Search

Long-term exposure to a relatively high concentration of airborne bacteria emitted from intensive livestock houses could potentially threaten the health and welfare of animals and workers. There is a dual effect of air sterilization and promotion of vitamin D synthesis for the specific bands of ultraviolet light. This study investigated the potential use of A-band ultraviolet (UVA) tubes as a clean and safe way of reducing airborne bacteria and improving calf health. The composition and emission characteristics of airborne bacteria were investigated and used to determine the correct operating regime of UVA tubes in calf houses. Intermittent exceedances of indoor airborne bacteria were observed in closed calf houses. The measured emission intensity of airborne bacteria was 1.13 ± 0.09 × 107 CFU h−1 per calf. Proteobacteria were the dominant microbial species in the air inside and outside calf houses. After UVA radiation, the indoor culturable airborne bacteria decreased in all particle size ranges of the Anderson sampler, and it showed the highest reduction rate in the size range of 3.3–4.7 μm. The results of this study would enrich the knowledge of the source characteristics of the airborne bacteria in intensive livestock farming and contribute to the environmental control of cattle in intensive livestock production. [ABSTRACT FROM AUTHOR]

The research on automatic monitoring methods for greenhouse gases and hazardous gas emissions is currently a focal point in the fields of environmental science and climatology. Until 2023, the amount of greenhouse gases emitted by the livestock sector accounts for about 11–17% of total global emissions, with enteric fermentation in ruminants being the main source of the gases. With the escalating problem of global climate change, accurate and effective monitoring of gas emissions has become a top priority. Presently, the determination of gas emission indices relies on specialized instrumentation such as breathing chambers, greenfeed systems, methane laser detectors, etc., each characterized by distinct principles, applicability, and accuracy levels. This paper first explains the mechanisms and effects of gas production by ruminant production systems, focusing on the monitoring methods, principles, advantages, and disadvantages of monitoring gas concentrations, and a summary of existing methods reveals their shortcomings, such as limited applicability, low accuracy, and high cost. In response to the current challenges in the field of equipment for monitoring greenhouse and hazardous gas emissions from ruminant production systems, this paper outlines future perspectives with the aim of developing more efficient, user-friendly, and cost-effective monitoring instruments. [ABSTRACT FROM AUTHOR]

Within the current process of large-scale dairy-cattle breeding, to address the problems of low recognition-accuracy and significant recognition-error associated with existing visual methods, we propose a method for recognizing the feeding behavior of dairy cows, one based on an improved RefineMask instance-segmentation model, and using high-quality detection and segmentation results to realize the recognition of the feeding behavior of dairy cows. Firstly, the input features are better extracted by incorporating the convolutional block attention module into the residual module of the feature extraction network. Secondly, an efficient channel attention module is incorporated into the neck design to achieve efficient integration of feature extraction while avoiding the surge of parameter volume computation. Subsequently, the GIoU loss function is used to increase the area of the prediction frame to optimize the convergence speed of the loss function, thus improving the regression accuracy. Finally, the logic of using mask information to recognize foraging behavior was designed, and the accurate recognition of foraging behavior was achieved according to the segmentation results of the model. We constructed, trained, and tested a cow dataset consisting of 1000 images from 50 different individual cows at peak feeding times. The method's effectiveness, robustness, and accuracy were verified by comparing it with example segmentation algorithms such as MSRCNN, Point_Rend, Cascade_Mask, and ConvNet_V2. The experimental results show that the accuracy of the improved RefineMask algorithm in recognizing the bounding box and accurately determining the segmentation mask is 98.3%, which is higher than that of the benchmark model by 0.7 percentage points; for this, the model parameter count size was 49.96 M, which meets the practical needs of local deployment. In addition, the technologies under study performed well in a variety of scenarios and adapted to various light environments; this research can provide technical support for the analysis of the relationship between cow feeding behavior and feed intake during peak feeding periods. [ABSTRACT FROM AUTHOR]

