Explore the vast range of titles available.

Automatic detection of kiwifruit in the orchard is challenging because illumination varies through the day and night and because of color similarity between kiwifruit and the complex background of leaves, branches and stems. Also, kiwifruits grow in clusters, which may result in having occluded and touching fruits. A fast and accurate object detection algorithm was developed to automatically detect kiwifruits in the orchard by improving the YOLOv3-tiny model. Based on the characteristics of kiwifruit images, two convolutional kernels of 3 × 3 and 1 × 1 were added to the fifth and sixth convolution layers of the YOLOv3-tiny model, respectively, to develop a deep YOLOv3-tiny (DY3TNet) model. It takes multiple 1 × 1 convolutional layers in intermediate layers of the network to reduce the computational complexity. Testing images captured from day and night and comparing with other deep learning models, namely, Faster R-CNN with ZFNet, Faster R-CNN with VGG16, YOLOv2 and YOLOv3-tiny, the DY3TNet model achieved the highest average precision of 0.9005 with the smallest data weight of 27 MB. Furthermore, it took only 34 ms on average to process an image of a resolution of 2352 × 1568 pixels. The DY3TNet model, along with the YOLOv3-tiny model, showed better performance on images captured with flash than those without. Moreover, the experiments indicated that the image augmentation process could improve the detection performance, and a simple lighting arrangement could improve the success rate of detection in the orchard. The experimental results demonstrated that the improved DY3TNet model is small and efficient and that it would increase the applicability of real-time kiwifruit detection in the orchard even when small hardware devices are used.

Leucine-rich alpha⁃2 glycoprotein 1 (LRG1) is an important member of the leucine-rich repetitive sequence protein family. LRG1 was mainly involved in normal physiological activities of the nervous system, such as synapse formation, synapse growth, the development of nerve processes, neurotransmitter transfer and release, and cell adhesion molecules or ligand-binding proteins. Also, LRG1 affected the development of respiratory diseases, hematological diseases, endocrine diseases, tumor diseases, eye diseases, cardiovascular diseases, rheumatic immune diseases, infectious diseases, etc. LRG1 was a newly discovered important upstream signaling molecule of transforming growth factor⁃β (TGF⁃β) that affected various pathological processes through the TGF⁃β signaling pathway. However, research on LRG1 and its involvement in the occurrence and development of diseases was still in its infancy and the current studies were mainly focused on proteomic detection and basic animal experimental reports. We could reasonably predict that LRG1 might act as a new direction and strategy for the treatment of many diseases.

Background and purpose Cerebral ischemia‒reperfusion injury causes significant harm to human health and is a major contributor to stroke-related deaths worldwide. Current treatments are limited, and new, more effective prevention and treatment strategies that target multiple cell components are urgently needed. Leucine-rich alpha-2 glycoprotein 1 (Lrg1) appears to be associated with the progression of cerebral ischemia‒reperfusion injury, but the exact mechanism of it is unknown. Methods Wild-type (WT) and Lrg1 knockout ( Lrg1 −/− ) mice were used to investigate the role of Lrg1 after cerebral ischemia‒reperfusion injury. The effects of Lrg1 knockout on brain infarct volume, blood‒brain barrier permeability, and neurological score (based on 2,3,5-triphenyl tetrazolium chloride, evans blue dye, hematoxylin, and eosin staining) were assessed. Single-cell RNA sequencing (scRNA-seq), immunofluorescence, and microvascular albumin leakage tests were utilized to investigate alterations in various cell components in brain tissue after Lrg1 knockout. Results Lrg1 expression was increased in various cell types of brain tissue after cerebral ischemia‒reperfusion injury. Lrg1 knockout reduced cerebral edema and infarct size and improved neurological function after cerebral ischemia‒reperfusion injury. Single-cell RNA sequencing analysis of WT and Lrg1 −/− mouse brain tissues after cerebral ischemia‒reperfusion injury revealed that Lrg1 knockout enhances blood‒brain barrier (BBB) by upregulating claudin 11, integrin β5, protocadherin 9, and annexin A2. Lrg1 knockout also promoted an anti-inflammatory and tissue-repairing phenotype in microglia and macrophages while reducing neuron and oligodendrocyte cell death. Conclusions Our results has shown that Lrg1 mediates numerous pathological processes involved in cerebral ischemia‒reperfusion injury by altering the functional states of various cell types, thereby rendering it a promising therapeutic target for cerebral ischemia‒reperfusion injury. Highlights Upregulated Lrg1 expression is observed in various cells in brain after cerebral ischemia‒reperfusion injury. Lrg1 knockout can attenuate brain damage and blood‒brain barrier dysfunction following cerebral ischemia‒reperfusion injury. Lrg1 knockout can alter the functional state of microglial cells towards the anti-inflammatory M2 phenotype. Lrg1 knockout can modulate the metabolic status of multiple cell types.

This study aims to demonstrate the feasibility for classifying kiwifruit into shape grades by adding a single camera to current Chinese sorting lines equipped with weight sensors. Image processing methods are employed to calculate fruit length, maximum diameter of the equatorial section, and projected area. A stepwise multiple linear regression method is applied to select significant variables for predicting minimum diameter of the equatorial section and volume and to establish corresponding estimation models. Results show that length, maximum diameter of the equatorial section and weight are selected to predict the minimum diameter of the equatorial section, with the coefficient of determination of only 0.82 when compared to manual measurements. Weight and length are then selected to estimate the volume, which is in good agreement with the measured one with the coefficient of determination of 0.98. Fruit classification based on the estimated minimum diameter of the equatorial section achieves a low success rate of 84.6%, which is significantly improved using a linear combination of the length/maximum diameter of the equatorial section and projected area/length ratios, reaching 98.3%. Thus, it is possible for Chinese kiwifruit sorting lines to reach international standards of grading kiwifruit on fruit shape classification by adding a single camera.

