Explore the vast range of titles available.

Fine-grained image classification is a challenging task because of the difficulty in identifying discriminant features, it is not easy to find the subtle features that fully represent the object. In the fine-grained classification of crop disease, visual disturbances such as light, fog, overlap, and jitter are frequently encountered. To explore the influence of the features of crop leaf images on the classification results, a classification model should focus on the more discriminative regions of the image while improving the classification accuracy of the model in complex scenes. This paper proposes a novel attention mechanism that effectively utilizes the informative regions of an image, and describes the use of transfer learning to quickly construct several fine-grained image classification models of crop disease based on this attention mechanism. This study uses 58,200 crop leaf images as a dataset, including 14 different crops and 37 different categories of healthy/diseased crops. Among them, different diseases of the same crop have strong similarities. The NASNetLarge fine-grained classification model based on the proposed attention mechanism achieves the best classification effect, with an F 1 score of up to 93.05%. The results show that the proposed attention mechanism effectively improves the fine-grained classification of crop disease images.

Plant biomass is a highly abundant renewable resource that can be converted into several types of high-value-added products, including chemicals, biofuels and advanced materials. In the last few decades, an increasing number of biomass species and processing techniques have been developed to enhance the application of plant biomass followed by the industrial application of some of the products, during which varied technologies have been successfully developed. In this review, we summarize the different sources of plant biomass, the evolving technologies for treating it, and the various products derived from plant biomass. Moreover, the challenges inherent in the valorization of plant biomass used in high-value-added products are also discussed. Overall, with the increased use of plant biomass, the development of treatment technologies, and the solution of the challenges raised during plant biomass valorization, the value-added products derived from plant biomass will become greater in number and more valuable.

Background WRKY transcription factors, so named because of the WRKYGQK heptapeptide at the N-terminal end, are widely distributed in plants and play an important role in physiological changes and response to biotic and abiotic stressors. Many previous studies have focused on the evolution of WRKY transcription factors in a given plant; however, little is known about WRKY evolution in legumes. The gene expression pattern of duplicated WRKY transcription factors remains unclear. Results We first identified the WRKY proteins in 12 legumes. We found that the WRKYGQK heptapeptide tended to mutate into WRKYGKK. The Q site in WRKYGQK preferentially mutated, while W, K, and Y were conserved. The phylogenetic tree shows that the WRKY proteins in legumes have multiple origins, especially group IIc. For example, WRKY64 from Lupinus angustifolius (LaWRKY64) contains three WRKY domains, of which the first two clustered together in the N-terminal WRKY domain of the group I WRKY protein, and the third WRKY domain grouped in the C-terminal WRKY domain of the group I WRKY protein. Orthologous WRKY genes have a faster evolutionary rate and are subject to constrained selective pressure, unlike paralogous WRKY genes. Different gene features were observed between duplicated WRKY genes and singleton WRKY genes. Duplicated Glycine max WRKY genes with similar gene features have gene expression divergence. Conclusions We analyzed the WRKY number and type in 12 legumes, concluding that the WRKY proteins have multiple origins. A novel WRKY protein, LaWRKY64, was found in L. angustifolius . The first two WRKY domains of LaWRKY64 have the same origin. The orthologous and paralogous WRKY proteins have different evolutionary rates. Duplicated WRKY genes have gene expression divergence under normal growth conditions in G. max . These results provide insight into understanding WRKY evolution and expression.

The self-powered photoelectrochemical components themselves featured advancements in operating independently without external supply. Ultimately, due to lack of assistance from the external bias, the photoelectrochemical response is commonly restricted by the deficient photo-quantum efficiency for the absence of carrier multiplication. This work demonstrates a self-powered photoelectrochemical photodetector based on CuO x /AlGaN nanowires with staggered band structure and enhanced built-in potential for efficient exciton extraction. The generated multiple excitons within reach-through CuO x layer could be speedily separated before Auger recombination. This yields a 131.5% external quantum efficiency and 270.6 mA W −1 responsivity at 255 nm. The work confirms the role of multiple exciton generation in photoelectrochemical systems, offering a solution on paving path of advance for self-powered optoelectronics and weak-light UV imaging applications. Xue et al. report self-powered photoelectrochemical photodetectors based on CuOx decorated AlGaN nanowires with staggered energy band structure. High-energy photons can be absorbed by CuOx to trigger the multiexciton generation effect, enabling an external quantum efficiency of 131.5% at 255 nm.

