scholarly journals Deep Neural Network Compression for Plant Disease Recognition

Symmetry ◽  
2021 ◽  
Vol 13 (10) ◽  
pp. 1769
Author(s):  
Ruiqing Wang ◽  
Wu Zhang ◽  
Jiuyang Ding ◽  
Meng Xia ◽  
Mengjian Wang ◽  
...  
Keyword(s):  
Plant Disease ◽  
Resource Constraints ◽  
Network Models ◽  
Performance Comparison ◽  
Plant Diseases ◽  
Compression Method ◽  
Before And After ◽  
Knowledge Distillation ◽  
Network Compression ◽  
Fully Connected

Deep neural networks (DNNs) have become the de facto standard for image recognition tasks, and their applications with respect to plant diseases have also obtained remarkable results. However, the large number of parameters and high computational complexities of these network models make them difficult to deploy on farms in remote areas. In this paper, focusing on the problems of resource constraints and plant diseases, we propose a DNN-based compression method. In order to reduce computational burden, this method uses lightweight fully connected layers to accelerate reasoning, pruning to remove redundant parameters and reduce multiply–accumulate operations, knowledge distillation instead of retraining to restore the lost accuracy, and then quantization to compress the size of the model further. After compressing the mainstream VGGNet and AlexNet models, the compressed versions are applied to the Plant Village dataset of plant disease images, and a performance comparison of the models before and after compression is obtained to verify the proposed method. The results show that the model can be compressed to 0.04 Mb with an accuracy of 97.09%. This experiment also proves the effectiveness of knowledge distillation during the pruning process, and compressed models are more efficient than prevalent lightweight models.

scholarly journals Microbial antagonists against plant pathogens in Iran: A review

2020 ◽  
Vol 5 (1) ◽  
pp. 404-440 ◽  
Author(s):  
Mehrdad Alizadeh ◽  
Yalda Vasebi ◽  
Naser Safaie
Keyword(s):  
Biological Control ◽  
Chemical Control ◽  
Plant Disease ◽  
Plant Pathogens ◽  
Plant Diseases ◽  
Agricultural Products ◽  
Control Measures ◽  
Wide Range ◽  
Plant Disease Management ◽  
Published Research

AbstractThe purpose of this article was to give a comprehensive review of the published research works on biological control of different fungal, bacterial, and nematode plant diseases in Iran from 1992 to 2018. Plant pathogens cause economical loss in many agricultural products in Iran. In an attempt to prevent these serious losses, chemical control measures have usually been applied to reduce diseases in farms, gardens, and greenhouses. In recent decades, using the biological control against plant diseases has been considered as a beneficial and alternative method to chemical control due to its potential in integrated plant disease management as well as the increasing yield in an eco-friendly manner. Based on the reported studies, various species of Trichoderma, Pseudomonas, and Bacillus were the most common biocontrol agents with the ability to control the wide range of plant pathogens in Iran from lab to the greenhouse and field conditions.

scholarly journals Agro-Nanotechnology as an Emerging Field: A Novel Sustainable Approach for Improving Plant Growth by Reducing Biotic Stress

2021 ◽  
Vol 11 (5) ◽  
pp. 2282
Author(s):  
Masudulla Khan ◽  
Azhar U. Khan ◽  
Mohd Abul Hasan ◽  
Krishna Kumar Yadav ◽  
Marina M. C. Pinto ◽  
...  
Keyword(s):  
Plant Growth ◽  
Crop Yield ◽  
Biotic Stress ◽  
Crop Production ◽  
Plant Disease ◽  
Yield Loss ◽  
Growth Parameters ◽  
Plant Diseases ◽  
High Yield ◽  
Plant Disease Management

In the present era, the global need for food is increasing rapidly; nanomaterials are a useful tool for improving crop production and yield. The application of nanomaterials can improve plant growth parameters. Biotic stress is induced by many microbes in crops and causes disease and high yield loss. Every year, approximately 20–40% of crop yield is lost due to plant diseases caused by various pests and pathogens. Current plant disease or biotic stress management mainly relies on toxic fungicides and pesticides that are potentially harmful to the environment. Nanotechnology emerged as an alternative for the sustainable and eco-friendly management of biotic stress induced by pests and pathogens on crops. In this review article, we assess the role and impact of different nanoparticles in plant disease management, and this review explores the direction in which nanoparticles can be utilized for improving plant growth and crop yield.