In animal husbandry applications, segmenting live pigs in complex farming environments faces many challenges, such as when pigs lick railings and defecate within the acquisition environment. The pig's behavior makes point cloud segmentation more complex because dynamic animal behaviors and environmental changes must be considered. This further requires point cloud segmentation algorithms to improve the feature capture capability. In order to tackle the challenges associated with accurately segmenting point cloud data collected in complex real-world scenarios, such as pig occlusion and posture changes, this study utilizes PointNet++. The SoftPool pooling method is employed to implement a PointNet++ model that can achieve accurate point cloud segmentation for live pigs in complex environments. Firstly, the PointNet++ model is modified to make it more suitable for pigs by adjusting its parameters related to feature extraction and sensory fields. Then, the model's ability to capture the details of point cloud features is further improved by using SoftPool as the point cloud feature pooling method. Finally, registration, filtering, and extraction are used to preprocess the point clouds before integrating them into a dataset for manual annotation. The improved PointNet++ model's segmentation ability was validated and redefined with the pig point cloud dataset. Through experiments, it was shown that the improved model has better learning ability across 529 pig point cloud data sets. The optimal mean Intersection over Union (mIoU) was recorded at 96.52% and the accuracy at 98.33%. This study has achieved the automatic segmentation of highly overlapping pigs and pen point clouds. This advancement enables future animal husbandry applications, such as estimating body weight and size based on 3D point clouds. [ABSTRACT FROM AUTHOR]

Livestock's live body dimensions are a pivotal indicator of economic output. Manual measurement is labor-intensive and time-consuming, often eliciting stress responses in the livestock. With the advancement of computer technology, the techniques for livestock live body dimension measurement have progressed rapidly, yielding significant research achievements. This paper presents a comprehensive review of the recent advancements in livestock live body dimension measurement, emphasizing the crucial role of computer-vision-based sensors. The discussion covers three main aspects: sensing data acquisition, sensing data processing, and sensing data analysis. The common techniques and measurement procedures in, and the current research status of, live body dimension measurement are introduced, along with a comparative analysis of their respective merits and drawbacks. Livestock data acquisition is the initial phase of live body dimension measurement, where sensors are employed as data collection equipment to obtain information conducive to precise measurements. Subsequently, the acquired data undergo processing, leveraging techniques such as 3D vision technology, computer graphics, image processing, and deep learning to calculate the measurements accurately. Lastly, this paper addresses the existing challenges within the domain of livestock live body dimension measurement in the livestock industry, highlighting the potential contributions of computer-vision-based sensors. Moreover, it predicts the potential development trends in the realm of high-throughput live body dimension measurement techniques for livestock. [ABSTRACT FROM AUTHOR]

Soil salinization is one of the main problems faced by modern agricultural production, especially cucumber production. This study screened the salt–alkali-tolerant cultivar 'D1909' and the salt–alkali-sensitive cultivar 'D1604' from 32 different cucumber ecological types on the basis of morphological indicators and salt–alkali indices combined with relevant physiological and biochemical indices. By performing a transcriptome metabolome analysis, the key gene CsSRG1, which is responsive to salt–alkali stress in cucumber, was screened, and its function was verified. The role of CsSRG1 in reducing salt–alkali stress in cucumber was clarified, and the mechanism of salt–alkali tolerance in cucumber was preliminarily explored. This study provides germplasm resources for cucumber salt–alkali tolerance breeding and a theoretical basis for the effective use of saline alkali soil to achieve high quality and high yield in other crops. [ABSTRACT FROM AUTHOR]

Acquiring phenotypic data from livestock constitutes a crucial yet cumbersome phase in the breeding process. Traditionally, obtaining livestock phenotypic data primarily involves manual, on-body measurement methods. This approach not only requires extensive labor but also induces stress on animals, which leads to potential economic losses. Presently, the integration of next-generation Artificial Intelligence (AI), visual processing, intelligent sensing, multimodal fusion processing, and robotic technology is increasingly prevalent in livestock farming. The advantages of these technologies lie in their rapidity and efficiency, coupled with their capability to acquire livestock data in a non-contact manner. Based on this, we provide a comprehensive summary and analysis of the primary advanced technologies employed in the non-contact acquisition of livestock phenotypic data. This review focuses on visual and AI-related techniques, including 3D reconstruction technology, body dimension acquisition techniques, and live animal weight estimation. We introduce the development of livestock 3D reconstruction technology and compare the methods of obtaining 3D point cloud data of livestock through RGB cameras, laser scanning, and 3D cameras. Subsequently, we explore body size calculation methods and compare the advantages and disadvantages of RGB image calculation methods and 3D point cloud body size calculation methods. Furthermore, we also compare and analyze weight estimation methods of linear regression and neural networks. Finally, we discuss the challenges and future trends of non-contact livestock phenotypic data acquisition. Through emerging technologies like next-generation AI and computer vision, the acquisition, analysis, and management of livestock phenotypic data are poised for rapid advancement. [ABSTRACT FROM AUTHOR]

