Search

Crop diseases are among the major natural disasters in agricultural production that seriously restrict the growth and development of crops, threatening food security. Timely classification, accurate identification, and the application of methods suitable for the situation can effectively prevent and control crop diseases, improving the quality of agricultural products. Considering the huge variety of crops, diseases, and differences in the characteristics of diseases during each stage, the current convolutional neural network models based on deep learning need to meet the higher requirement of classifying crop diseases accurately. It is necessary to introduce a new architecture scheme to improve the recognition effect. Therefore, in this study, we optimized the deep learning-based classification model for multiple crop leaf diseases using combined transfer learning and the attention mechanism, the modified model was deployed in the smartphone for testing. Dataset that containing 10 types of crops, 61 types of diseases, and different degrees was established, the algorithm structure based on ResNet50 was designed using transfer learning and the SE attention mechanism. The classification performances of different improvement methods were compared by model training. Result indicates that the average accuracy of the proposed TL-SE-ResNet50 model is increased by 7.7%, reaching 96.32%. The model was also integrated and implemented in the smartphone and the test result of the application reaches 94.8%, and the average response time is 882 ms. The improved model proposed has a good effect on the identification of diseases and their condition of multiple crops, and the application can meet the portable usage needs of farmers. This study can provide reference for more crop disease management research in agricultural production. [ABSTRACT FROM AUTHOR]

Convolutional neural network (CNN)-based and Transformer-based methods for hyperspectral image (HSI) classification have rapidly advanced due to their unique characterization capabilities. However, the fixed kernel sizes in convolutional layers limit the comprehensive utilization of multi-scale features in HSI land cover analysis, while the Transformer's multi-head self-attention (MHSA) mechanism faces challenges in effectively encoding feature information across various dimensions. To tackle this issue, this article introduces an HSI classification method, based on multi-scale convolutional features and multi-attention mechanisms (i.e., MSCF-MAM). Firstly, the model employs a multi-scale convolutional module to capture features across different scales in HSIs. Secondly, to enhance the integration of local and global channel features and establish long-range dependencies, a feature enhancement module based on pyramid squeeze attention (PSA) is employed. Lastly, the model leverages a classical Transformer Encoder (TE) and linear layers to encode and classify the transformed spatial–spectral features. The proposed method is evaluated on three publicly available datasets—Salina Valley (SV), WHU-Hi-HanChuan (HC), and WHU-Hi-HongHu (HH). Extensive experimental results have demonstrated that the MSCF-MAM method outperforms several representative methods in terms of classification performance. [ABSTRACT FROM AUTHOR]

The work focuses on the optimization of management strategies of energy supply chain in oil–gas enterprises to find out the optimal management strategy and overcome the fragility of the traditional energy supply system. Back propagation neural network (BPNN) is applied to energy supply predicting and energy security early warning in oil–gas enterprises, and the security early warning system is designed based on the auxiliary cognitive system. The security early warning system is used to predict the peak value of oil and gas supply, and then the detection performances and the data security transmission performances of different models are compared and analysed. Finally, a comprehensive evaluation model for security management of oil–gas supply chain based on the neural network is established. It is found that compared with convolutional neural network (CNNs), the improved BPNN model algorithm proposed shows increased accuracy by 5.4%, reduced model training time and test time, and improved accuracy and recall rate. The accuracy, recall rate, and F1 value of the proposed model are 88.48%, 75.88%, and 96.21%, respectively, which were obviously higher than those of the CNN. It suggests that the improved security management model of oil–gas supply chain shows better recognition and prediction accuracy. Based on the quantitative and qualitative analysis results, the optimization suggestions for management strategies in oil–gas enterprises are put forward, which is of strategic significance for improving the security of oil–gas supply. [ABSTRACT FROM AUTHOR]

