Search

• Spatiotemporal distribution of livestock behavior was monitored using multi-modal data. • Multi-source data fusion outperformed single-source data in multi-behavior classification. • The CNN-LSTM model was able to classify multi-behavior with higher accuracy. • 1HZ of multi-source fusion data still achieved reasonable classification accuracy. Monitoring multiple behavioral patterns and grazing trajectories of individual sheep can provide valuable information for various aspects of livestock production. The emergence of low-cost miniature sensors, coupled with the continuous advancement of deep learning technologies, has ushered in a new generation of intelligent solutions for precision livestock farming. This study aims to explore the deployment methods of motion sensors, selection of data collection frequencies, and choice of deep learning algorithms to provide accurate classification of multiple behaviors in grazing sheep. Based on this, in conjunction with the acquired location information, the goal is to comprehend the spatiotemporal distribution of grazing sheep behaviors. Devices capable of collecting Inertial Measurement Unit (IMU) and location data were attached to the jaw, neck, and hind leg of sheep. Four datasets were created using IMU data with a frequency of 20 Hz and a 5 s time window from different positions (neck, neck & leg, jaw, jaw & leg). Two deep learning models, Convolutional Neural Network (CNN) - Long Short Term Memory (LSTM) and Temporal Convolutional Network (TCN)-Transformer, were employed to classify six grazing sheep behaviors: walking, standing, grazing, lying, standing-ruminating, and lying-ruminating. The results indicate that by fusing data from the neck- and leg-mounted devices and utilizing the CNN-LSTM model, the accuracy reached the highest at 99.3 %. Furthermore, a comparison was made regarding the behavior classification accuracy of this fused data at different IMU data frequencies (20, 10, 5, and 1 Hz). It was found that even when the data frequency was reduced to 1 Hz, the classification accuracy for the six sheep behaviors still exceeded 96 %. Additionally, the trained model with the highest accuracy was applied to monitoring grazing sheep behavior under two different management procedures. Further analysis of the time budgets of sheep behavior revealed differences in the durations of behaviors under different management procedures. For extensively grazing sheep, location information was also monitored and combined with behavior classification results to generate the spatiotemporal distribution of sheep behavior. The technologies presented are important for gaining further insights into the health status of grazing livestock and grassland, thereby enhancing grazing management practices by informing grazing choices and optimizing grassland utilization. [ABSTRACT FROM AUTHOR]

Simple Summary: The monitoring and analysis of sheep behavior can reflect their welfare and health, which is beneficial for grazing management. For automatic classification and the continuous monitoring of grazing sheep behavior, wearable devices based on inertial measurement unit (IMU) sensors are important. The accuracy of different machine learning algorithms was compared, and the best one was used for the continuous monitoring and behavior classification of three grazing sheep on pasture with three different sward surface heights. The results showed that the algorithm automatically monitored the behavior of grazing sheep individuals and quantified the time of each behavior. 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. [ABSTRACT FROM AUTHOR]

In this paper, we consider the problem of multi-class image classification when the classes behaviour has a low rank structure. That is, classes can be embedded into a low dimensional space. Traditional multi-class classification algorithms usually use nuclear norm to approximate the rank of the weight matrix. Considering the limited ability of the nuclear norm for the accurate approximation, we propose a new scalable large scale multi-class classification algorithm by using the recently proposed truncated nuclear norm as a better surrogate of the rank operator of matrices along with multinomial logisitic loss. To solve the non-convex and non-smooth optimization problem, we further develop an efficient iterative procedure. In each iteration, by lifting the non-smooth convex subproblem into an infinite dimensional ℓ 1 norm regularized problem, a simple and efficient accelerated coordinate descent algorithm is applied to find the optimal solution. We conduct a series of evaluations on several public large scale image datasets, where the experimental results show the encouraging improvement of classification accuracy of the proposed algorithm in comparison with the state-of-the-art multi-class classification algorithms. [ABSTRACT FROM AUTHOR]

