DFN-PSAN: Multi-level deep information feature fusion extraction network for interpretable plant disease classification

With the rapid development of precision agriculture and smart agriculture, the need to build an automatic identification and detection system for diseases and insect pests is increasing. Using computers to correctly label plant diseases and insect pests is an important prerequisite for achieving accurate classification of plant diseases and insect pests and ensuring system performance. In order to improve the accuracy of computer classification of plant pests and diseases, this paper proposes an automatic pest identification method based on the Vision Transformer (ViT). In order to avoid training overfitting, the plant diseases and insect pests data sets are enhanced by methods such as Histogram Equalization, Laplacian, Gamma Transformation, CLAHE, Retinex-SSR, and Retinex-MSR. Then use the enhanced data set to train the constructed ViT neural network, so as to realize the automatic classification of plant diseases and insect pests. The simulation results show that the constructed ViT network has a test recognition accuracy rate of 96.71% on the plant disease and insect pest public data set Plant_Village, which is about 1.00% higher than the Plant disease and pest identification method based on traditional convolutional neural networks such as GoogleNet and EfficentNetV2.

This paper proposed a novel approach for detecting lung sound disorders using deep learning feature fusion. The lung sound dataset are oversampled and converted into spectrogram images. Then, extracting deep features from CNN architectures, which are pre-trained on large-scale image datasets. These deep features capture rich representations of spectrogram images from the input signals, allowing for a comprehensive analysis of lung disorders. Next, a fusion technique is employed to combine the extracted features from multiple CNN architectures totlaly 8064 feature. This fusion process enhances the discriminative power of the features, facilitating more accurate and robust detection of lung disorders. To further improve the detection performance, an improved CNN Architecture is employed. To evaluate the effectiveness of the proposed approach, an experiments conducted on a large dataset of lung disorder signals. The results demonstrate that the deep feature fusion from different CNN architectures, combined with different CNN Layers, achieves superior performance in lung disorder detection. Compared to individual CNN architectures, the proposed approach achieves higher accuracy, sensitivity, and specificity, effectively reducing false negatives and false positives. The proposed model achieves 96.03% accuracy, 96.53% Sensitivity, 99.424% specificity, 96.52% precision, and 96.50% F1 Score when predicting lung diseases from sound files. This approach has the potential to assist healthcare professionals in the early detection and diagnosis of lung disorders, ultimately leading to improved patient outcomes and enhanced healthcare practices.

The accurate recognition and early warning for plant diseases and pests are a prerequisite of intelligent prevention and control for plant diseases and pests. As a result of the phenotype similarity of the hazarded plant after plant diseases and pests occur, as well as the interference of the external environment, traditional deep learning models often face the overfitting problem in phenotype recognition of plant diseases and pests, which leads to not only the slow convergence speed of the network, but also low recognition accuracy. Motivated by the above problems, the present study proposes a deep learning model EResNet-support vector machine (SVM) to alleviate the overfitting for the recognition and classification of plant diseases and pests. First, the feature extraction capability of the model is improved by increasing feature extraction layers in the convolutional neural network. Second, the order-reduced modules are embedded and a sparsely activated function is introduced to reduce model complexity and alleviate overfitting. Finally, a classifier fused by SVM and fully connected layers are introduced to transforms the original non-linear classification problem into a linear classification problem in high-dimensional space to further alleviate the overfitting and improve the recognition accuracy of plant diseases and pests. The ablation experiments further demonstrate that the fused structure can effectively alleviate the overfitting and improve the recognition accuracy. The experimental recognition results for typical plant diseases and pests show that the proposed EResNet-SVM model has 99.30% test accuracy for eight conditions (seven plant diseases and one normal), which is 5.90% higher than the original ResNet18. Compared with the classic AlexNet, GoogLeNet, Xception, SqueezeNet and DenseNet201 models, the accuracy of the EResNet-SVM model has improved by 5.10%, 7%, 8.10%, 6.20% and 1.90%, respectively. The testing accuracy of the EResNet-SVM model for 6 insect pests is 100%, which is 3.90% higher than that of the original ResNet18 model. This research provides not only useful references for alleviating the overfitting problem in deep learning, but also a theoretical and technical support for the intelligent detection and control of plant diseases and pests. © 2024 Society of Chemical Industry.