Hyperspectral image classification (HSIC) has garnered increasing attention among researchers. While classical networks like convolution neural networks (CNNs) have achieved satisfactory results with the advent of deep learning, they are confined to processing local information. Vision transformers, despite being effective at establishing long-distance dependencies, face challenges in extracting high-representation features for high-dimensional images. In this paper, we present the multiscale efficient attention with enhanced feature transformer (MEA-EFFormer), which is designed for the efficient extraction of spectral–spatial features, leading to effective classification. MEA-EFFormer employs a multiscale efficient attention feature extraction module to initially extract 3D convolution features and applies effective channel attention to refine spectral information. Following this, 2D convolution features are extracted and integrated with local binary pattern (LBP) spatial information to augment their representation. Then, the processed features are fed into a spectral–spatial enhancement attention (SSEA) module that facilitates interactive enhancement of spectral–spatial information across the three dimensions. Finally, these features undergo classification through a transformer encoder. We evaluate MEA-EFFormer against several state-of-the-art methods on three datasets and demonstrate its outstanding HSIC performance. [ABSTRACT FROM AUTHOR]

Over the past several decades, deep neural networks have been extensively applied to medical image segmentation tasks, achieving significant success. However, the effectiveness of traditional deep segmentation networks is substantially limited by the small scale of medical datasets, a limitation directly stemming from current medical data acquisition capabilities. To this end, we introduce AttEUnet, a medical cell segmentation network enhanced by edge attention, based on the Attention U-Net architecture. It incorporates a detection branch enhanced with edge attention and a learnable fusion gate unit to improve segmentation accuracy and convergence speed on small medical datasets. The AttEUnet allows for the integration of various types of prior information into the backbone network according to different tasks, offering notable flexibility and generalization ability. This method was trained and validated on two public datasets, MoNuSeg and PanNuke. The results show that AttEUnet significantly improves segmentation performance on small medical datasets, especially in capturing edge details, with F1 scores of 0.859 and 0.888 and Intersection over Union (IoU) scores of 0.758 and 0.794 on the respective datasets, outperforming both convolutional neural networks (CNNs) and transformer-based baseline networks. Furthermore, the proposed method demonstrated a convergence speed over 10.6 times faster than that of the baseline networks. The edge attention branch proposed in this study can also be added as an independent module to other classic network structures and can integrate more attention priors based on the task at hand, offering considerable scalability. [ABSTRACT FROM AUTHOR]

Despite notable advancements achieved on Hyperspectral (HS) pansharpening tasks through deep learning techniques, previous methods are inherently constrained by convolution or self-attention intrinsic defects, leading to limited performance. In this paper, we proposed an Attention-Interactive Dual-Branch Convolutional Neural Network (AIDB-Net) for HS pansharpening. Our model purely consists of convolutional layers and simultaneously inherits the strengths of both convolution and self-attention, especially the modeling of short- and long-range dependencies. Specially, we first extract, tokenize, and align the hyperspectral image (HSI) and panchromatic image (PAN) by Overlapping Patch Embedding Blocks. Then, we specialize a novel Spectral-Spatial Interactive Attention which is able to globally interact and fuse the cross-modality features. The resultant token-global similarity scores can guide the refinement and renewal of the textural details and spectral characteristics within HSI features. By deeply combined these two paradigms, our AIDB-Net significantly improve the pansharpening performance. Moreover, with the acceleration by the convolution inductive bias, our interactive attention can be trained without large scale dataset and achieves competitive time cost with its counterparts. Compared with the state-of-the-art methods, our AIDB-Net makes 5.2%, 3.1%, and 2.2% improvement on PSNR metric on three public datasets, respectively. Comprehensive experiments quantitatively and qualitatively demonstrate the effectiveness and superiority of our AIDB-Net. [ABSTRACT FROM AUTHOR]

