Black rot, Black measles, Leaf blight and Mites of grape are four common grape leaf diseases that seriously affect grape yield. However, the existing research lacks a real-time detecting method for ...grape leaf diseases, which cannot guarantee the healthy growth of grape plants. In this article, a real-time detector for grape leaf diseases based on improved deep convolutional neural networks is proposed. This article first expands the grape leaf disease images through digital image processing technology, constructing the grape leaf disease dataset (GLDD). Based on GLDD and the Faster R-CNN detection algorithm, a deep-learning-based Faster DR-IACNN model with higher feature extraction capability is presented for detecting grape leaf diseases by introducing the Inception-v1 module, Inception-ResNet-v2 module and SE-blocks. The experimental results show that the detection model Faster DR-IACNN achieves a precision of 81.1% mAP on GLDD, and the detection speed reaches 15.01 FPS. This research indicates that the real-time detector Faster DR-IACNN based on deep learning provides a feasible solution for the diagnosis of grape leaf diseases and provides guidance for the detection of other plant diseases.
Obesity has been recognized as a major risk factor for chronic kidney disease, but the underlying mechanism remains elusive. Here, we investigated the mechanism whereby long-term high-fat diet (HFD) ...feeding induces renal injury in mice. The C57BL/6 mice fed HFD for 16 weeks developed obesity, diabetes, and kidney dysfunction manifested by albuminuria and blood accumulation of BUN and creatinine. The HFD-fed kidney showed marked glomerular and tubular injuries, including prominent defects in the glomerular filtration barrier and increased tubular cell apoptosis. Mechanistically, HFD feeding markedly increased triglyceride and cholesterol contents in the kidney and activated lipogenic pathways for cholesterol and triglyceride synthesis. HFD feeding also increased oxidative stress and induced mitochondrial fission in tubular cells, thereby activating the pro-apoptotic pathway. In HK-2 and mesangial cell cultures, high glucose, fatty acid, and TNF-α combination was able to activate the lipogenic pathways, increase oxidative stress, promote mitochondrial fission, and activate the pro-apoptotic pathway, all of which could be attenuated by an inhibitor that depleted reactive oxygen species. Taken together, these observations suggest that long-term HFD feeding causes kidney injury at least in part as a result of tissue lipid accumulation, increased oxidative stress, and mitochondrial dysfunction, which promote excess programmed cell death.
The identification of grape leaf diseases based on deep learning is critical to controlling the spread of diseases and ensuring the healthy development of the grape industry. Focusing on the lack of ...training images of grape leaf diseases, this paper proposes a novel model named Leaf GAN, which is based on generative adversarial networks (GANs), to generate images of four different grape leaf diseases for training identification models. A generator model with degressive channels is first designed to generate grape leaf disease images; then, the dense connectivity strategy and instance normalization are fused into an efficient discriminator to identify real and fake disease images by utilizing their excellent feature extraction capability on grape leaf lesions. Finally, the deep regret gradient penalty method is applied to stabilize the training process of the model. Using a total of 4,062 grape leaf disease images, the Leaf GAN model ultimately generates 8,124 grape leaf disease images. The generated grape leaf disease images based on Leaf GAN model can obtain better performance than DCGAN and WGAN in terms of the Fréchet inception distance. The experimental results show that the proposed Leaf GAN model generates sufficient grape leaf disease images with prominent lesions, providing a feasible solution for the data augmentation of grape leaf disease images. For the eight prevailing classification models with the expanded dataset, the identification performance based on CNNs indicated higher accuracies, whereby all the accuracies were better than those of the initial dataset with other data augmentation methods. Among them, Xception achieves a recognition accuracy of 98.70% on the testing set. The results demonstrate that the proposed data augmentation method represents a new approach to overcoming the overfitting problem in disease identification and can effectively improve the identification accuracy.