Plant disease is an important factor affecting crop yield. With various types and complex conditions, plant diseases cause serious economic losses, as well as modern agriculture constraints. Hence, rapid, accurate, and early identification of crop diseases is of great significance. Recent developments in deep learning, especially convolutional neural network (CNN), have shown impressive performance in plant disease classification. However, most of the existing datasets for plant disease classification are a single background environment rather than a real field environment. In addition, the classification can only obtain the category of a single disease and fail to obtain the location of multiple different diseases, which limits the practical application. Therefore, the object detection method based on CNN can overcome these shortcomings and has broad application prospects. In this study, an annotated apple leaf disease dataset in a real field environment was first constructed to compensate for the lack of existing datasets. Moreover, the Faster R-CNN and YOLOv3 architectures were trained to detect apple leaf diseases in our dataset. Finally, comparative experiments were conducted and a variety of evaluation indicators were analyzed. The experimental results demonstrate that deep learning algorithms represented by YOLOv3 and Faster R-CNN are feasible for plant disease detection and have their own strong points and weaknesses.

<span id="docs-internal-guid-01580d49-7fff-6f2a-70d1-7893ec0a6e14"><span>Plant diseases are a major cause of destruction and death of most plants and especially trees. However, with the help of early detection, this issue can be solved and treated appropriately. A timely and accurate diagnosis is critical in maintaining the quality of crops. Recent innovations in the field of deep learning (DL), especially in convolutional neural networks (CNNs) have achieved great breakthroughs across different applications such as the classification of plant diseases. This study aims to evaluate scratch and pre-trained CNNs in the classification of tomato plant diseases by comparing some of the state-of-the-art architectures including densely connected convolutional network (Densenet) 120, residual network (ResNet) 101, ResNet 50, ReseNet 30, ResNet 18, squeezenet and Vgg.net. The comparison was then evaluated using a multiclass statistical analysis based on the F-Score, specificity, sensitivity, precision, and accuracy. The dataset used for the experiments was drawn from 9 classes of tomato diseases and a healthy class from PlantVillage. The findings show that the pretrained Densenet-120 performed excellently with 99.68% precision, 99.84% F-1 score, and 99.81% accuracy, which is higher compared to its non-trained based model showing the effectiveness of using a combination of a CNN model with fine-tuning adjustment in classifying crop diseases.</span></span>

Agriculture accepts a basic part by virtue of the quick improvement of the general population and extended interest in food in India. Hence, it is required to increase harvest yield. One serious cause of low collect yield is an infection brought about by microorganisms, infection, and organisms. Plant disease investigation is one of the major and essential tasks in the part of cultivating. It tends to be forestalled by utilizing plant disease detection techniques. To monitor, observe or take care of plant diseases manually is a very complex task. It requires gigantic proportions of work, and moreover needs outrageous planning time; consequently, image processing is utilized to distinguish diseases of plants. Plant disease classification can be done by using machine learning algorithms which include steps like dataset creation, load pictures, pre-preparing, segmentation, feature extraction, training classifier, and classification. The main objective of this research is to construct one model, which classifies the healthy and diseased harvest leaves and predicts diseases of plants. In this paper, the researchers have trained a model to recognize some unique harvests and 26 diseases from the public dataset which contains 54,306 images of the diseases and healthy plant leaves that are collected under controlled conditions. This paper worked on the ResNets algorithm. A residual neural network (ResNet) is a subpart of the artificial neural network (ANN). ResNet algorithm contains a residual block that can be used to solve the problem of vanishing/exploding gradient. ResNet algorithm is also used for creating Residual Network. For the image classification, ResNets achieve a much well result. The ResNets techniques applied some of the parameters like scheduling learning rate, gradient clipping, and weight decay. Using the ResNet algorithm, the researchers expect high accuracy results and detecting more diseases from the various harvests.