To improve the classification of pig vocalization using vocal signals and improve recognition accuracy, a pig vocalization classification method based on multi-feature fusion is proposed in this study. With the typical vocalization of pigs in large-scale breeding houses as the research object, short-time energy, frequency centroid, formant frequency and first-order difference, and Mel frequency cepstral coefficient and first-order difference were extracted as the fusion features. These fusion features were improved using principal component analysis. A pig vocalization classification model with a BP neural network optimized based on the genetic algorithm was constructed. The results showed that using the improved features to recognize pig grunting, squealing, and coughing, the average recognition accuracy was 93.2%; the recognition precisions were 87.9%, 98.1%, and 92.7%, respectively, with an average of 92.9%; and the recognition recalls were 92.0%, 99.1%, and 87.4%, respectively, with an average of 92.8%, which indicated that the proposed pig vocalization classification method had good recognition precision and recall, and could provide a reference for pig vocalization information feedback and automatic recognition. [ABSTRACT FROM AUTHOR]

A clear understanding of the number of pigs plays a crucial role in breeding management. Computer vision technology possesses several advantages, as it is harmless and labour-saving compared to traditional counting methods. Nevertheless, the existing methods still face some challenges, such as: (1) the lack of a substantial high-precision pig-counting dataset; (2) creating a dataset for instance segmentation can be time-consuming and labor-intensive; (3) interactive occlusion and overlapping always lead to incorrect recognition of pigs; (4) existing methods for counting such as object detection have limited accuracy. To address the issues of dataset scarcity and labor-intensive manual labeling, we make a semi-auto instance labeling tool (SAI) to help us to produce a high-precision pig counting dataset named Count1200 including 1220 images and 25,762 instances. The speed at which we make labels far exceeds the speed of manual annotation. A concise and efficient instance segmentation model built upon several novel modules, referred to as the Instances Counting Network (ICNet), is proposed in this paper for pig counting. ICNet is a dual-branch model ingeniously formed of a combination of several layers, which is named the Parallel Deformable Convolutions Layer (PDCL), which is trained from scratch and primarily composed of a couple of parallel deformable convolution blocks (PDCBs). We effectively leverage the characteristic of modeling long-range sequences to build our basic block and compute layer. Along with the benefits of a large effective receptive field, PDCL achieves a better performance for multi-scale objects. In the trade-off between computational resources and performance, ICNet demonstrates excellent performance and surpasses other models in Count1200, A P of 71.4% and A P 50 of 95.7% are obtained in our experiments. This work provides inspiration for the rapid creation of high-precision datasets and proposes an accurate approach to pig counting. [ABSTRACT FROM AUTHOR]

Rumination behavior is closely associated with factors such as cow productivity, reproductive performance, and disease incidence. For multi-object scenarios of dairy cattle, ruminant mouth area images accounted for little characteristic information, which was first put forward using an improved Faster R-CNN target detection algorithm to improve the detection performance model for the ruminant area of dairy cattle. The primary objective is to enhance the model's performance in accurately detecting cow rumination regions. To achieve this, the dataset used in this study is annotated with both the cow head region and the mouth region. The ResNet-50-FPN network is employed to extract the cow mouth features, and the CBAM attention mechanism is incorporated to further improve the algorithm's detection accuracy. Subsequently, the object detection results are combined with optical flow information to eliminate false detections. Finally, an interpolation approach is adopted to design a frame complementary algorithm that corrects the detection frame of the cow mouth region. This interpolation algorithm is employed to rectify the detection frame of the cow's mouth region, addressing the issue of missed detections and enhancing the accuracy of ruminant mouth region detection. To overcome the challenges associated with the inaccurate extraction of small-scale optical flow information and interference between different optical flow information in multi-objective scenes, an enhanced GMFlowNet-based method for multi-objective cow ruminant optical flow analysis is proposed. To mitigate interference from other head movements, the MeanShift clustering method is utilized to compute the velocity magnitude values of each pixel in the vertical direction within the intercepted ruminant mouth region. Furthermore, the mean square difference is calculated, incorporating the concept of range interquartile, to eliminate outliers in the optical flow curve. Finally, a final filter is applied to fit the optical flow curve of the multi-object cow mouth movement, and it is able to identify rumination behavior and calculate chewing times. The efficacy, robustness, and accuracy of the proposed method are evaluated through experiments, with nine videos capturing multi-object cow chewing behavior in different settings. The experimental findings demonstrate that the enhanced Faster R-CNN algorithm achieved an 84.70% accuracy in detecting the ruminant mouth region, representing an improvement of 11.80 percentage points over the results obtained using the Faster R-CNN detection approach. Additionally, the enhanced GMFlowNet algorithm accurately identifies the ruminant behavior of all multi-objective cows, with a 97.30% accuracy in calculating the number of ruminant chewing instances, surpassing the accuracy of the FlowNet2.0 algorithm by 3.97 percentage points. This study provides technical support for intelligent monitoring and analysis of rumination behavior of dairy cows in group breeding. [ABSTRACT FROM AUTHOR]