Background Rice bacterial blight (BB) has caused serious damage in rice yield and quality leading to huge economic loss and food safety problems. Breeding disease resistant cultivar becomes the eco-friendliest and most effective alternative to regulate its outburst, since the propagation of pathogenic bacteria is restrained. However, the BB resistance cultivar selection suffers tremendous labor cost, low efficiency, and subjective human error. And dynamic rice BB phenotyping study is absent from exploring the pattern of BB growth with different genotypes. Results In this paper, with the aim of alleviating the labor burden of plant breeding experts in the resistant cultivar screening processing and exploring the disease resistance phenotyping variation pattern, visible/near-infrared (VIS–NIR) hyperspectral images of rice leaves from three varieties after inoculation were collected and sent into a self-built deep learning model LPnet for disease severity assessment. The growth status of BB lesion at the time scale was fully revealed. On the strength of the attention mechanism inside LPnet, the most informative spectral features related to lesion proportion were further extracted and combined into a novel and refined leaf spectral index. The effectiveness and feasibility of the proposed wavelength combination were verified by identifying the resistant cultivar, assessing the resistant ability, and spectral image visualization. Conclusions This study illustrated that informative VIS–NIR spectrums coupled with attention deep learning had great potential to not only directly assess disease severity but also excavate spectral characteristics for rapid screening disease resistant cultivars in high-throughput phenotyping.

The accurate classification of crop pests and diseases is essential for their prevention and control. However, datasets of pest and disease images collected in the field usually exhibit long-tailed distributions with heavy category imbalance, posing great challenges for a deep recognition and classification model. This paper proposes a novel convolutional rebalancing network to classify rice pests and diseases from image datasets collected in the field. To improve the classification performance, the proposed network includes a convolutional rebalancing module, an image augmentation module, and a feature fusion module. In the convolutional rebalancing module, instance-balanced sampling is used to extract features of the images in the rice pest and disease dataset, while reversed sampling is used to improve feature extraction of the categories with fewer images in the dataset. Building on the convolutional rebalancing module, we design an image augmentation module to augment the training data effectively. To further enhance the classification performance, a feature fusion module fuses the image features learned by the convolutional rebalancing module and ensures that the feature extraction of the imbalanced dataset is more comprehensive. Extensive experiments in the large-scale imbalanced dataset of rice pests and diseases (18,391 images), publicly available plant image datasets (Flavia, Swedish Leaf, and UCI Leaf) and pest image datasets (SMALL and IP102) verify the robustness of the proposed network, and the results demonstrate its superior performance over state-of-the-art methods, with an accuracy of 97.58% on rice pest and disease image dataset. We conclude that the proposed network can provide an important tool for the intelligent control of rice pests and diseases in the field.

The object detection method based on deep learning convolutional neural network (CNN) significantly improves the detection performance of wheat head on wheat images obtained from the near ground. Nevertheless, for wheat head images of different stages, high density, and overlaps captured by the aerial-scale unmanned aerial vehicle (UAV), the existing deep learning-based object detection methods often have poor detection effects. Since the receptive field of CNN is usually small, it is not conducive to capture global features. The visual Transformer can capture the global information of an image; hence we introduce Transformer to improve the detection effect and reduce the computation of the network. Three object detection networks based on Transformer are designed and developed, including the two-stage method FR-Transformer and the one-stage methods R-Transformer and Y-Transformer. Compared with various other prevalent object detection CNN methods, our FR-Transformer method outperforms them by 88.3% for AP50 and 38.5% for AP75. The experiments represent that the FR-Transformer method can gratify requirements of rapid and precise detection of wheat heads by the UAV in the field to a certain extent. These more relevant and direct information provide a reliable reference for further estimation of wheat yield.