Queueing network models for intelligent manufacturing units with dual-resource constraints

2021 ◽  
pp. 105213
Author(s):  
Hui-Yu Zhang ◽  
Qing-Xin Chen ◽  
James MacGregor Smith ◽  
Ning Mao ◽  
Yong Liao ◽  
...  
Keyword(s):  
Resource Constraints ◽  
Queueing Network ◽  
Network Models ◽  
Intelligent Manufacturing ◽  
Queueing Network Models

scholarly journals Extension Plant Pathology: Strengthening Resources to Continue Serving the Public Interest

2012 ◽  
Vol 102 (7) ◽  
pp. 652-655 ◽  
Author(s):  
K. L. Everts ◽  
L. Osborne ◽  
A. J. Gevens ◽  
S. J. Vasquez ◽  
B. K. Gugino ◽  
...  
Keyword(s):  
Plant Pathology ◽  
Plant Disease ◽  
Crop Yields ◽  
Economic Value ◽  
The United States ◽  
Emerging Diseases ◽  
Plant Diseases ◽  
Economic Losses ◽  
Global Competitiveness ◽  
Horticultural Crops

Extension plant pathologists deliver science-based information that protects the economic value of agricultural and horticultural crops in the United States by educating growers and the general public about plant diseases. Extension plant pathologists diagnose plant diseases and disorders, provide advice, and conduct applied research on local and regional plant disease problems. During the last century, extension plant pathology programs have adjusted to demographic shifts in the U.S. population and to changes in program funding. Extension programs are now more collaborative and more specialized in response to a highly educated clientele. Changes in federal and state budgets and policies have also reduced funding and shifted the source of funding of extension plant pathologists from formula funds towards specialized competitive grants. These competitive grants often favor national over local and regional plant disease issues and typically require a long lead time to secure funding. These changes coupled with a reduction in personnel pose a threat to extension plant pathology programs. Increasing demand for high-quality, unbiased information and the continued reduction in local, state, and federal funds is unsustainable and, if not abated, will lead to a delay in response to emerging diseases, reduce crop yields, increase economic losses, and place U.S. agriculture at a global competitive disadvantage. In this letter, we outline four recommendations to strengthen the role and resources of extension plant pathologists as they guide our nation's food, feed, fuel, fiber, and ornamental producers into an era of increasing technological complexity and global competitiveness.

scholarly journals Automated Plant Disease Detection using Deep Learning Architectures with Autonomous rover

2020 ◽  
Vol 9 (2) ◽  
pp. 248-254
Keyword(s):  
Deep Learning ◽  
Plant Disease ◽  
Vital Role ◽  
Plant Diseases ◽  
Asian Countries ◽  
Agricultural Produce ◽  
Underlying Principle ◽  
Learning Architectures ◽  
The Internet Of Things ◽  
Identification Mechanism

Agriculture is the backbone and plays a vital role in many Asian countries. Farmers mainly depend on their agricultural produce for their living. A report says one-third of the farmers income account’s for the agricultural loss which is primarily due to plant diseases. To combat this farmers are in need of a early plant disease identification mechanism. Observation of individual plants in the farm for detecting the disease is labor-intensive and time consuming work, if the farm is vast and multiple plants are cultivated then it’s even worse. To solve such issues, current technologies like the Internet of Things (IoT) and artificial intelligence (AI) and Machine Learning (ML) are used to predict the diseases more effectively. Farmers usually detect plant diseases with the help of images captured manually and analyzed separately by experts. The proposed system renders an efficient solution for detecting multiple diseases in several plant varieties. The system is designed to detect and recognize several plant varieties, specifically pepper, grapes, and strawberry. The proposed system discovers various plant’s various diseases based on the inputs obtained by capturing images from a built-in camera present in the Autonomous rover. The rover also record’s it’s GPS location and makes a map of the entire farm traced and checked by the robot. The images are processed and are classified into their respective categories using deep learning algorithms. Convolutional neural networks the powerful methodology for image classification is the underlying principle applied. The deep learning model’s architecture namely, VGG16 and InceptionResNetV2, are used to train the model. These models are primarily made of convolutional layers. On testing, we recorded am accuracy of 93.21% was obtained from VGG16, and 95.24% from InceptionResNetV2.

scholarly journals Recognition of mango leaf disease using convolutional neural network models: a transfer learning approach

2021 ◽  
Vol 23 (3) ◽  
pp. 1681
Author(s):  
Aditya Rajbongshi ◽  
Thaharim Khan ◽  
Md. Mahbubur Rahman ◽  
Anik Pramanik ◽  
Shah Md Tanvir Siddiquee ◽  
...  
Keyword(s):  
Transfer Learning ◽  
Image Data ◽  
Network Models ◽  
Plant Diseases ◽  
Prevention Measures ◽  
Neural Network Models ◽  
Data Set ◽  
Learning Techniques ◽  
Overall Performance ◽  
Mango Leaves

