Enhancing Tea Leaf Disease Identification with Lightweight MobileNetV2

Diseases in tea trees can result in significant losses in both the quality and quantity of tea production.Regular monitoring can help to prevent the occurrence of large-scale diseases in tea plantations.However,existingmethods face challenges such as a high number of parameters and low recognition accuracy,which hinders their application in tea plantation monitoring equipment.This paper presents a lightweight I-MobileNetV2 model for identifying diseases in tea leaves,to address these challenges.The proposed method first embeds a Coordinate Attention(CA)module into the originalMobileNetV2 network,enabling the model to locate disease regions accurately.Secondly,a Multi-branch Parallel Convolution(MPC)module is employed to extract disease features across multiple scales,improving themodel’s adaptability to different disease scales.Finally,the AutoML for Model Compression(AMC)is used to compress themodel and reduce computational complexity.Experimental results indicate that our proposed algorithm attains an average accuracy of 96.12%on our self-built tea leaf disease dataset,surpassing the original MobileNetV2 by 1.91%.Furthermore,the number of model parameters have been reduced by 40%,making itmore suitable for practical application in tea plantation environments.

A Novel Agricultural Data Sharing Mode Based on Rice Disease Identification

In this paper,a variety of classical convolutional neural networks are trained on two different datasets using transfer learning method.We demonstrated that the training dataset has a significant impact on the training results,in addition to the optimization achieved through the model structure.However,the lack of open-source agricultural data,combined with the absence of a comprehensive open-source data sharing platform,remains a substantial obstacle.This issue is closely related to the difficulty and high cost of obtaining high-quality agricultural data,the low level of education of most employees,underdeveloped distributed training systems and unsecured data security.To address these challenges,this paper proposes a novel idea of constructing an agricultural data sharing platform based on a federated learning(FL)framework,aiming to overcome the deficiency of high-quality data in agricultural field training.

Lightweight Method for Plant Disease Identification Using Deep Learning

In the deep learning approach for identifying plant diseases,the high complexity of the network model,the large number of parameters,and great computational effort make it challenging to deploy the model on terminal devices with limited computational resources.In this study,a lightweight method for plant diseases identification that is an improved version of the ShuffleNetV2 model is proposed.In the proposed model,the depthwise convolution in the basic module of ShuffleNetV2 is replaced with mixed depthwise convolution to capture crop pest images with different resolutions;the efficient channel attention module is added into the ShuffleNetV2 model network structure to enhance the channel features;and the ReLU activation function is replaced with the ReLU6 activation function to prevent the gen-eration of large gradients.Experiments are conducted on the public dataset PlantVillage.The results show that the proposed model achieves an accuracy of 99.43%,which is an improvement of 0.6 percentage points compared to the ShuffleNetV2 model.Compared to lightweight network models,such as MobileNetV2,MobileNetV3,EfficientNet,and EfficientNetV2,and classical convolutional neural network models,such as ResNet34,ResNet50,and ResNet101,the proposed model has fewer parameters and higher recognition accuracy,which provides guidance for deploying crop pest identification methods on resource-constrained devices,including mobile terminals.

Image Generation of Tomato Leaf Disease Identification Based on Small-ACGAN

Plant diseases have become a challenging threat in the agricultural field.Various learning approaches for plant disease detection and classification have been adopted to detect and diagnose these diseases early.However,deep learning entails extensive data for training,and it may be challenging to collect plant datasets.Even though plant datasets can be collected,they may be uneven in quantity.As a result,the problem of classification model overfitting arises.This study targets this issue and proposes an auxiliary classifier GAN(small-ACGAN)model based on a small number of datasets to extend the available data.First,after comparing various attention mechanisms,this paper chose to add the lightweight Coordinate Attention(CA)to the generator module of Auxiliary Classifier GANs(ACGAN)to improve the image quality.Then,a gradient penalty mechanism was added to the loss function to improve the training stability of the model.Experiments show that the proposed method can best improve the recognition accuracy of the classifier with the doubled dataset.On AlexNet,the accuracy was increased by 11.2%.In addition,small-ACGAN outperformed the other three GANs used in the experiment.Moreover,the experimental accuracy,precision,recall,and F1 scores of the five convolutional neural network(CNN)classifiers on the enhanced dataset improved by an average of 3.74%,3.48%,3.74%,and 3.80%compared to the original dataset.Furthermore,the accuracy of MobileNetV3 reached 97.9%,which fully demonstrated the feasibility of this approach.The general experimental results indicate that the method proposed in this paper provides a new dataset expansion method for effectively improving the identification accuracy and can play an essential role in expanding the dataset of the sparse number of plant diseases.