Studying the distribution characteristics of bioaerosols and their interaction with the environment is crucial for dairy farms. The distribution of aerosols differs in dairy farming from farming of other livestock, and their sensitivity to environmental factors varies across sites. Field experiments were conducted in an intensive commercial dairy farm in Northern China to investigate the horizontal and vertical distribution of culturable bacterial bioaerosols. Concentration levels and particle size ranges were analyzed, and the impact of multiple environmental factors on culturable bacterial bioaerosols was assessed. Significant variations in culturable bacterial bioaerosol concentrations were observed across eight functional zones, ranging from 1.14 × 103 to 7.35 × 103 CFU/m3. Culturable bacterial bioaerosols exhibited consistent carrier distribution patterns across six different size ranges. Vertical analysis revealed significantly higher culturable bacterial bioaerosol concentrations at a 1 m height compared to 4 m (p < 0.05), while similar size distributions were observed at different heights of the same sampling location. The top three environmental factors influencing culturable bacterial bioaerosol concentrations were PM100 concentration, wind direction, and air temperature. This study provides insights into the distribution characteristics of culturable bacterial bioaerosols on dairy farms and their response to environmental factors. The findings serve as a reference for evaluating bioaerosol emissions and establishing daily disinfection management measures on dairy farms. [ABSTRACT FROM AUTHOR]

Earthen sites are a kind of constructure with significant historical and cultural value. However, the destruction of earthen sites caused by erosion occurs frequently. The solidification of calcined ginger nuts can improve the strength of the soil so that it can be used to protect the earthen sites. However, the strength degradation of solidified soil by calcined ginger nuts after dry–wet and freeze–thaw cycles is unclear. To reveal the deterioration pattern of solidified soil strength, the effects of its dosage and cycle number on the strength of solidified soil were analyzed through shear strength, dry–wet cycle, and freeze–thaw cycle tests. The results showed that the solidified soil strength decreased first and increased with dosage increase. With the number of dry–wet cycles increasing, the strength of the plain loess decreased rapidly and gradually turned flat. The strength loss of solidified soil was small in the dry–wet process. With freeze–thaw cycle numbers increasing, the strength of the plain loess decreased first and then tended to be flat, the strength of solidified soil decreased first and then increased slightly, and the change in the strength had a clear inflection point. With the increasing dosage, freeze–thaw cycle numbers corresponding to the inflection point were significantly reduced. These results indicate that calcined ginger nuts could enhance the resistance of earthen sites loess to dry–wet and freeze–thaw cycles. [ABSTRACT FROM AUTHOR]

Simple Summary: The H9N2 avian influenza virus has spread to the whole world and become one of the dominant subtype influenza viruses in chickens in China. H9N2 virus could not only result in great economic losses by reducing egg production but also serve as a gene vector to provide its gene segments to other emerging severe influenza A viruses to cause higher mortality and more serious consequences. Thus, developing models to predict H9N2 status should be given priority. Our main aim was to use the machine learning method (XGBoost classification algorithm) and regular production data (laying rate and mortality) to predict the occurrence and development of H9N2 in laying hen houses and evaluate their performance in disease prediction. Additionally, we assessed the working ability of the framework with different time frames to predict H9N2 status in advance within a 3-day period. We found that this framework could work well in prediction with high accuracy and sensitivity, and with more information introduced into the model, more "don't care values" would be added into datasets to affect model performance by forming attribute noise. Besides, our study recommended efficient frameworks and models for H9N2 status prediction and provided practical potential uses in the livestock and poultry industry. The H9N2 avian influenza virus has become one of the dominant subtypes of avian influenza virus in poultry and has been significantly harmful to chickens in China, with great economic losses in terms of reduced egg production or high mortality by co-infection with other pathogens. A prediction of H9N2 status based on easily available production data with high accuracy would be important and essential to prevent and control H9N2 outbreaks in advance. This study developed a machine learning framework based on the XGBoost classification algorithm using 3 months' laying rates and mortalities collected from three H9N2-infected laying hen houses with complete onset cycles. A framework was developed to automatically predict the H9N2 status of individual house for future 3 days (H9N2 status + 0, H9N2 status + 1, H9N2 status + 2) with five time frames (day + 0, day − 1, day − 2, day − 3, day − 4). It had been proven that a high accuracy rate > 90%, a recall rate > 90%, a precision rate of >80%, and an area under the curve of the receiver operator characteristic ≥ 0.85 could be achieved with the prediction models. Models with day + 0 and day − 1 were highly recommended to predict H9N2 status + 0 and H9N2 status + 1 for the direct or auxiliary monitoring of its occurrence and development. Such a framework could provide new insights into predicting H9N2 outbreaks, and other practical potential applications to assist in disease monitor were also considerable. [ABSTRACT FROM AUTHOR]

