Early identification of plant diseases is crucial as they can hinder the growth of their respective species. Although many machine learning models have been utilised for detecting and classifying plant diseases. The advent of deep Learning, a subset of machine learning, has revolutionised this field by offering greater accuracy. Therefore, deep learning has the potential to greatly enhance the accuracy of plant disease detection and classification. Recent research progress on the use of deep learning technology in the identification of crop leaf diseases is reviewed in this article. The current trends and challenges in plant leaf disease detection using advanced imaging techniques and deep learning are presented. This survey aims to provide a valuable resource for the researchers investigating the detection of plant diseases and detection of those using state of the art models for ease of saving time and cost. Additionally, the article also addresses some of the current challenges and issues in the detection process that need to be resolved.
Crop Leaf Disease Diagnosis using Convolutional Neural Networkijtsrd
This document summarizes a research paper that proposes a system for detecting crop leaf diseases using convolutional neural networks. The system can identify diseases in five major crops: corn, sugarcane, wheat, grape, and rice. It uses a MobileNet CNN model trained on a dataset of leaf images. Experiments show the system can accurately classify leaf diseases with 97.33% precision. The system automatically diagnoses leaf diseases and recommends pesticides, helping farmers detect and address issues early.
Plant Disease Detection and Identification using Leaf Images using deep learningIRJET Journal
The document discusses a method for plant disease detection and identification using deep learning on leaf images. The method involves collecting images of plant leaves, preprocessing the images through steps like segmentation and grayscale conversion, and classifying plant diseases using a convolutional neural network (CNN) classifier. The goal is to develop an automated system for early and accurate detection of plant diseases to improve crop productivity and help farmers. The system could help reduce costs and time compared to traditional expert-based identification methods. Experimental results found the CNN achieved over 99% accuracy in identifying three common pomegranate diseases from leaf images.
Plant Leaf Disease Detection Using Machine LearningIRJET Journal
This document describes a research project that uses machine learning to detect plant leaf diseases. Specifically, it uses a Convolutional Neural Network (CNN) model trained on the PlantVillage dataset to classify images and identify 15 common diseases in tomato, potato, and pepper plants. The system is implemented as a web application that farmers can use to upload images of plant leaves. It provides disease names and treatment recommendations to help farmers efficiently diagnose issues and select appropriate pesticides. Validation tests found the system could accurately identify diseases 93.5% of the time. The goal is to help farmers, especially small-scale farmers, save crops and income by enabling easy, early detection of plant diseases.
This document discusses techniques for detecting plant diseases using leaf images and convolutional neural networks. It begins with an abstract describing how image processing can be used for plant disease detection by applying techniques like preprocessing, segmentation, feature extraction, and classification to images. It then provides background on the importance of accurate plant disease detection. The paper reviews existing literature on plant disease detection methods and summarizes the datasets and techniques used in the proposed system, which applies a pretrained convolutional neural network model to classify leaf images as either healthy or diseased with common maize diseases.
RICE PLANT DISEASE DETECTION AND REMEDIES RECOMMENDATION USING MACHINE LEARNINGIRJET Journal
This document describes a machine learning approach to detect diseases in rice plants from images and recommend remedies. It discusses three common rice diseases - leaf blast, bacterial leaf blight, and hispa - and how a convolutional neural network was trained on thousands of images to classify diseases. The proposed method uses CNN layers to extract features from images and fully connected layers to classify diseases. It aims to help farmers early detect diseases from photos and provide effective treatment recommendations to improve crop yields.
Plant Disease Detection and Severity Classification using Support Vector Mach...IRJET Journal
This document discusses a study that used support vector machines (SVM) and convolutional neural networks (CNN) to detect plant diseases and classify their severity using images. The researchers trained their models on a dataset containing images of four plant species with different diseases. SVM was used for disease detection, achieving 80-90% accuracy. CNN models like DenseNet and EfficientNet were used to classify disease severity. The goal of the study was to help farmers identify plant diseases early to mitigate losses and improve food security.
An Exploration on the Identification of Plant Leaf Diseases using Image Proce...Tarun Kumar
From the ancient years, humans and other
social species directly & indirectly dependent on Plants.
