and social interactions to determine whether they are healthy or not. The objective of this study was to propose a framework based on inertial measurement unit (IMU) data from 10 dairy cows to classify unitary behaviors such as feeding, standing, lying, ruminating-standing, ruminating-lying, and walking, and identify movements during unitary behaviors. Classification performance was investigated for three machine learning algorithms (K-nearest neighbors (KNN), random forest (RF), and extreme boosting algorithm (XGBoost)) in four time windows (5, 10, 30, and 60 s). Furthermore, feed tossing, rolling biting, and chewing in the correctly classified feeding segments were analyzed by the magnitude of the acceleration. The results revealed that the XGBoost had the highest performance in the 60 s time window with an average F1 score of 94% for the six unitary behavior classes. The F1 score of movements is 78% (feed tossing), 87% (rolling biting), and 87% (chewing). This framework offers a possibility to explore more detailed movements based on the unitary behavior classification.

Evaluation of the Best Region for Measuring Eye Temperature in Dairy Cows Exposed to Heat Stress.

Eye temperature (ET) has long been used for predicting or indicating heat stress in dairy cows. However, the region of interest (ROI) and temperature parameter of the eye have not been standardized and various options were adopted by previous studies. The aim of this study was to determine the best ROI for measuring ET as the predictor of heat stress in dairy cows in consideration of repeatability and validity. The ET of 40 lactating Holstein dairy cows was measured using infrared thermography. The mean and maximum temperature of five ROIs-medial canthus (MC), lateral canthus, eyeball, whole eye (WE), and lacrimal sac (LS)-were manually captured. The results show that the ET of left eyes was slightly higher than that of right eyes. The ET taken in MC, WE, and LS within 2 min had a moderate to substantial repeatability. The maximum temperature obtained at the LS had the highest correlation coefficients with respiration rate and core body temperature (all p < 0.001). Therefore, the maximum temperature of LS should be considered by future studies that want to use ET as the predictor or indicator of heat stress in dairy cows.

Evaluation of environmental and physiological indicators in lactating dairy cows exposed to heat stress.

This study aimed to better understand environmental heat stress and physiological heat strain indicators in lactating dairy cows. Sixteen heat stress indicators were derived using microenvironmental parameters that were measured at the surrounding of cows and at usual fixed locations in the barn by using handheld and fixed subarea sensors, respectively. Twenty high-producing Holstein-Friesian dairy cows (> 30.0 kg/day) from an intensive dairy farm were chosen to measure respiration rate (RR), vaginal temperature (VT), and body surface temperature of forehead (FT), eye (ET), and muzzle (MT). Our results show that microenvironments measured by the handheld sensor were slightly warmer and drier than those measured by the fixed subarea sensor; however, their derived heat stress indicators correlated equally well with physiological indicators. Interestingly, ambient temperature (Ta) had the highest correlations with physiological indicators and the best classification performance in recognizing actual heat strain state. Using segmented mixed models, the determined Ta thresholds for maximum FT, mean FT, RR, maximum ET, mean ET, VT, mean MT, and maximum MT were 24.1 °C, 24.2 °C, 24.4 °C, 24.6 °C, 24.6 °C, 25.3 °C, 25.4 °C, and 25.4 °C, respectively. Thus, we concluded that the fixed subarea sensor is a reliable tool for measuring cows' microenvironments; Ta is an appropriate heat stress indicator; FT, RR, and ET are good early heat strain indicators. The results of this study could be helpful for dairy practitioners in a similar intensive setting to detect and respond to heat strain with more appropriate indicators.

A new insight to characterize immunomodulation based on hepatopancreatic transcriptome and humoral immune factor analysis of the Cherax quadricarinatus infected with Aeromonas veronii.

Cherax quadricarinatus is a type of large freshwater crayfish that is characterized by rapid growth and formidable adaptability. It has also been widely cultured and studied as a model organism. Aeromonas veronii is the dominant pathogen in aquatic environments and the primary threat to aquaculture's economic stability. To better understand the interactions between C. quadricarinatus and A. veronii, high-throughput RNA sequencing of the C. quadricarinatus hepatopancreas was carried out on a control group, susceptible group (6 h after infection), and resistant group (48 h after infection). A total of 65,850,929 genes were obtained. Compared with the control group, 2616 genes were up-regulated and 1551 genes were down-regulated in the susceptible group; while 1488 genes were up-regulated and 1712 genes were down-regulated in the resistant group. GO and KEGG analysis showed that these differentially expressed genes (DEGs) were associated with multiple immune pathways, including Toll-like receptors (TLRs), antigen processing and presentation, NOD-like receptor signaling pathway, phagosome, lysosome, JAK-STAT signaling pathway. qRT-PCR showed that infection by A. veronii changed the expression pattern of the serine proteinase inhibitor (SPI), crustacean hyperglycemic hormone (CHH), anti-lipopolysaccharide factor (ALF), and extracellular copper/zinc superoxide dismutase (SOD1), all of which were significantly higher than in the control group up to 48 h after infection. In addition, detection of superoxide dismutase (SOD), catalase (CAT), lysozyme (LZM), and phenoloxidase (PO) activity, as well as ceruloplasmin (CP) concentration at different times after infection showed diverse trends. Furthermore, pathological sections obtained 24 h after infection show lesions on the hepatopancreas and intestinal tissues caused by A. veronii. The results of this study provide a foundation for analyzing the immune mechanism of C. quadricarinatus infected with A. veronii at the transcriptional level and a theoretical basis for screening disease-resistant individuals to ensure healthy economic development of the aquatic industry.

