FCA-ResNet: An Improved Model with Enhanced Multi-Scale Feature Fusion and Coordinate Attention for Wheat Leaf Disease Classification

Complex pest and disease features appearing during the growth of wheat crops are difficult to capture and can seriously affect the normal growth of wheat crops. The existing methods ignore the full pre-interaction of deep and shallow features, which largely affects the accuracy of identification. To address the above problems and needs, we rethink the feature representation and attention mechanism in intelligent recognition of wheat leaf diseases and pests, and propose a representation and recognition network (RReNet) based on the feature attention mechanism. RReNet captures key information more efficiently by focusing on complex pest and disease characteristics and fusing multi-semantic feature information. In addition, RReNet further enhances the perception of complex disease and pest features by using four layers of detection units and fast IoU loss function, which significantly improves the accuracy and robustness of wheat leaf disease and pest recognition. Tests on a challenging wheat leaf pest and disease dataset with twelve pest and disease types show that RReNet achieves precision, recall and mAP as high as 94.1%, 95.7% and 98.3% respectively. Also, ablation experiments proved the effectiveness of all parts of the proposed method.

Recognition of rice leaf diseases and wheat leaf diseases based on multi-task deep transfer learning

In today’s leaf disease detection, the accuracy of recognition has never been of such importance as it is now. In this aspect, leaf disease recognition method based on machine learning relies heavily on the size of the region of interest and the dispersion of lesions. Professional instrument for leaf disease detection remains a challenging task in accuracy and convenience. A new lightweight model based on advanced residual network and attention mechanism for extracting more accurate region of interest and the lesion, SE-VRNet, was proposed. The proposed SE-VRNet incorporated deep variant residual network (VRNet) and a squeeze-and-excitation (SE) module with attention mechanism, in order to solve the problem that the feature extraction was difficult due to the dispersed location of the leaf disease. The accuracy of top-1 and top-3 obtained by the model SE-VRNet on NewData is 99.73% and 99.98%, respectively, and the accuracy of top-1 and top-3 obtained by the model on SelfData is 95.71% and 99.89%, respectively. The experimental results on the datasets of PlantVillage, OriData, NewData and SelfData were better than other state-of-the-art methods, demonstrating the effectiveness and feasibility of the proposed SE-VRNet in identifying leaf diseases with mobile devices.

Soybean is an important oil crop and plant protein source, and phenotypic traits' detection for soybean diseases, which seriously restrict yield and quality, is of great significance for soybean breeding, cultivation, and fine management. The recognition accuracy of traditional deep learning models is not high, and the chemical analysis operation process of soybean diseases is time-consuming. In addition, artificial observation and experience judgment are easily affected by subjective factors and difficult to guarantee the accuracy of the objective. Thus, a rapid identification method of soybean diseases was proposed based on a new residual attention network (RANet) model. First, soybean brown leaf spot, soybean frogeye leaf spot, and soybean phyllosticta leaf spot were used as research objects, the OTSU algorithm was adopted to remove the background from the original image. Then, the sample dataset of soybean disease images was expanded by image enhancement technology based on a single leaf image of soybean disease. In addition, a residual attention layer (RAL) was constructed using attention mechanisms and shortcut connections, which further embedded into the residual neural network 18 (ResNet18) model. Finally, a new model of RANet for recognition of soybean diseases was established based on attention mechanism and idea of residuals. The result showed that the average recognition accuracy of soybean leaf diseases was 98.49%, and the F1-value was 98.52 with recognition time of 0.0514 s, which realized an accurate, fast, and efficient recognition model for soybean leaf diseases.

A diagnosis model of soybean leaf diseases based on improved residual neural network

Oil painting image style recognition based on ResNet-NTS network

Big data for social transportation brings unprecedented opportunities for us to solve the transportation problems that cannot be solved by traditional methods and build the next generation of the intelligent transportation system (ITS). As one of the important functions of the ITS, supply-demand difference prediction for autonomous vehicles provides a decision basis for its control. In this article, a new learning process is proposed with Multiple feature Extraction and Fusion utilizing the combination of deep and shallow Features (MEFF) (the spatial deep features, (short and long) temporal deep features, and fuzzy shallow (semantic) features). The spatial deep features are captured with residual network and dimension reduction in spatial deep block. The fuzzy shallow (semantic) features are captured with multiattention fuzzy mechanism in the fuzzy shallow block. With the fused spatial deep features and fuzzy shallow features, the temporal deep features are captured with long short-term memory (LSTM) and attention mechanism in the temporal and prediction block to get the final prediction results. Based on two different distributions of membership attention (mean distribution and Gaussian distribution) in the fuzzy shallow block, our process MEFF has two methods, i.e., MEFF-mean method and MEFF-Gaussian method. Extensive experiments show that our methods provide more accurate and stable prediction results than the existing state-of-art-methods.