Plants play an enormous role in human life by providing
them food for living, wood for houses and other resources
to live life.So, human should take care of plants and
agricultural crops. But apart from the human, various
natural factors are there that are responsible for
destroying the growth of plants like unavailability of
accurate plant resources, deficiency of sunlight, weather
conditions, lack of expert knowledge for the accurate use
of pesticides. The major factor responsible for this
destruction of plant growth is diseases. Early detection
and accurate identification of diseases can control the
spread of infection.In the earlier days, it was not easy to
identify the plant diseases but with the advancements of
digital technology, it becomes easy to identify plant disease
with image processing techniques. In this paper, an
exploration is made on the exiting approaches of plant leaf
disease detection using image processing approach. Also a
discussion is made on the major disease types like fungal,
bacterial and viral diseases. Different authors have
presented the different approaches for the identification of
leaf diseases for the different plant types.
Food is one of the basic needs of human being. Population is increasing day by day. So, it has become important to grow sufficient amount of crops to feed such a huge population. Agricultural intervention in the livelihood of rural India is about 58%. But with the time passing by, plants are being affected with many kinds of diseases, which cause great harm to the agricultural plant productions. It is very difficult to monitor the plant diseases. It requires tremendous amount of work, expertise in the plant diseases, and also require the excessive processing speed and time. Hence, image processing is used for the detection of plant diseases by just capturing the images of the leaves and comparing it with the data sets available. Latest and fostering technologies like Image processing is used to rectify such issues very effectively. In this project, four consecutive stages are used to discover the type of disease. The four stages include pre-processing, leaf segmentation, feature extraction and classification. This paper aims to support and help the farmers in an efficient way.
Crop Leaf Disease Diagnosis using Convolutional Neural Networkijtsrd
This document summarizes a research paper that proposes a system for detecting crop leaf diseases using convolutional neural networks. The system can identify diseases in five major crops: corn, sugarcane, wheat, grape, and rice. It uses a MobileNet CNN model trained on a dataset of leaf images. Experiments show the system can accurately classify leaf diseases with 97.33% precision. The system automatically diagnoses leaf diseases and recommends pesticides, helping farmers detect and address issues early.
Plant Disease Detection and Identification using Leaf Images using deep learningIRJET Journal
The document discusses a method for plant disease detection and identification using deep learning on leaf images. The method involves collecting images of plant leaves, preprocessing the images through steps like segmentation and grayscale conversion, and classifying plant diseases using a convolutional neural network (CNN) classifier. The goal is to develop an automated system for early and accurate detection of plant diseases to improve crop productivity and help farmers. The system could help reduce costs and time compared to traditional expert-based identification methods. Experimental results found the CNN achieved over 99% accuracy in identifying three common pomegranate diseases from leaf images.
Plant Leaf Disease Detection Using Machine LearningIRJET Journal
This document describes a research project that uses machine learning to detect plant leaf diseases. Specifically, it uses a Convolutional Neural Network (CNN) model trained on the PlantVillage dataset to classify images and identify 15 common diseases in tomato, potato, and pepper plants. The system is implemented as a web application that farmers can use to upload images of plant leaves. It provides disease names and treatment recommendations to help farmers efficiently diagnose issues and select appropriate pesticides. Validation tests found the system could accurately identify diseases 93.5% of the time. The goal is to help farmers, especially small-scale farmers, save crops and income by enabling easy, early detection of plant diseases.
This document discusses techniques for detecting plant diseases using leaf images and convolutional neural networks. It begins with an abstract describing how image processing can be used for plant disease detection by applying techniques like preprocessing, segmentation, feature extraction, and classification to images. It then provides background on the importance of accurate plant disease detection. The paper reviews existing literature on plant disease detection methods and summarizes the datasets and techniques used in the proposed system, which applies a pretrained convolutional neural network model to classify leaf images as either healthy or diseased with common maize diseases.