Research on Identification Method of Apple Diseases in Southern Xinjiang Based on Deep Learning and Its System Implementation

Apple disease samples were collected from the southern Xinjiang and annotated to design a convolutional neural network model based on deep learning.The accuracy and robustness of the model was improved through training and optimization algorithms,and a complete apple disease identification system was developed with the model as the core,and evaluated for its performance in terms of accuracy,recall rate and speed.This study provides a reliable AI-based apple disease diagnosis solution for the apple planting industry in the southern Xinjiang,hoping to help farmers better manage and protect crop health.

Deep Transfer Learning Models for Mobile-Based Ocular Disorder Identification on Retinal Images

Mobile technology is developing significantly.Mobile phone technologies have been integrated into the healthcare industry to help medical practitioners.Typically,computer vision models focus on image detection and classification issues.MobileNetV2 is a computer vision model that performs well on mobile devices,but it requires cloud services to process biometric image information and provide predictions to users.This leads to increased latency.Processing biometrics image datasets on mobile devices will make the prediction faster,but mobiles are resource-restricted devices in terms of storage,power,and computational speed.Hence,a model that is small in size,efficient,and has good prediction quality for biometrics image classification problems is required.Quantizing pre-trained CNN(PCNN)MobileNetV2 architecture combined with a Support Vector Machine(SVM)compacts the model representation and reduces the computational cost and memory requirement.This proposed novel approach combines quantized pre-trained CNN(PCNN)MobileNetV2 architecture with a Support Vector Machine(SVM)to represent models efficiently with low computational cost and memory.Our contributions include evaluating three CNN models for ocular disease identification in transfer learning and deep feature plus SVM approaches,showing the superiority of deep features from MobileNetV2 and SVM classification models,comparing traditional methods,exploring six ocular diseases and normal classification with 20,111 images postdata augmentation,and reducing the number of trainable models.The model is trained on ocular disorder retinal fundus image datasets according to the severity of six age-related macular degeneration(AMD),one of the most common eye illnesses,Cataract,Diabetes,Glaucoma,Hypertension,andMyopia with one class Normal.From the experiment outcomes,it is observed that the suggested MobileNetV2-SVM model size is compressed.The testing accuracy for MobileNetV2-SVM,InceptionV3,and MobileNetV2 is 90.11%,86.88%,and 89.76%respectively while MobileNetV2-SVM,InceptionV3,and MobileNetV2 accuracy are observed to be 92.59%,83.38%,and 90.16%,respectively.The proposed novel technique can be used to classify all biometric medical image datasets on mobile devices.

Establishment and Application of Identification Methods for Resistance to Sugarcane White Leaf Disease(SCWL)