Inflammation is involved in cerebral ischemia/reperfusion (I/R)-induced neurological damage. Saikosaponin A (SSa), extracted from , has been reported to exert anti-inflammatory effects. This article aimed to investigate whether SSa could ameliorate neuroinflammation mediated by ischemic stroke and the underlying mechanism. Rat middle cerebral artery occlusion (MCAO) model was employed in this study, and the cognitive and motor functions were detected by behavioral tests. Inflammatory cytokines in the serum were detected by ELISA kits. The expression levels of Toll-like receptor 4 (TLR4), nuclear factor-kappa B (NF-κB), and high-mobility group box 1 (HMGB1) in the brain tissues were assayed with Western blot. Our results showed that SSa pretreatment could significantly reduce brain damage, improve neurological function recovery, and decrease the water content of brain tissues when compared with the model group. SSa pretreatment significantly reduced the serum HMGB1 level and downregulated the contents of inflammatory cytokines including tumor necrosis factor-α, interleukin-1 beta, and interleukin-6. Furthermore, SSa pretreatment could attenuate the decreased TLR4 and nucleus NF-κB in the brain of MCAO rats. The protein level of HMGB1 in the nucleus was significantly upregulated in the SSa pretreatment group. Our results suggested that the pretreatment with SSa provided significant protection against cerebral I/R injury in rats via its anti-inflammation property by inhibiting the nucleus HMGB1 release.

Melatonin is an important, multifunctional protective agent against a variety of abiotic and biotic stressors in plants. Caffeic acid O-methyltransferase (COMT) catalyzes the last step of melatonin synthesis in plants and reportedly participates in the regulation of stress response and tolerance. However, few studies have reported its function in melatonin-mediated drought resistance. In this study, CrCOMT was identified and was strongly induced by drought stress in Carex rigescens . CrCOMT overexpression in transgenic tobacco increased tolerance to drought stress with high levels of seed germination, relative water content, and survival rates. CrCOMT overexpression in tobacco improved membrane stability, and plants exhibited lower relative electrolytic leakage and malondialdehyde content, as well as higher photochemical efficiency than the wildtype (WT) under drought stress. The transgenic plants also had higher levels of proline accumulation and antioxidant enzyme activity, which decreased oxidative stress damage due to reactive oxygen species (ROS) hyperaccumulation under drought stress. The transcription of drought stress response and ROS scavenging genes was significantly higher in the CrCOMT overexpression plants than in the WT plants. In addition, CrCOMT transgenic tobacco plants exhibited higher melatonin content under drought stress conditions. Exogenous melatonin was applied to C. rigescens under drought stress to confirm the function of melatonin in mediating drought tolerance; the relative water content and proline content were higher, and the relative electrolytic leakage was lower in melatonin-treated C. rigescens than in the untreated plants. In summary, these results show that CrCOMT plays a positive role in plant drought stress tolerance by regulating endogenous melatonin content.

Background Pumpkin seeds are major oil crops with high nutritional value and high oil content. The collection and identification of different pumpkin germplasm resources play a significant role in the realization of precision breeding and variety improvement. In this research, we collected 75 species of pumpkin from the Zhejiang Province of China. 35,927 near-infrared hyperspectral images of 75 types of pumpkin seeds were used as the research object. Results To realize the rapid classification of pumpkin seed varieties, position attention embedded three-dimensional convolutional neural network (PA-3DCNN) was designed based on hyperspectral image technology. The experimental results showed that PA-3DCNN had the best classification effect than other classical machine learning technology. The classification accuracy of 99.14% and 95.20% were severally reached on the training and test sets. We also demonstrated that the PA-3DCNN model performed well in next year’s classification with fine-tuning and met with 94.8% accuracy. Conclusions The model performance improved by introducing double convolution and pooling structure and position attention module. Meanwhile, the generalization performance of the model was verified, which can be adopted for the classification of pumpkin seeds in multiple years. This study provided a new strategy and a feasible technical approach for identifying germplasm resources of pumpkin seeds.