RICE PLANT DISEASE DETECTION AND REMEDIES RECOMMENDATION USING MACHINE LEARNINGIRJET Journal
This document describes a machine learning approach to detect diseases in rice plants from images and recommend remedies. It discusses three common rice diseases - leaf blast, bacterial leaf blight, and hispa - and how a convolutional neural network was trained on thousands of images to classify diseases. The proposed method uses CNN layers to extract features from images and fully connected layers to classify diseases. It aims to help farmers early detect diseases from photos and provide effective treatment recommendations to improve crop yields.
Plant Disease Detection and Severity Classification using Support Vector Mach...IRJET Journal
This document discusses a study that used support vector machines (SVM) and convolutional neural networks (CNN) to detect plant diseases and classify their severity using images. The researchers trained their models on a dataset containing images of four plant species with different diseases. SVM was used for disease detection, achieving 80-90% accuracy. CNN models like DenseNet and EfficientNet were used to classify disease severity. The goal of the study was to help farmers identify plant diseases early to mitigate losses and improve food security.
An Exploration on the Identification of Plant Leaf Diseases using Image Proce...Tarun Kumar
From the ancient years, humans and other
social species directly & indirectly dependent on Plants.
Plants play an enormous role in human life by providing
them food for living, wood for houses and other resources
to live life.So, human should take care of plants and
agricultural crops. But apart from the human, various
natural factors are there that are responsible for
destroying the growth of plants like unavailability of
accurate plant resources, deficiency of sunlight, weather
conditions, lack of expert knowledge for the accurate use
of pesticides. The major factor responsible for this
destruction of plant growth is diseases. Early detection
and accurate identification of diseases can control the
spread of infection.In the earlier days, it was not easy to
identify the plant diseases but with the advancements of
digital technology, it becomes easy to identify plant disease
with image processing techniques. In this paper, an
exploration is made on the exiting approaches of plant leaf
disease detection using image processing approach. Also a
discussion is made on the major disease types like fungal,
bacterial and viral diseases. Different authors have
presented the different approaches for the identification of
leaf diseases for the different plant types.
Food is one of the basic needs of human being. Population is increasing day by day. So, it has become important to grow sufficient amount of crops to feed such a huge population. Agricultural intervention in the livelihood of rural India is about 58%. But with the time passing by, plants are being affected with many kinds of diseases, which cause great harm to the agricultural plant productions. It is very difficult to monitor the plant diseases. It requires tremendous amount of work, expertise in the plant diseases, and also require the excessive processing speed and time. Hence, image processing is used for the detection of plant diseases by just capturing the images of the leaves and comparing it with the data sets available. Latest and fostering technologies like Image processing is used to rectify such issues very effectively. In this project, four consecutive stages are used to discover the type of disease. The four stages include pre-processing, leaf segmentation, feature extraction and classification. This paper aims to support and help the farmers in an efficient way.
A study on real time plant disease diagonsis systemIJARIIT
The document discusses developing a real-time plant disease diagnosis mobile application. It aims to allow farmers to easily capture images of plant leaves using a mobile camera, send the images to a central system for analysis, and receive diagnoses and treatment recommendations. The proposed system would use image processing and data mining techniques to analyze leaf images for abnormalities, identify the plant species, recognize any diseases present, and recommend appropriate pesticides and estimate treatment costs. This would provide a low-cost, convenient solution for farmers to quickly diagnose and respond to plant diseases.
A classification model based on depthwise separable convolutional neural net...IJECEIAES
Every year a number of rice diseases cause major damage to crop around the world. Early and accurate prediction of various rice plant diseases has been a major challenge for farmers and researchers. Recent developments in the convolutional neural networks (CNNs) have made image processing techniques more convenient and precise. Motivated from that in this research, a depthwise separable convolutional neural network based classification model has been proposed for identifying 12 types of rice plant diseases. Also, 8 different state-of-the-art convolution neural network model has been fine-tuned specifically for identifying the rice plant diseases and their performance has been evaluated. The proposed model performs considerably well in contrast to existing state-of-the-art CNN architectures. The experimental analysis indicates that the proposed model can correctly diagnose rice plant diseases with a validation and testing accuracy of 96.5% and 95.3% respectively while having a substantially smaller model size.