Hepatopancreatic transcriptome analysis and humoral immune factor assays in red claw crayfish (Cherax quadricarinatus) provide insight into innate immunomodulation under Vibrio parahaemolyticus infection.

Red claw crayfish (Cherax quadricarinatus) is an economically and nutritionally important specie. We aimed to assess the immunostimulatory response to C. quadricarinatus infection with Vibrio parahaemolyticus. After determining the LD50, we infected C. quadricarinatus and examined the differential expression profiles of hepatopancreas transcriptional genes, and observed the temporal changes of hepatopancreas pathological sections and serum immunoenzymatic activities at different time points to reveal the infection mechanism of V. parahaemolyticus and the immune detoxification mechanism of the organism. The results showed that V. parahaemolyticus infection with C. quadricarinatus caused hepatopancreas injury and the immune enzyme activity of the organism changed with time delay. Transcriptome analysis of 47,338 single genes obtained by RNA sequencing and de nove transcriptome assembly identified a total of 3678 differentially expressed genes (P < 0.05) in the expression profiles of susceptible and normal animals for comparative analysis, and 2516 differentially expressed genes (P < 0.05) in the expression profiles of asymptomatic (infection-resistant) and normal animals. GO and KEGG and analyses revealed immune-related pathways under V. parahaemolyticus infection, including Vibrio cholerae infection, phagosome, lysozyme, oxidative phosphorylation, antigen processing and presentation, apoptosis, and Toll-like receptor signaling, as well as significant differences in the expression patterns of related immune genes at different times (P < 0.05). These new experimental results reveal the molecular response of the hepatopancreas to V. parahaemolyticus infection and the corresponding adaptive mechanisms, thus further revealing the pathogenesis due to bacterial infection in the aquatic environment, and providing a reference for further understanding of microbial-host interactions in aquatic systems.

Recent Advances on Early Detection of Heat Strain in Dairy Cows Using Animal-Based Indicators: A Review.

In pursuit of precision livestock farming, the real-time measurement for heat strain-related data has been more and more valued. Efforts have been made recently to use more sensitive physiological indicators with the hope to better inform decision-making in heat abatement in dairy farms. To get an insight into the early detection of heat strain in dairy cows, the present review focuses on the recent efforts developing early detection methods of heat strain in dairy cows based on body temperatures and respiratory dynamics. For every candidate animal-based indicator, state-of-the-art measurement methods and existing thresholds were summarized. Body surface temperature and respiration rate were concluded to be the best early indicators of heat strain due to their high feasibility of measurement and sensitivity to heat stress. Future studies should customize heat strain thresholds according to different internal and external factors that have an impact on the sensitivity to heat stress. Wearable devices are most promising to achieve real-time measurement in practical dairy farms. Combined with internet of things technologies, a comprehensive strategy based on both animal- and environment-based indicators is expected to increase the precision of early detection of heat strain in dairy cows.

Ag-YOLO: A Real-Time Low-Cost Detector for Precise Spraying With Case Study of Palms.

To date, unmanned aerial vehicles (UAVs), commonly known as drones, have been widely used in precision agriculture (PA) for crop monitoring and crop spraying, allowing farmers to increase the efficiency of the farming process, meanwhile reducing environmental impact. However, to spray pesticides effectively and safely to the trees in small fields or rugged environments, such as mountain areas, is still an open question. To bridge this gap, in this study, an onboard computer vision (CV) component for UAVs is developed. The system is low-cost, flexible, and energy-effective. It consists of two parts, the hardware part is an Intel Neural Compute Stick 2 (NCS2), and the software part is an object detection algorithm named the Ag-YOLO. The NCS2 is 18 grams in weight, 1.5 watts in energy consumption, and costs about $66. The proposed model Ag-YOLO is inspired by You Only Look Once (YOLO), trained and tested with aerial images of areca plantations, and shows high accuracy (F1 score = 0.9205) and high speed [36.5 frames per second (fps)] on the target hardware. Compared to YOLOv3-Tiny, Ag-YOLO is 2× faster while using 12× fewer parameters. Based on this study, crop monitoring and crop spraying can be synchronized into one process, so that smart and precise spraying can be performed.

Transcriptome analysis of the Macrobrachium nipponense hepatopancreas provides insights into immunoregulation under Aeromonas veronii infection.

The oriental river prawn Macrobrachium nipponense is a commercially important freshwater shrimp that is widely farmed in China. Aeromonas veronii is a conditional pathogen of farmed shrimp, which has caused huge economic losses to the industry. Therefore, there is urgency to study the host-pathogen interactions between M. nipponense and A. veronii to screen individuals with antimicrobial resistance. In this study, we examined the hepatopancreas of moribund M. nipponense infected with A. veronii and healthy individuals at both the histopathological and transcriptomic levels. We showed that A. veronii infection resulted in tubular necrosis of the M. nipponense hepatopancreas. Such changes likely affect assimilation, storage, and excretion by the hepatopancreas, which could ultimately affect the survival and growth of infected individuals. Among the 61,345 unigenes obtained through RNA sequencing and de novo transcriptome assembly, 232 were differentially expressed between the two groups. KEGG and GO analyses revealed that these differentially expressed genes were implicated in pathways, including PPAR, PI3K/AKT, and AMPK signaling. The results of this study will contribute to an analysis of the immune response of M. nipponense to A. veronii infection at the transcriptomic level. Furthermore, the RNA-seq data generated here provide an important genomic resource for research on M. nipponense in the absence of a reference genome.