[Objectives]This study was conducted to establish simple, efficient, stable, standardized and practical identification methods for sugarcane resistance to white leaf disease(SCWL), and promote the breeding for sugarcane resistance to SCWL. [Methods]The identification technology of sugarcane resistance to SCWL was systematically studied and explored from the aspects of sugarcane material treatment and planting, inoculation liquid preparation, inoculation method, disease investigation, grading standard formulation, etc., and two sets of simple, efficient, stable, standardized and practical accurate identification methods for sugarcane resistance to SCWL were created for the first time, namely, the seed cane coating inoculation method and the stem-cutting inoculation method at the growth stage. The seed cane coating inoculation method includes the steps of directly screening SCWL phytoplasma, extracting juice from cane and adding 10 times of sterile water to prepare an inoculation liquid, spraying seed cane on plastic film to keep moisture, planting the inoculated materials in barrels in an insect-proof greenhouse for cultivation, investigating the incidence rate 30 d after inoculation, and evaluating the disease resistance according to the 1-5 level standard. The method of stem-cutting inoculation includes the steps of directly screening sugarcane stems carrying SCWL phytoplasma and adding 10 times of sterile water to prepare an inoculation liquid, cultivating the identification materials in an insect-proof greenhouse, dropping 100 μl of the inoculation liquid into each root incision with a pipette gun at the age of 6 months, investigating the incidence rate 20 d after planting, and evaluating the disease resistance according to the 1-5 level standard. [Results] The two methods are similar to the natural transmission method. After inoculation, SCML occurred significantly, with high sensitivity and good reproducibility. The results of resistance identification were consistent with those of natural disease in the field. Through the two inoculation methods and field natural disease investigation, the resistance of 10 main cultivars to SCML was identified, which was true and reliable. [Conclusions] This study can provide standard varieties for identification of SCML resistance in the future.

Identification of Crop Diseases Based on Improved Genetic Algorithm and Extreme Learning Machine

As an indispensable task in crop protection,the detection of crop diseases directly impacts the income of farmers.To address the problems of low crop-disease identification precision and detection abilities,a new method of detection is proposed based on improved genetic algorithm and extreme learning machine.Taking five different typical diseases with common crops as the objects,this method first preprocesses the images of crops and selects the optimal features for fusion.Then,it builds a model of crop disease identification for extreme learning machine,introduces the hill-climbing algorithm to improve the traditional genetic algorithm,optimizes the initial weights and thresholds of the machine,and acquires the approximately optimal solution.And finally,a data set of crop diseases is used for verification,demonstrating that,compared with several other common machine learning methods,this method can effectively improve the crop-disease identification precision and detection abilities and provide a basis for the identification of other crop diseases.

Identification of Typical Rice Diseases Based on Interleaved Attention Neural Network

Taking Jiuhong Modern Agriculture Demonstration Park of Heilongjiang Province as the base for rice disease image acquisition,a total of 841 images of the four different diseases,including rice blast,stripe leaf blight,red blight and bacterial brown spot,were obtained.In this study,an interleaved attention neural network(IANN)was proposed to realize the recognition of rice disease images and an interleaved group convolutions(IGC)network was introduced to reduce the number of convolutional parameters,which realized the information interaction between channels.Based on the convolutional block attention module(CBAM),attention was paid to the features of results of the primary group convolution in the cross-group convolution to improve the classification performance of the deep learning model.The results showed that the classification accuracy of IANN was 96.14%,which was 4.72%higher than that of the classical convolutional neural network(CNN).This study showed a new idea for the efficient training of neural networks in the case of small samples and provided a reference for the image recognition and diagnosis of rice and other crop diseases.

Classification Methods Based on Pattern Discrimination Models for Web-Based Diagnosis of Rice Diseases

Two classification and identification methods based on pattern discrimination models and the majority-vote technique were investigated for implementing a World Wide Web-based system for the identification of rice diseases. The experiment was carried out using color and shape patterns in 425 images of three rice diseases, which were classified into four classes： two classes of leaf blast, and one class each of sheath blight and brown spot. A method consisting of two discrimination steps involving application of multiple discrimination models of a support vector machine gave the best result because of its capacity to evaluate the similarity of disease types. This accuracy of the method was 88% for leaf blast （A-type）, 94% for sheath blight, and 80% for leaf blast （B-type） and brown spot; on average, the accuracy of this method was 5% greater than that of the other method when three classes were used in the model. Although the accuracy of both methods was inadequate, the results of this study show that it is possible to estimate the least number of possible or similar diseases from a large number of diseases. Therefore, we conclude that there is merit in grouping classes into subgroups rather than attempting to discriminate between all classes simultaneously and that these methods are effective in identifying diseases for web-based diagnosis.