The performance of the salient object detection of strip surface defects has been promoted largely by deep learning based models. However, due to the complexity of strip surface defects, the existing models perform poorly in the challenging scenes such as noise disturbance, and low contrast between defect regions and background. Meanwhile, the detection results of existing models often suffer from coarse boundary details. Therefore, we propose a novel saliency model, namely an Edge-aware Multi-level Interactive Network, to detect the defects from the strip steel surface. Concretely, our model adopts the U-shape architecture where the two crucial points are the interactive feature integration and the edge-guided saliency fusion. Firstly, except the skip connection that combines the same stage of encoder and decoder, we deploy another connection, where the features from adjacent levels of encoder are transferred to the same stage of decoder. By this way, we are able to provide an effective fusion of multi-level deep features, yielding a well depiction for defects. Secondly, to give well-defined boundaries for prediction results, we add the edge extraction branch after each decoder block, where the progressive feature aggregation endows the edge with precise details and complete object cues. Meanwhile, together with the edge extraction branches, we deploy the saliency prediction branch at each decoder stage. After that, coupled with the fine edge information, we fuse all outputs of saliency prediction branches into the final saliency map, where the edge cue steers the saliency result to pay more attention to the boundary details. Following this way, we can provide a high-quality saliency map which can accurately locate and segment the defects. Extensive experiments are performed on the public dataset, and the results prove the effectiveness and robustness of our model which consistently outperforms the state-of-the-art models.

The agriculture industry significantly contributes to economic and population growth through the provision of high-quality food. Plant diseases decrease crop yields, which directly influences food production systems and leads to economic losses. Insufficient diagnosis and treatment of plant diseases can significantly affect agricultural productivity. Accurate identification is essential in order to prevent a severe decline in agricultural yield. Automatic detection models are crucial for accurate plant disease prediction and effective agricultural disease management. Deep Learning (DL) models are in great demand right now for identifying plant diseases because of how well they can anticipate and improve farmers’ crop yields. This study examines various DL algorithms for visual data-based plant disease detection and classification in great detail. Firstly, a brief overview is provided on various plant disease identification and classification systems developed by researchers, which utilize DL algorithms. Subsequently, a comprehensive analysis is undertaken to get deeper insights into the constraints of current algorithms and propose an innovative methodology for categorizing various forms of plant diseases, thereby contributing to the enhancement of agricultural output.

With the development of social platforms, people are more likely to use pictures to share their sentiments and opinions. With the development of deep learning, the current mainstream image sentiment analysis research mainly focuses on the use of high-level semantic sentiment features of images, and less on the use of low-level sentiment features such as colors, lines and so on. Aiming at the above problems, this paper proposes an image sentiment analysis model based on multi-level feature fusion (MLFF). Firstly, the convolution neural network is used to learn different levels of image features; Then the multi-level features are input into the bidirectional sequential neural network, and attention is introduced to fuse to generate multi-level fusion features; Finally, the multi-level fusion features are input to the full connection layer for classification. The experimental results show that the fusion model proposed in this paper can make effective use of multi-level image features and effectively improve the performance of image sentiment analysis.

Automated diagnosis of plant diseases is critical for ensuring food security and agricultural sustainability. In this study, we propose DeepLeaf, a novel deep-learning framework for the automated recognition and classification of plant diseases. DeepLeaf leverages convolutional neural networks to analyze plant leaf images and accurately identify disease symptoms. The framework is trained on a large dataset of annotated images, encompassing a wide range of plant species and disease types. Through extensive experimentation, we demonstrate the effectiveness of DeepLeaf in accurately diagnosing plant diseases across diverse environmental conditions and varying degrees of disease severity. Our results show that DeepLeaf achieves high accuracy and robustness, outperforming traditional methods and commercial systems in speed and reliability. Furthermore, DeepLeaf is designed to be easily deployable in real-world agricultural settings, enabling farmers and agronomists to identify and mitigate plant diseases quickly, thus refining crop yield and dropping economic losses.