Within the context of rapidly progressing industrial sectors, rolling bearings have become a fundamental component across an array of mechanical systems. Their fault detection and remaining useful life (RUL) estimations are vital for ensuring industrial production safety. Yet, the understated characteristics of early-stage, minor faults in bearing degradation often escape detection. Additionally, numerous existing networks overlook the critical information embedded in multi-scale features, consequently diminishing the accuracy of predictions and classifications. The present study proposes MM-InfoGAN (multi-branch residual feature fusion and multi-objective optimization information maximization generative adversarial network), an innovative approach for intelligent fault detection and RUL prediction to address these issues. MM-InfoGAN augments the network’s ability to extract bearing fault characteristics and RUL data, employing a multi-branch residual feature fusion network structure coupled with an attention mechanism. Moreover, it refines the weight allocation strategy for geometric loss and introduces a novel loss function. This function optimizes weight distribution during the GAN’s training phase, expediting the attainment of network equilibrium. The efficacy of the comprehensive MM-InfoGAN model and its integrated modules was substantiated through comparative and ablation experiments conducted on the XJTU-SY dataset and IMS Bearing dataset.

Specific emitter identification technology plays a very important role in spectrum resource management, wireless network security, cognitive radio etc. However, in complex electromagnetic environments, the variability and uncertainty of signals make it very difficult to extract representative feature representations of the signals. At the same time, the feature extraction capability of the recognition model is also a factor that needs to be considered. To address these issues, a wavelet residual neural network model based on attention mechanism is proposed for specific emitter identification. First, multi‐level wavelet decomposition is performed on all received signals to obtain their wavelet detail coefficients at different scales. Next, all the wavelet detail coefficients are used as the feature input for the attention‐based residual network, and perform parallel feature extraction at multi scales. Finally, the feature representation capability of all coefficients are compared, and the model's recognition results based on it are obtained. The recognition rates on the three datasets are 94.7%, 93.21%, and 86.1%, respectively, all of which are superior to recent state‐of‐the‐art algorithms. In addition, through ablation experiment, the validity of each component of the model has been verified.

ProblemGarlic is a common ingredient that not only enhances the flavor of dishes but also has various beneficial effects and functions for humans. However, its leaf diseases and pests have a serious impact on the growth and yield. Traditional plant leaf disease detection methods have shortcomings, such as high time consumption and low recognition accuracy.MethodologyAs a result, we present a deep learning approach based on an upgraded ResNet18, triplet, convolutional block (RTCB) attention mechanism for recognizing garlic leaf diseases. First, we replace the convolutional layers in the residual block with partial convolutions based on the classic ResNet18 architecture to improve computational efficiency. Then, we introduce triplet attention after the first convolutional layer to enhance the model’s ability to focus on key features. Finally, we add a convolutional block attention mechanism after each residual layer to improve the model’s feature perception.ResultsThe experimental results demonstrate that the proposed model achieves a classification accuracy of 98.90%, which is superior to outstanding deep learning models such as Efficient-v2-B0, MobileOne-S0, OverLoCK-S, EfficientFormer, and MobileMamba. The proposed RTCB has a faster computation speed, higher recognition precision, and stronger generalization ability.ContributionThe proposed approach provides a scalable technical reference for the engineering application of automatic disease monitoring and control in intelligent agriculture. The current strategy is conducive to the deployment of edge computing equipment and has extensive significance and application potential in plant leaf disease detection.