The images acquired by a single visible light sensor are very susceptible to light conditions, weather changes, and other factors, while the images acquired by a single infrared light sensor generally have poor resolution, low contrast, low signal-to-noise ratio, and blurred visual effects. The fusion of visible and infrared light can avoid the disadvantages of two single sensors and, in fusing the advantages of both sensors, significantly improve the quality of the images. The fusion of infrared and visible images is widely used in agriculture, industry, medicine, and other fields. In this study, firstly, the architecture of mainstream infrared and visible image fusion technology and application was reviewed; secondly, the application status in robot vision, medical imaging, agricultural remote sensing, and industrial defect detection fields was discussed; thirdly, the evaluation indicators of the main image fusion methods were combined into the subjective evaluation and the objective evaluation, the properties of current mainstream technologies were then specifically analyzed and compared, and the outlook for image fusion was assessed; finally, infrared and visible image fusion was summarized. The results show that the definition and efficiency of the fused infrared and visible image had been improved significantly. However, there were still some problems, such as the poor accuracy of the fused image, and irretrievably lost pixels. There is a need to improve the adaptive design of the traditional algorithm parameters, to combine the innovation of the fusion algorithm and the optimization of the neural network, so as to further improve the image fusion accuracy, reduce noise interference, and improve the real-time performance of the algorithm. [ABSTRACT FROM AUTHOR]

As machine vision technology has advanced, pig face recognition has gained wide attention as an individual pig identification method. This study establishes an improved ResNAM network as a backbone network for pig face image feature extraction by combining an NAM (normalization-based attention module) attention mechanism and a ResNet model to probe non-contact open-set pig face recognition. Then, an open-set pig face recognition framework is designed by integrating three loss functions and two metrics to finish the task with no crossover of individuals in the training and test sets. The SphereFace loss function with the cosine distance as a metric and ResNAM are combined in the framework to obtain the optimal open-set pig face recognition model. To train our model, 37 pigs with a total of 12,993 images were randomly selected from the collected pig face images, and 9 pigs with a total of 3431 images were set as a test set. 900 pairs of positive sample pairs and 900 pairs of negative pairs were obtained from the images in the test set. A series of experimental results show that our accuracy reached 95.28%, which was 2.61% higher than that of a human face recognition model. NAM was more effective in improving the performance of the pig face recognition model than the mainstream BAM (bottleneck attention module) and CBAM (convolutional block attention module). The research results can provide technological support for non-contact open-set individual recognition for intelligent farming processes. [ABSTRACT FROM AUTHOR]

Natural breeding scenes have the characteristics of a large number of cows, complex lighting, and a complex background environment, which presents great difficulties for the detection of dairy cow estrus behavior. However, the existing research on cow estrus behavior detection works well in ideal environments with a small number of cows and has a low inference speed and accuracy in natural scenes. To improve the inference speed and accuracy of cow estrus behavior in natural scenes, this paper proposes a cow estrus behavior detection method based on the improved YOLOv5. By improving the YOLOv5 model, it has stronger detection ability for complex environments and multi-scale objects. First, the atrous spatial pyramid pooling (ASPP) module is employed to optimize the YOLOv5l network at multiple scales, which improves the model's receptive field and ability to perceive global contextual multiscale information. Second, a cow estrus behavior detection model is constructed by combining the channel-attention mechanism and a deep-asymmetric-bottleneck module. Last, K-means clustering is performed to obtain new anchors and complete intersection over union (CIoU) is used to introduce the relative ratio between the predicted box of the cow mounting and the true box of the cow mounting to the regression box prediction function to improve the scale invariance of the model. Multiple cameras were installed in a natural breeding scene containing 200 cows to capture videos of cows mounting. A total of 2668 images were obtained from 115 videos of cow mounting events from the training set, and 675 images were obtained from 29 videos of cow mounting events from the test set. The training set is augmented by the mosaic method to increase the diversity of the dataset. The experimental results show that the average accuracy of the improved model was 94.3%, that the precision was 97.0%, and that the recall was 89.5%, which were higher than those of mainstream models such as YOLOv5, YOLOv3, and Faster R-CNN. The results of the ablation experiments show that ASPP, new anchors, C3SAB, and C3DAB designed in this study can improve the accuracy of the model by 5.9%. Furthermore, when the ASPP dilated convolution was set to (1,5,9,13) and the loss function was set to CIoU, the model had the highest accuracy. The class activation map function was utilized to visualize the model's feature extraction results and to explain the model's region of interest for cow images in natural scenes, which demonstrates the effectiveness of the model. Therefore, the model proposed in this study can improve the accuracy of the model for detecting cow estrus events. Additionally, the model's inference speed was 71 frames per second (fps), which meets the requirements of fast and accurate detection of cow estrus events in natural scenes and all-weather conditions. [ABSTRACT FROM AUTHOR]