IRJET - Paddy Crop Disease Detection using Deep Learning Technique by using D...IRJET Journal
This document describes a study that uses deep learning and digital image processing techniques to detect diseases in paddy crops. The proposed system takes digital images of affected leaf parts as input and outputs the name of the detected disease and recommended pesticides. It first preprocesses and enhances the images before using edge detection, segmentation, and classification algorithms to analyze leaf parameters and identify diseases. The goal is to enable accurate, automated disease detection to help farmers protect crops and minimize pesticide usage.
This document discusses a proposed loss-fused convolutional neural network model for identifying and classifying plant disease. The model aims to improve predictive performance by combining the advantages of two different loss functions. The model was tested on a dataset from the Plant Village Database and achieved 98.93% accuracy in discriminating between affected and unaffected plant leaf samples, outperforming other existing methodologies. The paper provides background on plant disease detection techniques and reviews related work applying machine learning and deep learning methods.
An Innovative Approach for Tomato Leaf Disease Identification and its Benefic...IRJET Journal
This document summarizes an innovative approach for identifying diseases in tomato leaves using image processing and machine learning techniques. Specifically, a Convolutional Neural Network (CNN) model is developed and trained on a dataset of tomato leaf images showing various disease symptoms. Through testing and validation, the proposed approach achieves high accuracy in classifying different types of tomato leaf diseases. Integrating this method could enable timely disease detection, reduce crop losses, and optimize resource allocation for more sustainable agricultural practices. The research contributes a practical solution for automating tomato leaf disease detection to enhance disease management and food security.
POMDETECT: AN INVESTIGATION INTO LEAF DISEASE DETECTION TECHNIQUESIRJET Journal
This document discusses various techniques for detecting diseases in pomegranate leaves, including visual inspection, spectral imaging, and machine learning approaches. It analyzes several studies that evaluated these techniques and their effectiveness in detecting common diseases like bacterial blight, anthracnose, and powdery mildew. Machine learning techniques like convolutional neural networks were shown to outperform other methods in accuracy and speed of detection. The document highlights the potential of these techniques, especially deep learning, to develop automated disease monitoring systems and aid farmers in managing diseases.
POMDETECT: AN INVESTIGATION INTO LEAF DISEASE DETECTION TECHNIQUESIRJET Journal
This document discusses various techniques for detecting diseases in pomegranate leaves, including visual inspection, spectral imaging, and machine learning approaches. It analyzes several studies that evaluated these techniques and their effectiveness in detecting common diseases like bacterial blight, anthracnose, and powdery mildew. Machine learning techniques like convolutional neural networks were shown to outperform other methods in accuracy and speed of detection. The document highlights the potential of automated disease detection systems to help farmers manage diseases and improve crop yields.
Tomato Disease Fusion and Classification using Deep LearningIJCI JOURNAL
Tomato plants' susceptibility to diseases imperils agricultural yields. About 30% of the total crop loss is attributable to plants with disease. Detecting such illnesses in the plant is crucial to avoid significant output losses.This study introduces "data fusion" to enhance disease classification by amalgamating distinct disease-specific traits from leaf halves. Data fusion generates synthetic samples, fortifying a TensorFlow Keras deep learning model using a diverse tomato leaf image dataset. Results illuminate the augmented model's efficacy, particularly for diseases marked by overlapping traits. Enhanced disease recognition accuracy and insights into disease interactions transpire. Evaluation metrics (accuracy 0.95, precision 0.58, recall 0.50, F1 score 0.51) spotlight balanced performance. While attaining commendable accuracy, the intricate precision-recall interplay beckons further examination. In conclusion, data fusion emerges as a promising avenue for refining disease classification, effectively addressing challenges rooted in trait overlap. The integration of TensorFlow Keras underscores the potential for enhancing agricultural practices. Sustained endeavours toward enhanced recall remain pivotal, charting a trajectory for future advancements.
A Novel Machine Learning Based Approach for Detection and Classification of S...IRJET Journal
This document presents a novel machine learning approach for detecting and classifying sugarcane plant diseases using discrete wavelet transform (DWT). Existing methods use MATLAB and support vector machines with limited accuracy. The proposed method uses DWT for image segmentation to identify affected plant regions. It acquires images, pre-processes for noise reduction, segments using edge detection, extracts features from regions of interest, classifies diseases, and detects diseases based on image analysis and classification. The goal is to more accurately detect diseases early to control crop damage and losses. A dataset of 13 sugarcane diseases is used to evaluate the approach.