On-farm sorting and transportation of postharvest fruit include sorting out defective products, grading them into categories based on quality, distributing them into bins, and carrying bins to field collecting stations. Advances in artificial intelligence (AI) can speed up on-farm sorting and transportation with high accuracy and robustness and significantly reduce postharvest losses. The primary objective of this literature review is to provide an overview to present a critical analysis and identify the challenges and opportunities of AI applications for on-farm sorting and transportation, with a focus on fruit. The challenges of on-farm sorting and transportation were discussed to specify the role of AI. Sensors and techniques for data acquisition were investigated to illustrate the tasks that AI models have addressed for on-farm sorting and transportation. AI models proposed in previous studies were compared to investigate the adequate approaches for on-farm sorting and transportation. Finally, the advantages and limitations of utilizing AI have been discussed, and in-depth analysis has been provided to identify future research directions. We anticipate that this survey will pave the way for further studies on the implementation of automated systems for on-farm fruit sorting and transportation.

An apple-picking robot is now the most widely accepted method in the substitution of low-efficiency and high-cost labor-intensive apple harvesting. Although most current research on apple-picking robots works well in the laboratory, most of them are unworkable in an orchard environment due to unsatisfied apple positioning performance. In general, an accurate, fast, and widely used apple positioning method for an apple-picking robot remains lacking. Some positioning methods with detection-based deep learning reached an acceptable performance in some orchards. However, apples occluded by apples, leaves, and branches are ignored in these methods with detection-based deep learning. Therefore, an apple binocular positioning method based on a Mask Region Convolutional Neural Network (Mask R-CNN, an instance segmentation network) was developed to achieve better apple positioning. A binocular camera (Bumblebee XB3) was adapted to capture binocular images of apples. After that, a Mask R-CNN was applied to implement instance segmentation of apple binocular images. Then, template matching with a parallel polar line constraint was applied for the stereo matching of apples. Finally, four feature point pairs of apples from binocular images were selected to calculate disparity and depth. The trained Mask R-CNN reached a detection and segmentation intersection over union (IoU) of 80.11% and 84.39%, respectively. The coefficient of variation (CoV) and positioning accuracy (PA) of binocular positioning were 5.28 mm and 99.49%, respectively. The research developed a new method to fulfill binocular positioning with a segmentation-based neural network.

Background and purpose Nonmuscle myosin heavy chain IIA, played an essential role in the promotion of tight junction injury in vascular endothelial cells under oxygen glucose deprivation condition. Rat microvascular endothelial cells had been confirmed to have the susceptibility to ox-LDL stimulation under OGD condition. We proposed the hypothesis that lipid metabolic reprogramming might be the root cause for damage to RBMCs tight junction. Methods Untargeted shotgun and targeted lipid metabolomics mass spectrometry approaches combined with principal component analysis was applied to better define the lipids contributing to the variance observed between control and different OGD time. The protein expression of tight junction of RBMCs: occludin, claudin-5, and ZO-1 were detected with immunofluorescence staining and western blot. The proof of the interaction between NMMHC IIA and SREBP1 was investigated via GST-pull down, while their specific binding fragments were also confirmed. The regulation mechanism of NMMHC IIA on SREBP1 was investigated to explore downstream regulatory signaling pathways. Results Untargeted and targeted shotgun lipidomics data revealed that OGD might be the conditional factor in reshaping lipid components. Mechanistic studies showed that with the increase of OGD time, PCA analysis of lipidomics obtained from RBMCs indicated their specificity in reshaping lipid components, while ≥80% major lipid components phospholipids and sphingolipids transferred from phospholipids, sphingolipids, and neutral lipids, of which neutral lipids taken the largest proportion with OGD time course. Perturbing reprogramming of lipid composition was less susceptible to OGD condition via knockdown of NMMHC IIA of vascular endothelial cells. Knockdown of NMMHC IIA could promote tight junction defense to OGD condition. NMMHC IIA could directly bind with SREBP1, then could affect sterol regulatory element binding protein-1 to adjust lipid metabolize reprogramming of RBMCs. Conclusions Mechanistic studies showed that perturbing reprogramming of lipid composition could enhance tight junction damage, which was mediated by the opposing effects of NMMHC IIA.

High resolution three-dimensional (3D) point clouds enable the mapping of cotton boll spatial distribution, aiding breeders in better understanding the correlation between boll positions on branches and overall yield and fiber quality. This study developed a segmentation workflow for point clouds of 18 cotton genotypes to map the spatial distribution of bolls on the plants. The data processing workflow includes two independent approaches to map the vertical and horizontal distribution of cotton bolls. The vertical distribution was mapped by segmenting bolls using PointNet++ and identifying individual instances through Euclidean clustering. For horizontal distribution, TreeQSM segmented the plant into the main stem and individual branches. PointNet++ and Euclidean clustering were then used to achieve cotton boll instance segmentation. The horizontal distribution was determined by calculating the Euclidean distance of each cotton boll relative to the main stem. Additionally, branch types were classified using point cloud meshing completion and the Dijkstra shortest path algorithm. The results highlight that the accuracy and mean intersection over union (mIoU) of the 2-class segmentation based on PointNet++ reached 0.954 and 0.896 on the whole plant dataset, and 0.968 and 0.897 on the branch dataset, respectively. The coefficient of determination (R 2 ) for the boll counting was 0.99 with a root mean squared error (RMSE) of 5.4. For the first time, this study accomplished high-granularity spatial mapping of cotton bolls and branches, but directly predicting fiber quality from 3D point clouds remains a challenge. This method provides a promising tool for 3D cotton plant mapping of different genotypes, which potentially could accelerate plant physiological studies and breeding programs.