In response to the problem that current multi-city multi-pollutant prediction methods based on one-dimensional undirected graph neural network models cannot accurately reflect the two-dimensional spatial correlations and directedness, this study proposes a four-dimensional directed graph model that can capture the two-dimensional spatial directed information and node correlation information related to multiple factors, as well as extract temporal correlation information at different times. Firstly, A four-dimensional directed GCN model with directed information graph in two-dimensional space was established based on the geographical location of the city. Secondly, Spectral decomposition and tensor operations were then applied to the two-dimensional directed information graph to obtain the graph Fourier coefficients and graph Fourier basis. Thirdly, the graph filter of the four-dimensional directed GCN model was further improved and optimized. Finally, an LSTM network architecture was introduced to construct the four-dimensional directed GCN-LSTM model for synchronous extraction of spatio-temporal information and prediction of atmospheric pollutant concentrations. The study uses the 2020 atmospheric six-parameter data of the Taihu Lake city cluster and applies canonical correlation analysis to confirm the data's temporal, spatial, and multi-factor correlations. Through experimentation, it is verified that the proposed 4D-DGCN-LSTM model achieves a MAE reduction of 1.12%, 4.91%, 5.62%, and 11.67% compared with the 4D-DGCN, GCN-LSTM, GCN, and LSTM models, respectively, indicating the good performance of the 4D-DGCN-LSTM model in predicting multiple types of atmospheric pollutants in various cities. [ABSTRACT FROM AUTHOR]

Online surface inspection systems have gradually found applications in industrial settings. However, the manual effort required to sift through a vast amount of data to identify defect images remains costly. This study delves into a self-supervised binary classification algorithm for addressing the task of defect image classification within ductile cast iron pipe (DCIP) images. Leveraging the CutPaste-Mix data augmentation strategy, we combine defect-free data with enhanced data to input into a deep convolutional neural network. Through Gaussian Density Estimation, we compute anomaly scores to achieve the classification of abnormal regions. Our approach has been implemented in real-world scenarios, involving equipment installation, data collection, and experimentation. The results demonstrate the robust performance of our method, in both the DCIP image dataset and practical field application, achieving an impressive 99.5 AUC (Area Under Curve). This presents a cost-effective means of providing data support for subsequent DCIP surface inspection model training. [ABSTRACT FROM AUTHOR]

Objective: The purpose of this study is to develop and validate a deep convolutional neural network (DCNN) model to automatically identify the manufacturer and model of hip internal fixation devices from anteroposterior (AP) radiographs. Materials and methods: In this retrospective study, 1721 hip AP radiographs, including six internal fixation devices from 1012 patients, were collected from an orthopedic center between June 2014 and June 2022 to establish a classification network. The images were divided into training set (1106 images), validation set (272 images), and test set (343 images). The model efficacy is evaluated by using the data on the test set. The overall TOP-1 accuracy, and the precision, sensitivity, specificity, and F1 score of each model are calculated, and receiver operating characteristic (ROC) curves are plotted to evaluate the model performance. Gradient-weighted class activation mapping (Grad-CAM) images are used to determine the image features that are most important for DCNN decisions. Results: A total of 1378 (80%) images were used for model development, and model efficacy was validated on a test set with 343 (20%) images. The overall TOP-1 accuracy was 98.5%. The area under the receiver operating characteristic curve (AUC) values for each internal fixation model were 1.000, 1.000, 0.980, 1.000, 0.999, and 1.000, respectively. Gradient-weighted class activation mapping showed the unique design of the internal fixation device. Conclusion: We developed a deep convolutional neural network model that can identify the manufacturer and model of hip internal fixation devices from the hip AP radiographs. [ABSTRACT FROM AUTHOR]

Metaverse applications often require many new 3D point cloud models that are unlabeled and that have never been seen before; this limited information results in difficulties for data-driven model analyses. In this paper, we propose a novel data-driven 3D point cloud analysis network GN-CNN that is suitable for such scenarios. We tackle the difficulties with a few-shot learning (FSL) approach by proposing an unsupervised generative adversarial network GN-GAN to generate prior knowledge and perform warm start pre-training for GN-CNN. Furthermore, the 3D models in the Metaverse are mostly acquired with a focus on the models' visual appearances instead of the exact positions. Thus, conceptually, we also propose to augment the information by unleashing and incorporating local variance information, which conveys the appearance of the model. This is realized by introducing a graph convolution-enhanced combined multilayer perceptron operation (CMLP), namely GCMLP, to capture the local geometric relationship as well as a local normal-aware GeoConv, namely GNConv. The GN-GAN adopts an encoder–decoder structure and the GCMLP is used as the core operation of the encoder. It can perform the reconstruction task. The GNConv is used as the convolution-like operation in GN-CNN. The classification performance of GN-CNN is evaluated on ModelNet10 with an overall accuracy of 95.9%. Its few-shot learning performance is evaluated on ModelNet40, when the training set size is reduced to 30%, the overall classification accuracy can reach 91.8%, which is 2.5% higher than Geo-CNN. Experiments show that the proposed method could improve the accuracy in 3D point cloud classification tasks and under few-shot learning scenarios, compared with existing methods such as PointNet, PointNet++, DGCNN, and Geo-CNN, making it a beneficial method for Metaverse applications. [ABSTRACT FROM AUTHOR]