Recently, networks consider spectral-spatial information in multiscale inputs less, even though there are some networks that consider this factor, however these networks cannot guarantee to get ...optimal features, which are extracted from each scale input. Furthermore, these networks do not consider the complementary and related information among different scale features. To address these issues, a multiscale deep middle-level feature fusion network (MMFN) is proposed in this paper for hyperspectral classification. In MMFN, the network fully fuses the strong complementary and related information among different scale features to extract more discriminative features. The training of network contains two stages: the first stage obtains the optimal models corresponding to different scale inputs and extracts the middle-level features under the corresponding scale model. It can guarantee the multiscale middle-level features are optimal. The second stage fuses the optimal multiscale middle-level features in the convolutional layer, and the subsequent residual blocks can learn the complementary and related information among different scale middle-level features. Moreover, the idea of identity mapping in residual learning can help the network obtain a higher accuracy when the network is deeper. The effectiveness of our method is proved on four HSI data sets and the experimental results show that our method outperforms the other state-of-the-art methods especially with small training samples.
Pesticide residue is an important factor that affects food safety. In order to achieve effective detection of pesticide residues in apples, a machine-vision-based segmentation algorithm and ...hyperspectral techniques were used to segment the foreground and background regions of the apple image. By calculating the roundness value and extracting the region with the highest roundness value in the connected region, a region of interest (ROI) mask was created for the apple. Four pesticides (chlorpyrifos, carbendazim and two mixed pesticides) and an inactive control were used at the same concentration of 100 ppm (except for the control group), and the hyperspectral region of the corresponding sample image was extracted by obtaining the different types of pesticide residues in the ROI masks. To increase the diversity of the samples and to expand the dataset, Gaussian white noise with a varying signal-to-noise ratio was added to each of the hyperspectral images of the apple. The number of samples was increased from four types of 12 samples to four types of 72 samples, giving 4608 hyperspectral data images in each category. The structure and parameters of a convolutional neural network (CNN) were determined using theoretical analysis and experimental verification. All the extracted hyperspectral images of apples were normalized to 227 × 227 × 3 pixels as the input of the CNN network for pesticide residue detection. There were 18,432 sample data of four types for 72 samples. Of these, 12,288 images were selected using a bootstrap sampling method as the training set, and 6144 as the test set, with no overlap. The test results show that when the number of training epochs was 10, the accuracy of the test set detection was 99.09%, and the detection accuracy of the single-band average image was 95.35%. A comparison with traditional k-nearest neighbor (KNN) and support vector machine classification algorithms showed that the detection accuracy for KNN was 43.75% and the average time was 0.7645 s. These results demonstrate that our method is a small-sample, non-contact, fast, effective and low-cost technique that can provide effective pesticide residue detection in postharvest apples.
•AlexNet-CNNs deep learning network was applied for pesticide detection of postharvest apples.•The method is of short time consumption and good noise immunity property.•The accuracy of the proposed method for apple pesticide detection was 99.09%.
The alkali-aggregate reaction (AAR) is a harmful chemical reaction that reduces the mechanical properties and weakens the durability of concrete. Different types of activated aggregates may result in ...various AAR modes, which affect the mechanical deterioration of concrete. In this paper, the aggregate expansion model and the gel pocket model are considered to represent the two well-recognized AAR modes. The mesoscale particle model of concrete was presented to model the AAR expansion process and the splitting tensile behavior of AAR-affected concrete. The numerical results show that different AAR modes have a great influence on the development of AAR in terms of expansion and microcracks and the deterioration of concrete specimens. The AAR mode of the gel pocket model causes slight expansion, but generates microcracks in the concrete at the early stage of AAR. This means there is difficulty in achieving early warning and timely maintenance of AAR-affected concrete structures based on the monitoring expansion. Compared with the aggregate expansion model, more severe cracking can be observed, and a greater loss of tensile strength is achieved at the same AAR expansion in the gel pocket model. AAR modes determine the subsequent reaction process and deterioration, and thus, it is necessary to develop effective detection methods and standards for large concrete projects according to different reactive aggregates.