Abstract: An effective lubrication can significantly reduce wear of metal-on-metal artificial hip joints. The improvement of the lubrication can be achieved through the optimisation of the bearing geometry in terms of a small clearance and/or the structural support such as a polyethylene backing underneath a metallic bearing in a sandwich acetabular cup form. The separate effects of these two factors on fluid film lubrication of 28mm diameter metal-on-metal total hip joints under walking conditions were numerically investigated in this paper. The results show that a larger lubricant film due to the polyethylene backing can be significantly enhanced by the transient squeeze-film action, particularly during the stance phase, and a similar lubricant film can be developed for both the monolithic cup relying on the smaller clearance and the sandwich cup benefiting from the polyethylene backing. Both cup systems can function in a wide range of lubrication regimes, covering both mixed and fluid film, under the current design and manufacture conditions. [Copyright &y& Elsevier]

Simple Summary: In the process of calf rearing, it is inevitable to encounter issues of illness and death among calves. Often, due to the inability to detect sicknesses such as diarrhoea in a timely fashion, these sicknesses lead to the calves' demise. This research starts from the practical application needs, and proposes the development of a monitoring system using deep learning technology to monitor the daily standing and lying behaviour of calves to predict their condition and adaptation to the environment. By analysing the standing and lying time of calves, the system can provide early warnings about calves' condition and health status. This research helps to promptly grasp calves' condition and growth status, thereby improving their welfare and management, enhancing the health condition of reared calves, ensuring the quality and safety of meat and milk, and reducing production costs. This research method also offers a new idea for the construction of smart ranches, as the construction of precision and smart ranches is not only a demand of consumers but also an inevitable direction for the development of the breeding industry. 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. [ABSTRACT FROM AUTHOR]

Model fine-tuning is a widely used transfer learning approach in person Re-identification (ReID) applications, which fine-tuning a pre-trained feature extraction model into the target scenario instead of training a model from scratch. It is challenging due to the significant variations inside the target scenario, e.g., different camera viewpoint, illumination changes, and occlusion. These variations result in a gap between each mini-batch’s distribution and the whole dataset’s distribution when using mini-batch training. In this paper, we study model fine-tuning from the perspective of the aggregation and utilization of the dataset’s global information when using mini-batch training. Specifically, we introduce a novel network structure called Batch-related Convolutional Cell (BConv-Cell), which progressively collects the dataset’s global information into a latent state and uses it to rectify the extracted feature. Based on BConv-Cells, we further proposed the Progressive Transfer Learning (PTL) method to facilitate the model fine-tuning process by jointly optimizing BConv-Cells and the pre-trained ReID model. Empirical experiments show that our proposal can greatly improve the ReID model’s performance on MSMT17, Market-1501, CUHK03, and DukeMTMC-reID datasets. Moreover, we extend our proposal to the general image classification task. The experiments in several image classification benchmark datasets demonstrate that our proposal can significantly improve baseline models’ performance. The code has been released at https://github.com/ZJULearning/PTL [ABSTRACT FROM AUTHOR]

The re-identification (ReID) task has received increasing studies in recent years and its performance has gained significant improvement. The progress mainly comes from searching for new network structures to learn person representations. However, limited efforts have been made to explore the potential performance of existing ReID networks directly by better training scheme, which leaves a large space for ReID research. In this paper, we propose a Self-Inspirited Feature Learning (SIF) method to enhance the performance of given ReID networks from the viewpoint of optimization. We design a simple adversarial learning scheme to encourage a network to learn more discriminative person representation. In our method, an auxiliary branch is added into the network only in the training stage, while the structure of the original network stays unchanged during the testing stage. In summary, SIF has three aspects of advantages: 1) it is designed under general setting; 2) it is compatible with many existing feature learning networks on the ReID task; 3) it is easy to implement and has steady performance. We evaluate the performance of SIF on three public ReID datasets: Market1501, DuckMTMC-reID, and CUHK03(both labeled and detected). The results demonstrate significant improvement in performance brought by SIF. We also apply SIF to obtain state-of-the-art results on all the three datasets. Specifically, mAP / Rank-1 accuracy are: 87.6%/95.2% (without re-rank) on Market1501, 79.4%/89.8% on DuckMTMC-reID, 77.0%/79.5% on CUHK03 (labeled) and 73.9%/76.6% on CUHK03 (detected), respectively. [ABSTRACT FROM AUTHOR]