Classification of infection grade for anthracnose in mango leaves under complex background based on CBAM-DBIRNet

Accurate diagnosis of various lesions in the formation stage of gastric cancer is an important problem for doctors. Automatic diagnosis tools based on deep learning can help doctors improve the accuracy of gastric lesion diagnosis. Most of the existing deep learning-based methods have been used to detect a limited number of lesions in the formation stage of gastric cancer, and the classification accuracy needs to be improved. To this end, this study proposed an attention mechanism feature fusion deep learning model with only 14 million (M) parameters. Based on that model, the automatic classification of a wide range of lesions covering the stage of gastric cancer formation was investigated, including non-neoplasm(including gastritis and intestinal metaplasia), low-grade intraepithelial neoplasia, and early gastric cancer (including high-grade intraepithelial neoplasia and early gastric cancer). 4455 magnification endoscopy with narrow-band imaging(ME-NBI) images from 1188 patients were collected to train and test the proposed method. The results of the test dataset showed that compared with the advanced gastric lesions classification method with the best performance (overall accuracy = 94.3%, parameters = 23.9 M), the proposed method achieved both higher overall accuracy and a relatively lightweight model (overall accuracy =95.6%, parameter = 14 M). The accuracy, sensitivity, and specificity of low-grade intraepithelial neoplasia were 94.5%, 93.0%, and 96.5%, respectively, achieving state-of-the-art classification performance. In conclusion, our method has demonstrated its potential in diagnosing various lesions at the stage of gastric cancer formation.

Human epidermal growth factor receptor 2 (HER2)-positive breast cancer is an aggressive cancer type that requires special diagnosis and treatment methods. Immunohistochemistry (IHC) staining effectively highlights relevant morphological structures within histopathological images yet can be expensive in terms of both labor and required laboratory equipment. Hematoxylin and eosin (H&E) images are more readily available and less expensive than IHC images as they are routinely performed for all patient samples. Lightweight models are well-suited for deployment on resource-constrained devices such as mobile phones and embedded systems, making them ideal for real-time diagnosis in rural regions and developing countries. In this study, IHC images are compared to H&E images for automatic HER2 scoring using lightweight deep models that incorporate several advanced techniques including network pruning, domain adaptation, and attention mechanisms. Two lightweight models are presented: PrunEff4 and ATHER2. PrunEff4 is a subset of EfficientNetV2B0 pruned to reduce the network parameters by ~80%. ATHER2 is a customized lightweight network that employs different sized convolutional filters along with a convolutional block attention module (CBAM). For PrunEff4 and ATHER2, transfer learning (pretraining on ImageNet) and domain-specific pretraining were employed, respectively. Different datasets were utilized in the development and final testing phases in order to effectively evaluate their generalization capability. In all experiments, both networks resulted in accuracies ranging from 97% to 100% for binary classifications and from 95.5% to 98.5% for multiclass classifications regardless of whether IHC or H&E images were utilized. Network pruning significantly reduced the network parameters whilst maintaining reliable performance. Domain-specific pretraining significantly enhanced performance, particularly in complex classification tasks such as HER2 scoring using H&E images and multiclass classifications. Both IHC and H&E stained images were suitable for deep learning-based HER2 scoring, given that the deep networks are efficiently trained for the specified task.

This paper focuses on detecting leaf diseases in wheat plants from the beginning to the end of the plant's life cycle. It highlights the best techniques for detecting various types of wheat leaf diseases and emphasizes the use of computer vision, image processing, and machine learning. The main focus is on classifying these diseases through deep convolutional neural networks, a popular image recognition and classification approach. The paper reviews various techniques for classifying image-based wheat leaf diseases, including spot blotch, stripe rust, brown rust, and powdery mildew. The paper aims to summarize the state-of-the-art techniques for detecting wheat leaf diseases.

Clinically, red blood cell abnormalities are closely related to tumor diseases, red blood cell diseases, internal medicine, and other diseases. Red blood cell classification is the key to detecting red blood cell abnormalities. Traditional red blood cell classification is done manually by doctors, which requires a lot of manpower produces subjective results. This paper proposes an Attention-based Residual Feature Pyramid Network (ARFPN) to classify 14 types of red blood cells to assist the diagnosis of related diseases. The model performs classification directly on the entire red blood cell image. Meanwhile, a spatial attention mechanism and channel attention mechanism are combined with residual units to improve the expression of category-related features and achieve accurate extraction of features. Besides, the RoI align method is used to reduce the loss of spatial symmetry and improve classification accuracy. Five hundred and eighty eight red blood cell images are used to train and verify the effectiveness of the proposed method. The Channel Attention Residual Feature Pyramid Network (C-ARFPN) model achieves an mAP of 86%; the Channel and Spatial Attention Residual Feature Pyramid Network (CS-ARFPN) model achieves an mAP of 86.9%. The experimental results indicate that our method can classify more red blood cell types and better adapt to the needs of doctors, thus reducing the doctor's time and improving the diagnosis efficiency.