A deep learning-based mobile app system for visual identification of tomato p...IJECEIAES
Tomato is one of many horticulture crops in Indonesia which plays a vital role in supplying public food needs. However, tomato is a very susceptible plant to pests and diseases caused by bacteria and fungus. The infected diseases should be isolated as soon as it was detected. Therefore, developing a reliable and fast system is essential for controlling tomato pests and diseases. The deep learning-based application can help to speed up the identification of tomato disease as it can perform direct identification from the image. In this research, EfficientNetB0 was implemented to perform multi-class tomato plant disease classification. The model was then deployed to an android-based application using machine learning (ML) kit library. The proposed system obtained satisfactory results, reaching an average accuracy of 91.4%.
The document proposes a Vulture-based Auto-metric Graph Neural Network (VAGNN) framework for rice leaf disease classification. It involves several stages: image acquisition from a dataset, pre-processing using Anisotropic Diffusion Filter Based Unsharp Masking and crispening, segmentation using Bayesian Fuzzy Clustering, and classification of rice leaf diseases into bacterial blight, brown spot, blast, and tungro using the VAGNN. The performance of the proposed VAGNN framework is analyzed and compared to existing methods.
This document presents a method for recognizing five fungal diseases of wheat (leaf rust, stem rust, yellow rust, powdery mildew, and septoria) using deep learning on images. A dataset of 2414 wheat disease images (WFD2020) was created with over 80% representing single diseases and over 12% healthy plants. A convolutional neural network with the EfficientNet architecture achieved the best accuracy of 94.2% for identification. The recognition method was implemented as a Telegram bot, allowing users to assess wheat plants for disease in field conditions using mobile devices.
Detection of diseases in rice leaf using convolutional neural network with tr...IJECEIAES
Rice is the most cultivated crop in the agricultural field and is a major food source for more than 60% of the population in India. The occurrence of disease in rice leaves, majorly affects the rice quality, production and also the farmers’ income. Nowadays, new variety of diseases in rice leaves are identified and detected periodically throughout the world. Manual monitoring and detection of plant diseases proves to be time consuming for the farmer and also a costly affair for using chemicals in the disease treatment. In this paper, a deep learning method of convolutional neural networks (CNN) with a transfer learning technique is proposed for the detection of a variety of diseases in rice leaves. This method uses the ResNeXt network model for classifying the images of disease-affected plants. The proposed model’s performance is evaluated using accuracy, precision, recall, F1-score and specificity. The experimental results of ResNeXt model measured for accuracy, precision, recall, F1-score, and specificity, are respectively 99.22%, 92.87%, 91.97%, 90.95%, and 99.05%, which proves greater accuracy improvement than the existing methods of SG2-ADA, YOLOV5, InceptionResNetV2 and Raspberry Pi.
Image based anthracnose and red-rust leaf disease detection using deep learningTELKOMNIKA JOURNAL
Deep residual learning frameworks have achieved great success in image classification. This article presents the use of transfer learning which is applied on mango leaf image dataset for its disease’s detection. New methodology and training have been used to facilitate the easy and rapid implementation of the mango leaf disease detection system in practice. Proposed system can be used to identify the mango leaf for whether it is healthy or infected with the diseases like anthracnose or red rust. This paper describes all the steps which are considered during the experimentation and design. These steps include leaf image data collection, its preparation, data assessment by agricultural experts, and selection and tranning of deep neural network architectures. A deep residual framework, residual neural network (ResNET), was used to perform deep convolutional neural network training. ResNETs are easy to optimize and can achieve better accuracies. The experimental results obtained from “ResNET architectures, such as ResNet18, ResNet34, ResNet50, and ResNet101” show the accuracies from 94% to 98%. ResNET18 architecture selected from above for system design as it gives 98% accuracy for mango leaf disease’s detection. System will help farmers to identify leaf diseases in quick and efficient manner and facilitate decision-making in this front.