The Person Re-identification (ReID) task aims to match persons across cameras in a surveillance system. In the past few years, many researches are devoted to ReID and its performance has gained significant improvement. ReID models are usually trained as a joint framework comprising a person feature extractor and a classifier. However, there exists co-adaptation between the feature extractor and the classifier, which prevents the feature extractor from making effective and sufficient optimization and results in inferior retrieval performance. In this paper, we propose a very simple and effective training method, called DeAda, to decouple this co-adaptation. Our main motivation is to construct a series of weak classifiers during training by randomization of parameters, so that optimization on the feature extractor could be strengthened in the training stage. DeAda is easy, effective, and efficient, and could serve as a plug-and-play optimization tool for ReID models, without additional memory and time cost. We also analyze the theoretical property of DeAda and show that it could produce identical features for the same person under some simple assumptions. We demonstrate its effectiveness on three public ReID datasets: Market1501, DukeMTMC-reID and CUHK03 over different ReID models. With DeAda optimization, we finally obtain state-of-the-art results on all the three datasets. [ABSTRACT FROM AUTHOR]

In this paper, we study Stochastic Composite Optimization (SCO) for sparse learning that aims to learn a sparse solution from a composite function. Most of the recent SCO algorithms have already reached the optimal expected convergence rate \mathcal O(1/\lambda T) , but they often fail to deliver sparse solutions at the end either due to the limited sparsity regularization during stochastic optimization (SO) or due to the limitation in online-to-batch conversion. Even when the objective function is strongly convex, their high probability bounds can only attain \mathcal O(\sqrt\log (1/\delta)/T) with $\delta$ is the failure probability, which is much worse than the expected convergence rate. To address these limitations, we propose a simple yet effective two-phase Stochastic Composite Optimization scheme by adding a novel powerful sparse online-to-batch conversion to the general Stochastic Optimization algorithms. We further develop three concrete algorithms, OptimalSL, LastSL and AverageSL, directly under our scheme to prove the effectiveness of the proposed scheme. Both the theoretical analysis and the experiment results show that our methods can really outperform the existing methods at the ability of sparse learning and at the meantime we can improve the high probability bound to approximately \mathcal {O}(\log (\log (T)/\delta)/\lambda T) . [ABSTRACT FROM AUTHOR]

Simple Summary: Traditionally, farmers are unable to pay enough attention to individual livestock. An increasing number of sensors are being used to monitor animal behavior, early disease detection, and evaluation of animal welfare. In this study, we used machine learning algorithms to identify multiple unitary behaviors and movements of dairy cattle recorded by motion sensors. We also investigated the effect of time window on the performance of unitary behaviors classification and discussed the necessity of movement analysis. This study shows a feasible way to explore more detailed movements based on the result of unitary behaviors classification. Low-cost sensors provide remote monitoring of animal behaviors to help producers comprehensively and accurately identify the health status of individual livestock in real-time. 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. [ABSTRACT FROM AUTHOR]