Body dimensions are key indicators for the beef cattle fattening and breeding process. On-animal measurement is relatively inefficient, and can induce severe stress responses among beef cattle and pose a risk for operators, thereby impacting the cattle's growth rate and wellbeing. To address the above issues, a highly efficient and automatic method was developed to measure beef cattle's body dimensions, including the oblique length, height, width, abdominal girth, and chest girth, based on the reconstructed three-dimensional point cloud data. The horizontal continuous slice sequence of the complete point clouds was first extracted, and the central point of the beef cattle leg region was determined from the span distribution of the point cloud clusters in the targeted slices. Subsequently, the boundary of the beef cattle leg region was identified by the "five-point clustering gradient boundary recognition algorithm" and was then calibrated, followed by the accurate segmentation of the corresponding region. The key regions for body dimension data calculation were further determined by the proposed algorithm, which forms the basis of the scientific calculation of key body dimensions. The influence of different postures of beef cattle on the measurement results was also preliminarily discussed. The results showed that the errors of calculated body dimensions, i.e., the oblique length, height, width, abdominal girth, and chest girth, were 2.3%, 2.8%, 1.6%, 2.8%, and 2.6%, respectively. In the present work, the beef cattle body dimensions could be effectively measured based on the 3D regional features of the point cloud data. The proposed algorithm shows a degree of generalization and robustness that is not affected by different postures of beef cattle. This automatic method can be effectively used to collect reliable phenotype data during the fattening of beef cattle and can be directly integrated into the breeding process. [ABSTRACT FROM AUTHOR]

The use of an accelerometer is considered as a promising method for the automatic measurement of the feeding behavior or feed intake of cattle, with great significance in facilitating daily management. To address further need for commercial use, an efficient classification algorithm at a low sample frequency is needed to reduce the amount of recorded data to increase the battery life of the monitoring device, and a high-precision model needs to be developed to predict feed intake on the basis of feeding behavior. Accelerograms for the jaw movement and feed intake of 13 mid-lactating cows were collected during feeding with a sampling frequency of 1 Hz at three different positions: the nasolabial levator muscle (P1), the right masseter muscle (P2), and the left lower lip muscle (P3). A behavior identification framework was developed to recognize jaw movements including ingesting, chewing and ingesting–chewing through extreme gradient boosting (XGB) integrated with the hidden Markov model solved by the Viterbi algorithm (HMM–Viterbi). Fourteen machine learning models were established and compared in order to predict feed intake rate through the accelerometer signals of recognized jaw movement activities. The developed behavior identification framework could effectively recognize different jaw movement activities with a precision of 99% at a window size of 10 s. The measured feed intake rate was 190 ± 89 g/min and could be predicted efficiently using the extra trees regressor (ETR), whose R2, RMSE, and NME were 0.97, 0.36 and 0.05, respectively. The three investigated monitoring sites may have affected the accuracy of feed intake prediction, but not behavior identification. P1 was recommended as the proper monitoring site, and the results of this study provide a reference for the further development of a wearable device equipped with accelerometers to measure feeding behavior and to predict feed intake. [ABSTRACT FROM AUTHOR]

Collaborative reasoning for knowledge-based visual question answering is challenging but vital and efficient in understanding the features of the images and questions. While previous methods jointly fuse all kinds of features by attention mechanism or use handcrafted rules to generate a layout for performing compositional reasoning, which lacks the process of visual reasoning and introduces a large number of parameters for predicting the correct answer. For conducting visual reasoning on all kinds of image–question pairs, in this paper, we propose a novel reasoning model of a question-guided tree structure with a knowledge base (QGTSKB) for addressing these problems. In addition, our model consists of four neural module networks: the attention model that locates attended regions based on the image features and question embeddings by attention mechanism, the gated reasoning model that forgets and updates the fused features, the fusion reasoning model that mines high-level semantics of the attended visual features and knowledge base and knowledge-based fact model that makes up for the lack of visual and textual information with external knowledge. Therefore, our model performs visual analysis and reasoning based on tree structures, knowledge base and four neural module networks. Experimental results show that our model achieves superior performance over existing methods on the VQA v2.0 and CLVER dataset, and visual reasoning experiments prove the interpretability of the model. [ABSTRACT FROM AUTHOR]