This document describes a system for predicting and detecting grape diseases using IoT sensors, image recognition, and machine learning models. Environmental sensors collect data on humidity, temperature, and soil moisture that is sent to the cloud and used to predict disease probability with a linear regression model. Images of grape leaves are also analyzed with a convolutional neural network model to detect three main diseases. The system is intended to help farmers monitor their crops, detect diseases early, and determine appropriate treatments to prevent economic losses from grape diseases.
BIOINFORMATICS AND ITS APPLICATIONS IN ENVIRONMENTAL SCIENCE AND HEALTH AND I...Dr Varruchi Sharma
Bioinformatics in integration to computational biology is a novel field which applies computer to biology, with which biologists are able to make detailed use of biological data for its advancement. In bioinformatics, the computers are used for the storage followed by the processing and analyzing, along with retrieval of large amounts of biologic and genomic data. In recent years, the field of Bioinformatics is gaining more interest. Earlier, the methodology adopted by the researchers to generate, collect followed by the analysis of various types of scientific data, which is the most time consuming and quite expensive for the work to be carried out. On the other hand with the help of computational tools & techniques, software & databases, one can process a large amount of biological data in a short span such as computer-aided drug designing (CADD). Environment and its protection in today’s word are the most challenging. The problems associated with its protection, planning can be resolved by the best bases of Information technology.
Plant Leaf Diseases Identification in Deep LearningCSEIJJournal
Crop diseases constitute a big threat to plant existence, but their rapid identification remains difficult in
many parts of the planet because of the shortage of the required infrastructure. In computer vision, plant
leaf detection made possible by deep learning has paved the way for smartphone-assisted disease
diagnosis. employing a public dataset of 4,306 images of diseased and healthy plant leaves collected under
controlled conditions, we train a deep convolutional neural network to spot one crop species and
4 diseases (or absence thereof). The trained model achieves an accuracy of 97.35% on a held-out test set,
demonstrating the feasibility of this approach. Overall, the approach of coaching deep learning models on
increasingly large and publicly available image datasets presents a transparent path toward smartphone-
assisted crop disease diagnosis on a large global scale. After the disease is successfully predicted with a
decent confidence level, the corresponding remedy for the disease present is displayed that may be taken as
a cure.
Bacterial foraging optimization based adaptive neuro fuzzy inference system IJECEIAES
Life of human being and animals depend on the environment which is surrounded by plants. Like human beings, plants also suffer from lot of diseases. Plant gets affected by completely including leaf, stem, root, fruit and flower; this affects the normal growth of the plant. Manual identification and diagnosis of plant diseases is very difficult. This method is costly as well as time-consuming so it is inefficient to be highly specific. Plant pathology deals with the progress in developing classification of plant diseases and their identification. This work clarifies the identification of plant diseases using leaf images caused by bacteria, viruses and fungus. By this method it can be identified and control the diseases. To identify the plant leaf disease Adaptive Neuro Fuzzy Inference System (ANFIS) was proposed. The proposed method shows more refined results than the existing works.
Diseases in edible and industrial plants remains a major concern, affecting producers and consumers. The problem is further exacerbated as there are different species of plants with a wide variety of diseases that reduce the effectiveness of certain pesticides while increasing our risk of illness. A timely, accurate and automated detection of diseases can be beneficial. Our work focuses on evaluating deep learning (DL) approaches using transfer learning to automatically detect diseases in plants. To enhance the capabilities of our approach, we compiled a novel image dataset containing 87,570 records encompassing 32 different plants and 74 types of diseases. The dataset consists of leaf images from both laboratory setups and cultivation fields, making it more representative. To the best of our knowledge, no such datasets have been used for DL models. Four pretrained computer vision models, namely VGG-16, VGG-19, ResNet-50, and ResNet-101 were evaluated on our dataset. Our experiments demonstrate that both VGG-16 and VGG-19 models proved more efficient, yielding an accuracy of approximately 86% and a f1-score of 87%, as compared to ResNet-50 and ResNet-101. ResNet-50 attains an accuracy and a f1-score of 46.9% and 45.6%, respectively, while ResNet-101 reaches an accuracy of 40.7% and a f1-score of 26.9%.