Real-Time Multi-Class Infection Classification for Respiratory Diseases

Real-time disease prediction has emerged as the main focus of study in the field of computerized medicine.Intelligent disease identification framework can assist medical practitioners in diagnosing disease in a way that is reliable,consistent,and timely,successfully lowering mortality rates,particularly during endemics and pandemics.To prevent this pandemic’s rapid and widespread,it is vital to quickly identify,confine,and treat affected individuals.The need for auxiliary computer-aided diagnostic(CAD)systems has grown.Numerous recent studies have indicated that radiological pictures contained critical information regarding the COVID-19 virus.Utilizing advanced convolutional neural network(CNN)architectures in conjunction with radiological imaging makes it possible to provide rapid,accurate,and extremely useful susceptible classifications.This research work proposes a methodology for real-time detection of COVID-19 infections caused by the Corona Virus.The purpose of this study is to offer a two-way COVID-19(2WCD)diagnosis prediction deep learning system that is built on Transfer Learning Methodologies(TLM)and features customized fine-tuning on top of fully connected layered pre-trained CNN architectures.2WCD has applied modifications to pre-trained models for better performance.It is designed and implemented to improve the generalization ability of the classifier for binary and multi-class models.Along with the ability to differentiate COVID-19 and No-Patient in the binary class model and COVID-19,No-Patient,and Pneumonia in the multi-class model,our framework is augmented with a critical add-on for visually demonstrating infection in any tested radiological image by highlighting the affected region in the patient’s lung in a recognizable color pattern.The proposed system is shown to be extremely robust and reliable for real-time COVID-19 diagnostic prediction.It can also be used to forecast other lung-related disorders.As the system can assist medical practitioners in diagnosing the greatest number of patients in the shortestamount of time, radiologists can also be used or published online to assistany less-experienced individual in obtaining an accurate immediate screeningfor their radiological images.

Identification of diseases for soybean seeds by computer vision applying BP neural network

The use of computer vision for estimating quality in agriculture products has become wide spread in recent years and the composition,variety,or ripeness can be estimated.On the other hand,the appearance is one of the most worrying issues for producers due to its influence on quality.In this research,computer vision technology combined with BP artificial neural network(ANN)was developed to identify soybean frogeye,mildewed soybean,worm-eaten soybean and damaged soybean.Thirty-nine characteristic parameters from color,texture and shape characteristics were computed after preprocessing the acquired soybean images.The dimensionality of the characteristic parameters was reduced from 39 dimensionalities to 12 dimensionalities using the method of principal component analysis(PCA).MALAB software was used to build a prediction model according to 12 characteristic parameters.The identification accuracies of soybean frogeye,mildewed soybean,damaged soybean and worm-eaten soybean are 96%,95%,92%,and 92%,respectively.And the accuracy for heterogeneous soybean seeds with several diseases is 90%.The results show that the prediction model constructed by BP neural network can identify the diseases of soybean seeds.And it is useful to estimate appearance quality of soybean by computer vision applying BP neural network.

Disease gene identification by using graph kernels and Markov random fields

Genes associated with similar diseases are often functionally related.This principle is largely supported by many biological data sources,such as disease phenotype similarities,protein complexes,protein-protein interactions,pathways and gene expression profiles.Integrating multiple types of biological data is an effective method to identify disease genes for many genetic diseases.To capture the gene-disease associations based on biological networks,a kernel-based Markov random field(MRF)method is proposed by combining graph kernels and the MRF method.In the proposed method,three kinds of kernels are employed to describe the overall relationships of vertices in five biological networks,respectively,and a novel weighted MRF method is developed to integrate those data.In addition,an improved Gibbs sampling procedure and a novel parameter estimation method are proposed to generate predictions from the kernel-based MRF method.Numerical experiments are carried out by integrating known gene-disease associations,protein complexes,protein-protein interactions,pathways and gene expression profiles.The proposed kernel-based MRF method is evaluated by the leave-one-out cross validation paradigm,achieving an AUC score of 0.771 when integrating all those biological data in our experiments,which indicates that our proposed method is very promising compared with many existing methods.