Deep learning has attracted extensive attention in the field of hyperspectral images (HSIs) classification. However, supervised deep learning methods heavily rely on a large amount of label ...information. To address this problem, in this paper, we propose a two-stage deep domain adaptation method for hyperspectral image classification, which can minimize the data shift between two domains and learn a more discriminative deep embedding space with very few labeled target samples. A deep embedding space is first learned by minimizing the distance between the source domain and the target domain based on Maximum Mean Discrepancy (MMD) criterion. The Spatial–Spectral Siamese Network is then exploited to reduce the data shift and learn a more discriminative deep embedding space by minimizing the distance between samples from different domains but the same class label and maximizes the distance between samples from different domains and class labels based on pairwise loss. For the classification task, the softmax layer is replaced with a linear support vector machine, in which learning minimizes a margin-based loss instead of the cross-entropy loss. The experimental results on two sets of hyperspectral remote sensing images show that the proposed method can outperform several state-of-the-art methods.
The third plague pandemic originated from Yunnan Province, China in the middle of the 19th century. The last human plague epidemic in Yunnan occurred from 1986-2005. On June 6, 2016, a case of human ...plague was reported in the Xishuangbanna Prefecture, Yunnan. The patient suffered from primary septicemic plague after exposure to a dead house rat (Rattus flavipectus), which has been identified as the main plague reservoir in the local epizootic area. Moreover, a retrospective investigation identified another bubonic plague case in this area. Based on these data, human plague reemerged after a silent period of ten years. In this study, three molecular typing methods, including a clustered regularly interspaced short palindromic repeats (CRISPR) analysis, different region analysis (DFR), and multiple-locus variable number of tandem repeats analysis (MLVA), were used to illustrate the molecular characteristics of Yersinia pestis (Y. pestis) strains isolated in Yunnan. The DFR profiles of the strains isolated in Yunnan in 2016 were the same as the strains that had previously been isolated in this Rattus flavipectus plague focus. The c3 spacer present in the previously isolated strains was absent in the spacer arrays of the Ypc CRISPR loci of the strains isolated in 2016. The MLVA analysis using MLVA (14+12) showed that the strains isolated from the human plague case and host animal plague infection in 2016 in Yunnan displayed different molecular patterns than the strains that had previously been isolated from Yunnan and adjacent provinces.
The Green Technology Innovation Behavior (GTIB) of construction enterprises is crucial for promoting green development in the construction industry. In order to clarify the mechanism of action ...affecting the GTIB of construction enterprises, this paper considers the context of green development in the construction industry based on the vector autoregressive model and constructs a theoretical model of GTIB in construction enterprises. Time series data collected by the Chinese government (2000–2018) were used to analyze the mechanism of action of the factors influencing the GTIB of construction enterprises by EViews 10.0. The results of the paper showed the following: (1) direct government investment has the greatest impact on the GTIB of construction enterprises and has made a positive contribution; (2) the added value of Gross Domestic Product (GDP) of the construction industry has a relatively small impact on the GTIB of construction enterprises; (3) the role of environmental regulation on the GTIB of construction enterprises is non-linear. This paper further broadens the research to the factors influencing the GTIB of construction enterprises. Meanwhile, this paper provides a reference basis for local governments to formulate policies related to the GTIB of construction enterprises.
Abstract
The green development behavior of construction enterprises is an environmental behavior that contributes evidence from construction enterprises to the field of resource recycling and ...environmental protection. Revealing the mechanism of green development behavior of construction enterprises has become the key to guide construction enterprises to adopt green development behavior and improve the level of green development. However, existing studies on the mechanistic discussion of green development behavior of construction enterprises do not reach a consensus. In order to reveal the mechanism of the green development behavior of construction enterprises, this study examines how the green development behavior of construction enterprises is influenced by factors based on the Theory of Planned Behavior. Using partial least squares structural equation modeling (PLS-SEM), this study analyzed 306 questionnaire data points from construction enterprises in 28 provinces (cities) across China. The main conclusions are as follows. (1) Attitudes, subjective norms and perceived behavioral control have significant positive effects on the green development behavioral intentions of construction enterprises, with attitudes being the strongest predictor. (2) Intention intermediates the relationships between attitude, subjective norms, perceived behavioral control, and the green development behavior of construction enterprises to varying degrees. (3) Regional green development level and enterprise size positively moderate the four groups of the relationship between attitude, subjective norms, perceived behavioral control, intention and green development behavior of construction enterprises. This study provides theoretical guidance for promoting green transformation and upgrading construction enterprises and helps the construction industry achieve a balanced mode of development that supports both economic growth and environmental protection.