IRJET- Semi-Automatic Leaf Disease Detection and Classification System for So...IRJET Journal
This document presents a semi-automatic system for detecting and classifying leaf diseases in soybean plants. The system uses image processing and machine learning techniques. It first segments leaf images into clusters using k-means clustering. It then extracts color and texture features from the clusters. Support vector machines are used to classify leaves as healthy or diseased, and to further classify diseased leaves into categories like downy mildew or leaf blight. The system achieves acceptable average accuracy levels that are better than existing methods. It provides a way to identify leaf diseases early in an automated manner to improve crop yields and food security.
The Statutory Interpretation of Renewable Energy Based on Syllogism of Britis...AI Publications
The current production for energy consumption generates harmful impacts of carbon dioxide to the environment causing instability to sustainable development goals. The constitutional reforms of British Government serve to be an important means of resolving any encountered incompatibilities to political environment. This study aims to evaluate green economy using developed equation for renewable energy towards political polarization of corporate governance. The Kano Model Assessment is used to measure the equivalency of 1970 Patents Act to UK Intellectual Property tabulating the criteria for the fulfillment of sustainable development goals in respect to the environment, artificial intelligence, and dynamic dichotomy of administrative agencies and presidential restriction, as statutory interpretation development to renewable energy. The constitutional forms of British government satisfy the sustainable development goals needed to fight climate change, advocate healthy ecosystem, promote leadership of magnates, and delegate responsibilities towards green economy. The presidential partisanship must be observed to delineate parties of concerns and execute the government prescriptions in equivalence to the dichotomous relationship of technology and the environment in fulfilling the rights and privileges of all citizens. Hence, the political elites can execute corporate governance towards sustainable development of renewable energy promoting environmental parks and zero emission target of carbon dioxide discharges. The economic theory developed in statutory interpretation for renewable energy serves as a tool to reduce detrimental impacts of carbon dioxide to the environment, mitigate climate change, and produce artefacts of bioenergy and artificial intelligence promoting sustainable development. It is suggested to explore other vulnerabilities of artificial intelligence to prosper economic success.
Enhancement of Aqueous Solubility of Piroxicam Using Solvent Deposition SystemAI Publications
Piroxicam is a non-steroidal anti-inflammatory drug that is characterized by low solubility-high permeability. The present study was designed to improve the dissolution rate of piroxicam at the physiological pH's through its increased solubility by using solvent deposition system.
More Related Content
Similar to Survey on Plant Disease Detection using Deep Learning based Frameworks
A study on real time plant disease diagonsis systemIJARIIT
The document discusses developing a real-time plant disease diagnosis mobile application. It aims to allow farmers to easily capture images of plant leaves using a mobile camera, send the images to a central system for analysis, and receive diagnoses and treatment recommendations. The proposed system would use image processing and data mining techniques to analyze leaf images for abnormalities, identify the plant species, recognize any diseases present, and recommend appropriate pesticides and estimate treatment costs. This would provide a low-cost, convenient solution for farmers to quickly diagnose and respond to plant diseases.
A classification model based on depthwise separable convolutional neural net...IJECEIAES
Every year a number of rice diseases cause major damage to crop around the world. Early and accurate prediction of various rice plant diseases has been a major challenge for farmers and researchers. Recent developments in the convolutional neural networks (CNNs) have made image processing techniques more convenient and precise. Motivated from that in this research, a depthwise separable convolutional neural network based classification model has been proposed for identifying 12 types of rice plant diseases. Also, 8 different state-of-the-art convolution neural network model has been fine-tuned specifically for identifying the rice plant diseases and their performance has been evaluated. The proposed model performs considerably well in contrast to existing state-of-the-art CNN architectures. The experimental analysis indicates that the proposed model can correctly diagnose rice plant diseases with a validation and testing accuracy of 96.5% and 95.3% respectively while having a substantially smaller model size.