Edge-loading generates higher wear rates in ceramic-on-ceramic total hip prosthesis (THP). To investigate the friction coefficient (FC) in these conditions, three alumina ceramic (Biolox Forte) 32 mm-diameter components were tested using a hip friction simulator. The cup was positioned with a 75° abduction angle to achieve edge-loading conditions. The motion was first applied along the edge and then across the edge of the cup. First, tests were conducted under lubricated conditions with 25% bovine serum. Next, to simulate an extremely high contact pressure, the tests were run with the addition of a third body alumina ceramic chip inserted between the edge of the cup and the head. Engineering blue was used to analyze the contact area. Reference values were determined using a 0° cup abduction angle. Edge loading was achieved. The FC increased by three- to sixfold when the motion was applied along the edge, and by 70% when the motion was applied across the edge. However, the FC value was still low (about 0.1), which is similar to metal-on-metal THP. With the third body alumina ceramic particle inserted, the FC was 26 times higher than in the ideal conditions and intermittent squeaking occurred. High cup abduction angles may generate edge-loading and an increase in the friction coefficient for ceramic THP. © 2010 Orthopaedic Research Society. Published by Wiley Periodicals, Inc. J Orthop Res 28:979-985, 2010 [ABSTRACT FROM AUTHOR]

In this paper, we present novel sharp attention networks by adaptively sampling feature maps from convolutional neural networks for person re-identification (re-ID) problems. Due to the introduction of sampling-based attention models, the proposed approach can adaptively generate sharper attention-aware feature masks. This greatly differs from the gating-based attention mechanism that relies on soft gating functions to select the relevant features for person re-ID. In contrast, the proposed sampling-based attention mechanism allows us to effectively trim irrelevant features by enforcing the resultant feature masks to focus on the most discriminative features. It can produce sharper attentions that is more assertive in localizing subtle features relevant to re-identifying people across cameras. For this purpose, a differentiable Gumbel-Softmax sampler is employed to approximate the Bernoulli sampling to train the sharp attention networks. Extensive experimental evaluations demonstrate the superiority of this new sharp attention model for person re-ID over other related existing, published state-of-the-art works on three challenging benchmarks, including CUHK03, Market-1501, and DukeMTMC-reID. [ABSTRACT FROM AUTHOR]

• Heat stress modelling was done on an actual dairy farm equipped with sprinklers. • ANN models were the best to predict physiological responses in dairy cows. • Machine learning and its interpretation are relevant in heat stress research. • Individual heat stress states can be assessed non-invasively. Heat stress is increasingly affecting the production, health, and reproduction of dairy cows. Previous studies used limited variables as predictors of physiological responses, and the developed models poorly predict animal responses in evaporatively cooled environments. The aim of this study was to build machine learning models using comprehensive variables to predict physiological responses of dairy cows raised on an actual dairy farm equipped with sprinklers. Four algorithms including random forests, gradient boosting machines, artificial neural networks (ANN), and regularized linear regression were used to predict respiration rate (RR), vaginal temperature (VT), and eye temperature (ET) with 13 predictor variables from three dimensions: production, cow-related, and environmental factors. The classification performance of the predicted values in recognizing individual heat stress states was compared with commonly used thermal indices. The performance on the testing sets shows that the ANN models yielded the lowest root mean squared error for predicting RR (13.24 breaths/min), VT (0.30 °C), and ET (0.29 °C). The results interpreted with partial dependence plots and Local Interpretable Model-agnostic Explanations show that P.M. measurements and winter calving contributed most to high RR and VT predictions, whereas lying posture, high ambient temperature, and low wind speed contributed most to high ET predictions. When determining the ground-truth heat stress state by the actual RR, the best classification performance was yielded by the predicted RR with an accuracy of 77.7%; when determining the ground-truth heat stress state by the actual VT, the best classification performance was yielded by the predicted VT with an accuracy of 75.3%. This study demonstrates the ability of ANN in predicting physiological responses of dairy cows raised on actual farms with access to sprinklers. Adding more predictors other than meteorological parameters into training could increase predictive performance. Recognizing the heat stress state of individual animals, especially those at the highest risk, based on the predicted physiological responses and their interpretations can inform better heat abatement decisions. [ABSTRACT FROM AUTHOR]