<p>The acknowledgment of plant diseases assumes an indispensable part in taking infectious prevention measures to improve the quality and amount of harvest yield. Mechanization of plant diseases is a lot advantageous as it decreases the checking work in an enormous cultivated area where mango is planted to a huge extend. Leaves being the food hotspot for plants, the early and precise recognition of leaf diseases is significant. This work focused on grouping and distinguishing the diseases of mango leaves through the process of CNN. DenseNet201, InceptionResNetV2, InceptionV3, ResNet50, ResNet152V2, and Xception all these models of CNN with transfer learning techniques are used here for getting better accuracy from the targeted data set. Image acquisition, image segmentation, and features extraction are the steps involved in disease detection. Different kinds of leaf diseases which are considered as the class for this work such as anthracnose, gall machi, powdery mildew, red rust are used in the dataset consisting of 1500 images of diseased and also healthy mango leaves image data another class is also added in the dataset. We have also evaluated the overall performance matrices and found that the DenseNet201 outperforms by obtaining the highest accuracy as 98.00% than other models.</p>

scholarly journals A Review on Advances in Automated Plant Disease Detection

2021 ◽  
Vol 11 (4) ◽  
pp. 251-264
Author(s):  
Radhika Bhagwat ◽  
Yogesh Dandawate
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Plant Disease ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Plant Diseases ◽  
Detection Methods ◽  
Economic Losses ◽  
Disease Detection ◽  
Range Images

Plant diseases cause major yield and economic losses. To detect plant disease at early stages, selecting appropriate techniques is imperative as it affects the cost, diagnosis time, and accuracy. This research gives a comprehensive review of various plant disease detection methods based on the images used and processing algorithms applied. It systematically analyzes various traditional machine learning and deep learning algorithms used for processing visible and spectral range images, and comparatively evaluates the work done in literature in terms of datasets used, various image processing techniques employed, models utilized, and efficiency achieved. The study discusses the benefits and restrictions of each method along with the challenges to be addressed for rapid and accurate plant disease detection. Results show that for plant disease detection, deep learning outperforms traditional machine learning algorithms while visible range images are more widely used compared to spectral images.

scholarly journals Biochar and Trichoderma spp. in management of plant diseases caused by soilborne fungal pathogens: a review and perspective

2021 ◽  
Vol 10 (15) ◽  
pp. e296101522465
Author(s):  
Erika Valente de Medeiros ◽  
Lucas Figueira da Silva ◽  
Jenifer Sthephanie Araújo da Silva ◽  
Diogo Paes da Costa ◽  
Carlos Alberto Fragoso de Souza ◽  
...  
Keyword(s):  
Soil Properties ◽  
Fungal Pathogens ◽  
Plant Disease ◽  
Plant Pathogens ◽  
Plant Diseases ◽  
Management Tool ◽  
Production Plant ◽  
Trichoderma Spp ◽  
Health Concept ◽  
Plant Disease Management

A better understanding of the use of biochar with Trichoderma spp. (TRI), considered the most studied tool for biological control, would increase our ability to set priorities. However, no studies exist using the two inputs on plant disease management. Here, we hypothesized that biochar and TRI would be used for the management of soilborne plant pathogens, mainly due to changes in soil properties and its interactions. To test this hypothesis, this review assesses papers that used biochar and TRI against plant diseases and we summarize the handling mechanisms for each input. Biochar acts by mechanisms: induction to plant resistance, sorption of allelopathic and fungitoxic compounds, increase of beneficial microorganisms, changes the soil properties that promote health and nutrient availability. Trichoderma as biocontrol agents by different mechanisms: mycoparasitism, enzyme and secondary metabolic production, plant promoter agent, natural decomposition agent, and biological agent of bioremediation. Overall, our findings expand our knowledge about the reuse of wastes transformed in biochar combined with Trichoderma has potential perspective to formulate products as alternative management tool of plant disease caused by soilborne fungal pathogen and add important information that can be suitable for development of strategy for use in the global health concept.

Classification of plant diseases using machine and deep learning

2021 ◽  
Vol 11 (1) ◽  
pp. 491-508
Author(s):  
Monika Lamba ◽  
Yogita Gigras ◽  
Anuradha Dhull
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Plant Disease ◽  
Nearest Neighbor ◽  
Early Recognition ◽  
Activation Function ◽  
Plant Diseases ◽  
Support Vector ◽  
Specificity And Sensitivity ◽  
Proposed Model

Abstract Detection of plant disease has a crucial role in better understanding the economy of India in terms of agricultural productivity. Early recognition and categorization of diseases in plants are very crucial as it can adversely affect the growth and development of species. Numerous machine learning methods like SVM (support vector machine), random forest, KNN (k-nearest neighbor), Naïve Bayes, decision tree, etc., have been exploited for recognition, discovery, and categorization of plant diseases; however, the advancement of machine learning by DL (deep learning) is supposed to possess tremendous potential in enhancing the accuracy. This paper proposed a model comprising of Auto-Color Correlogram as image filter and DL as classifiers with different activation functions for plant disease. This proposed model is implemented on four different datasets to solve binary and multiclass subcategories of plant diseases. Using the proposed model, results achieved are better, obtaining 99.4% accuracy and 99.9% sensitivity for binary class and 99.2% accuracy for multiclass. It is proven that the proposed model outperforms other approaches, namely LibSVM, SMO (sequential minimal optimization), and DL with activation function softmax and softsign in terms of F-measure, recall, MCC (Matthews correlation coefficient), specificity and sensitivity.

Sign in / Sign up

Export Citation Format

Share Document