Automatic classification of Lyme disease rashes on the skin helps clinicians and dermatologists’ probe and investigate Lyme skin rashes effectively. This paper proposes a new in‐depth features fusion system to classify Lyme disease rashes. The proposed method consists of two main steps. First, three different deep learning models, Densenet201, InceptionV3, and Exception, were trained independently to extract the deep features from the erythema migrans (EM) images. Second, a deep feature fusion mechanism (meta classifier) is developed to integrate the deep features before the final classification output layer. The meta classifier is a basic deep convolutional neural network trained on original images and features extracted from base level three deep learning models. In the feature fusion mechanism, the last three layers of base models are dropped out and connected to the meta classifier. The proposed deep feature fusion method significantly improved the classification process, where the classification accuracy was 98.97%, which is particularly impressive than the other state‐of‐the‐art models.

Research is still being done on the automated identification and classification of plant diseases. A quick and precise methodology for identifying plant diseases can improve both small-scale commercial crop protection and large-scale food security. Deep learning (DL) methods also enable the monitoring of plant health and the early diagnosis of illnesses. This study's DLEN-KLM model, which is built on EfficientNet and Kernel extreme Learning Machine (KLM) and is designed to diagnose plant diseases intelligently, addresses this issue. In contrast to limited adaptive histogram equalisation as a preprocessing method, the suggested DLEN-KLM model uses median filtering in its construction. A feature extractor built on EfficientNet B0 is also part of the DLEN-KLM model, which is used to create the best feature vectors before categorising them with the KLM model. Utilising a benchmark dataset, the effectiveness of the DLEN-KLM technique is validated. The experimental results showed that the technique outperformed more contemporary methods in terms of disease diagnosis.

Sustainable agriculture holds the key in meeting food production requirements for a rapidly growing population without exacerbating environmental degradation. Plant leaf diseases pose a critical threat to crop yield and quality. Existing inspection methods are labor-intensive and prone to human errors, while lacking support for large-scale agriculture. This research aims to enhance plant health by developing advanced deep learning models for the detection and classification of plant diseases across a variety of species. A deep learning model based on the paradigm of the MobileNet architecture is proposed, which employs a dedicated design through deeper convolutional layers, dropout regularization, and fully connected layers. This results in significant improvements in disease classification in tomato, bean, and chili plants, with accuracy rates of 97.90%, 98.12%, and 97.95%, respectively. Moreover, Grad-CAM is used to shed light on the decision-making process of the proposed model. The work contributes to the advancement of precision farming and sustainable agricultural practices, supporting timely and accurate plant disease diagnosis.

The Plant Disease is a major threat to Farmers, but faster identification remains a difficult task due to lack of incorporating latest technologies. The classification of plant disease is very challenging as it has only minimal features and hard to differentiate. The proposed technique uses a public dataset of 76,000 images of diseased plant leaves. We train the model using LeNet, AlexNet and Inception V3 for categorizing 38 varieties of plant diseases. The proposed model gives a comparison study of above three deep learning models and from the results we can predict Inception V3 performs better with an accuracy of 98% when compared to other models.

Plant diseases are responsible for economic loss in agricultural industry, as they destroy the crops. Although pesticides have been used to modify crop production, the excess amount of use of pesticides affects the environment negatively. Hence detection of diseases and differentiating it from nutritional deficiency has a considerable impact in deciding the requirement of pesticides. The conventional methods for plant diseases identification involve tedious chemical processes to be carried out in the laboratory and is also time consuming. This paper presents an automated system for identification and classification of plant diseases using Machine Learning (ML) and image processing technique. The feature extraction method is applied on images for training the algorithm. The skill of different Machine Learning algorithms is evaluated using the training data to find the best suiting algorithm for disease identification. The test folder contains the unseen images and is used for validating the performance of system in identification of plant diseases. The overall accuracy of the system is 95 percent. The system can be trained with large amount of images and yields accurate results at a faster rate.