With the acceleration of industrialization and urbanization, most lakes and reservoirs have been in eutrophication state. Eutrophication of water body will produce a series of environmental problems, among which cyanobacteria bloom is one of the most studied and seriously polluted problems. It is of great significance to effectively control the occurrence of cyanobacteria blooms by predicting and simulating the outbreak process of cyanobacteria blooms and accurately forecasting the relevant governance departments. However, there are two problems in the existing analysis of algal blooms: on the one hand, it is difficult to consider the impact of other factors on cyanobacteria blooms by taking chlorophyll concentration as the main influencing factor, and it is also unable to determine the relationship between various factors. On the other hand, only based on the field monitoring data research, lack of comprehensive analysis of the whole water area. The remote sensing image can reflect the change of the whole water area, but the traditional analysis method is difficult to deal with the massive remote sensing data effectively. In this study, eutrophication level was used as characterization index of cyanobacteria bloom, and the remote sensing image and its inversion map were taken as the main research data, and a new method of cyanobacteria bloom prediction based on four-dimensional (4D) fractal CNN was proposed. The prediction model uses 4D fractal CNN to extract the features of multi factor remote sensing images, capture the temporal and spatial characteristics and the interaction between multiple factors, and predict the eutrophication level of water body. In this study, a total of 216 remote sensing images of Taihu Lake Basin were selected from 29 groups with fine weather from 2009 to 2010 obtained by MODIS satellite. The simulation results show that the method proposed in this paper has excellent prediction performance, and the accuracy rate of 85.71% is better than that of common 3D CNN and 4D CNN models. [ABSTRACT FROM AUTHOR]

As the development of artificial intelligence (AI) technology, the deep-learning (DL)-based Virtual Reality (VR) technology, and DL technology are applied in human-computer interaction (HCI), and their impacts on modern film and TV works production and audience psychology are analyzed. In film and TV production, audiences have a higher demand for the verisimilitude and immersion of the works, especially in film production. Based on this, a 2D image recognition system for human body motions and a 3D recognition system for human body motions based on the convolutional neural network (CNN) algorithm of DL are proposed, and an analysis framework is established. The proposed systems are simulated on practical and professional datasets, respectively. The results show that the algorithm's computing performance in 2D image recognition is 7–9 times higher than that of the Open Pose method. It runs at 44.3 ms in 3D motion recognition, significantly lower than the Open Pose method's 794.5 and 138.7 ms. Although the detection accuracy has dropped by 2.4%, it is more efficient and convenient without limitations of scenarios in practical applications. The AI-based VR and DL enriches and expands the role and application of computer graphics in film and TV production using HCI technology theoretically and practically. [ABSTRACT FROM AUTHOR]

Feature extraction method of a phase-sensitive optical time-domain reflectometer distributed optical fiber vibration detection system requires a priori knowledge. A lack of feature evaluation methods leads to a low pattern recognition accuracy. Traditional pattern recognition methods cannot be widely applied. This paper presents the implementation of a deep learning-based method to identify vibration signal categories. First, the vibration signal was reconstructed in the time and space domain, which is regarded as a pulse scanning image. Secondly, moving average was used to reduce noise, and seeking the signal envelope surface as an image sample. Finally, the image sample was inputted into the trained convolutional neural network (CNN) to obtain recognition results. Experiments showed that the phase-sensitive optical time-domain reflectometer pulse scanning imaging pattern recognition method based on deep learning proposed in this paper improved recognition accuracy while ensuring recognition efficiency. The algorithm is easy to implement and apply and satisfies the requirements of real-time online monitoring. [ABSTRACT FROM AUTHOR]