In this paper, we provide external image features and use the internal attention mechanism to solve the VQA problem given a dataset of textual questions and related images. Most previous models for VQA use a pair of images and questions as input. In addition, the model adopts a question-oriented attention mechanism to extract the features of the entire image and then perform feature fusion. However, the shortcoming of these models is that they cannot effectively eliminate the irrelevant features of the image. In addition, the problem-oriented attention mechanism lacks in the mining of image features, which will bring in redundant image features. In this paper, we propose a VQA model based on adversarial learning and bidirectional attention. We exploit external image features that are not related to the question to form an adversarial mechanism to boost the accuracy of the model. Target detection is performed on the image—that is, the image-oriented attention mechanism. The bidirectional attention mechanism is conducive to promoting model attention and eliminating interference. Experimental results are evaluated on benchmark datasets, and our model performs better than other models based on attention methods. In addition, the qualitative results show the attention maps on the images and leads to predicting correct answers. [ABSTRACT FROM AUTHOR]

In the field of gliomas research, the broad availability of genetic and image information originated by computer technologies and the booming of biomedical publications has led to the advent of the big-data era. Machine learning methods were applied as possible approaches to speed up the data mining processes. In this article, we reviewed the present situation and future orientations of machine learning application in gliomas within the context of workflows to integrate analysis for precision cancer care. Publicly available tools or algorithms for key machine learning technologies in the literature mining for glioma clinical research were reviewed and compared. Further, the existing solutions of machine learning methods and their limitations in glioma prediction and diagnostics, such as overfitting and class imbalanced, were critically analyzed. [ABSTRACT FROM AUTHOR]

The interconnection of distributed energy resources (DERs) in microgrids (MGs) operating in both islanded and grid-connected modes require coordinated control strategies. DERs are interfaced with voltage source inverters (VSIs) enabling interconnection. This paper proposes a load demand sharing scheme for the parallel operation of VSIs in an islanded voltage source inverter-based microgrid (VSI-MG). The ride-through capability of a heavily loaded VSI-MG, where some of the VSIs are fully loaded due to the occurrence of an event is investigated. In developing analytical equations to model the VSI, the concept of virtual synchronous machines (VSM) is applied to enable the VSI mimic the inertia effect of synchronous machines. A power frame transformation (PFT) that takes the line ratios of the MG network into account is also incorporated to yield satisfactory transient responses of both network frequency and bus voltages in the MG network. A Jacobian-based method is then developed to take into account the operational capacity of each VSI in the VSI-MG. The resulting amendable droop control constrains the VSIs within their power capabilities when an event occurs. Simulation results presented within demonstrate the effectiveness of the proposed procedure which has great potential to facilitate efforts in maintaining system reliability and resiliency. [ABSTRACT FROM AUTHOR]

Graphene (Gr) has proved its significant role as a reinforcement material in improving the strength of metal matrix composites due to its excellent mechanical properties. In this paper, Gr/Cu composite film with a layered structure was prepared by layering electrodeposition. The directional distribution of Gr in the Cu film was insured by this method, which gives play to its ultra-high-strength in a two-dimensional plane. In the meantime, the effect of electrodeposition time on the distribution structure of the Gr layer was studied. The structure analysis and mechanical properties test show that the strength of the layered Gr/Cu composite film is greatly improved compared to the pure Cu film. Furthermore, the strength of the composite film increases at the beginning and then decreases with the electrodeposition time of the Gr layer increasing, while the coverage and the degree for the layer stacking of Gr gradually increase in this process. In conclusion, the influence of different Gr distributions on the mechanical properties of the composite film has been studied by combining the experimental results with molecular dynamics simulation, which lays an effective foundation for further optimizing the structure of Gr in the layered composite film and improving the mechanical properties. [ABSTRACT FROM AUTHOR]

By modifying the bonding of graphene (GR) and Fe3O4, a stable structure of GR-Fe3O4, namely magnetic GR, was obtained. Under the induction of a magnetic field, it can be orientated in an epoxy resin (EP) matrix, thus preparing EP/GR-Fe3O4 composites. The effects of the content of GR and the degree of orientation on the thermal conductivity of the composites were investigated, and the most suitable Fe3O4 load on GR was obtained. When the mass ratio of GR and Fe3O4 was 2:1, the thermal conductivity could be increased by 54.8% compared with that of pure EP. Meanwhile, EP/GR-Fe3O4 composites had a better thermal stability, dynamic thermomechanical properties, and excellent electrical insulation properties, which can meet the requirements of electronic packaging materials. [ABSTRACT FROM AUTHOR]

Background: Tibia fracture (BF) before stroke shortly causes long-term post-stroke memory dysfunction in mice. The mechanism is unclear. We hypothesize that BF enhances neuroinflammation and blood brain barrier (BBB) breakdown in the hippocampus and white matter (WM) damage. Methods: Mice were assigned to groups: BF, stroke, BF+stroke (BF 6 h before stroke) and sham. BBB integrity was analyzed 3 days after the surgeries and WM injury was analyzed 3 days and 8 weeks after the surgeries. Results: Stroke and BF+stroke groups had more activated microglia/macrophages and lower levels of claudin-5 in the ipsilateral hippocampi than the BF group. BF+stroke group had the highest number microglia/macrophages and the lowest level of claudin-5 among all groups and had fewer pericytes than BF group. Stroke and BF+stroke groups had smaller WM areas in the ipsilateral basal ganglia than the sham group 8 weeks after the injuries. The BF+stroke group also had smaller WM areas in the ipsilateral than sham and BF groups 3 days after the injuries and in the contralateral basal ganglia than stroke and BF groups 8 weeks after the injuries. Conclusions: BF exacerbates neuroinflammation and BBB leakage in the hippocampus and WM damage in basal ganglia, which could contribute to the long-lasting memory dysfunction in BF+stroke mice. [ABSTRACT FROM AUTHOR]

The secure operation of 110-kV networks should be considered in the optimal generation dispatch of regional power grids in large central cities. However, since 110-kV lines do not satisfy the premise of R << X in the direct current power flow (DCPF) model, the DCPF, which is mostly applied in the security-constrained unit commitment (SCUC) problem of high-voltage power grids, is no longer suitable for describing the active power flow of regional power grids in large central cities. Hence, the quadratic active power flow (QAPF) model considering the resistance of lines is proposed to describe the network security constraints, and an SCUC model for power system with 110-kV network and pumped-storage hydro (PSH) units is established. The analytical expressions of the spinning reserve (SR) capacity of PSH units are given considering different operational modes, and the SR capacity of PSH units is included in the constraint of the SR capacity requirement of the system. The QAPF is a set of quadratic equality constraints, making the SCUC model a mixed-integer nonlinear non-convex programming (MINNP) model. To reduce the computational complexity of solving the model when applied in actual large-scale regional networks, the QAPF model is relaxed by its convex hull, and the SCUC model is transformed into a mixed-integer convex programming (MICP) model, which can be solved to obtain the global optimal solution efficiently and reliably by the mature commercial solver GUROBI (24.3.3, GAMS Development Corporation, Guangzhou, China). Test results on the IEEE-9 bus system, the PEGASE 89 bus system and the Shenzhen city power grid including the 110-kV network demonstrate that the relaxed QAPF model has good calculation accuracy and efficiency, and it is suitable for solving the SCUC problem in large-scale regional networks. [ABSTRACT FROM AUTHOR]

The chlorine (Cl) and bromine (Br) co-doped lithium nickel manganese cobalt oxide (LiNi1/3Co1/3Mn1/3O2) was successfully synthesized by the molten salt method. The synthesized LiNi1/3Co1/3Mn1/3O2 compound demonstrates spherical morphology, which is formed by aggregated spherical-like or polygon primary particles. Halogen substitution would contribute to the growth of the primary particles. The LiNi1/3Co1/3Mn1/3O2 compound has the typical hexagonal layered structure, and no impurity phase is detected. The surface oxidation state of the compound is improved after Cl and Br substitution. Moreover, the Cl and Br co-doped LiNi1/3Co1/3Mn1/3O2 compound exhibits both improved rate capacity and cycle stability at a high voltage (4.6 V) compared with the pristine LiNi1/3Co1/3Mn1/3O2. The initial discharge capacities of Cl and Br co-doped LiNi1/3Co1/3Mn1/3O2 are 208.9 mAh g−1, 200.6 mAh g−1, 188.2 mAh g−1, 173.3 mAh g−1, and 157.1 mAh g−1 at the corresponding rates of 0.1C, 0.2C, 0.5C, 1C, and 3C respectively. The capacity retention at 1C after 50 cycles is increased from 81.1% to 93.2% by co-doping. The better contact between the electroactive particles of the electrode and the smaller resistance enhance the electric conductivity of the Cl and Br co-doped LiNi1/3Co1/3Mn1/3O2 cathode. The synthesized LiNi1/3Co1/3Mn1/3O2 is a promising cathode material for a high-power and large-capacity lithium-ion battery. [ABSTRACT FROM AUTHOR]