IRJET - Paddy Crop Disease Detection using Deep Learning Technique by using D...IRJET Journal
This document describes a study that uses deep learning and digital image processing techniques to detect diseases in paddy crops. The proposed system takes digital images of affected leaf parts as input and outputs the name of the detected disease and recommended pesticides. It first preprocesses and enhances the images before using edge detection, segmentation, and classification algorithms to analyze leaf parameters and identify diseases. The goal is to enable accurate, automated disease detection to help farmers protect crops and minimize pesticide usage.
This document discusses a proposed loss-fused convolutional neural network model for identifying and classifying plant disease. The model aims to improve predictive performance by combining the advantages of two different loss functions. The model was tested on a dataset from the Plant Village Database and achieved 98.93% accuracy in discriminating between affected and unaffected plant leaf samples, outperforming other existing methodologies. The paper provides background on plant disease detection techniques and reviews related work applying machine learning and deep learning methods.
An Innovative Approach for Tomato Leaf Disease Identification and its Benefic...IRJET Journal
This document summarizes an innovative approach for identifying diseases in tomato leaves using image processing and machine learning techniques. Specifically, a Convolutional Neural Network (CNN) model is developed and trained on a dataset of tomato leaf images showing various disease symptoms. Through testing and validation, the proposed approach achieves high accuracy in classifying different types of tomato leaf diseases. Integrating this method could enable timely disease detection, reduce crop losses, and optimize resource allocation for more sustainable agricultural practices. The research contributes a practical solution for automating tomato leaf disease detection to enhance disease management and food security.
POMDETECT: AN INVESTIGATION INTO LEAF DISEASE DETECTION TECHNIQUESIRJET Journal
This document discusses various techniques for detecting diseases in pomegranate leaves, including visual inspection, spectral imaging, and machine learning approaches. It analyzes several studies that evaluated these techniques and their effectiveness in detecting common diseases like bacterial blight, anthracnose, and powdery mildew. Machine learning techniques like convolutional neural networks were shown to outperform other methods in accuracy and speed of detection. The document highlights the potential of these techniques, especially deep learning, to develop automated disease monitoring systems and aid farmers in managing diseases.
POMDETECT: AN INVESTIGATION INTO LEAF DISEASE DETECTION TECHNIQUESIRJET Journal
This document discusses various techniques for detecting diseases in pomegranate leaves, including visual inspection, spectral imaging, and machine learning approaches. It analyzes several studies that evaluated these techniques and their effectiveness in detecting common diseases like bacterial blight, anthracnose, and powdery mildew. Machine learning techniques like convolutional neural networks were shown to outperform other methods in accuracy and speed of detection. The document highlights the potential of automated disease detection systems to help farmers manage diseases and improve crop yields.
Tomato Disease Fusion and Classification using Deep LearningIJCI JOURNAL
Tomato plants' susceptibility to diseases imperils agricultural yields. About 30% of the total crop loss is attributable to plants with disease. Detecting such illnesses in the plant is crucial to avoid significant output losses.This study introduces "data fusion" to enhance disease classification by amalgamating distinct disease-specific traits from leaf halves. Data fusion generates synthetic samples, fortifying a TensorFlow Keras deep learning model using a diverse tomato leaf image dataset. Results illuminate the augmented model's efficacy, particularly for diseases marked by overlapping traits. Enhanced disease recognition accuracy and insights into disease interactions transpire. Evaluation metrics (accuracy 0.95, precision 0.58, recall 0.50, F1 score 0.51) spotlight balanced performance. While attaining commendable accuracy, the intricate precision-recall interplay beckons further examination. In conclusion, data fusion emerges as a promising avenue for refining disease classification, effectively addressing challenges rooted in trait overlap. The integration of TensorFlow Keras underscores the potential for enhancing agricultural practices. Sustained endeavours toward enhanced recall remain pivotal, charting a trajectory for future advancements.
A Novel Machine Learning Based Approach for Detection and Classification of S...IRJET Journal
This document presents a novel machine learning approach for detecting and classifying sugarcane plant diseases using discrete wavelet transform (DWT). Existing methods use MATLAB and support vector machines with limited accuracy. The proposed method uses DWT for image segmentation to identify affected plant regions. It acquires images, pre-processes for noise reduction, segments using edge detection, extracts features from regions of interest, classifies diseases, and detects diseases based on image analysis and classification. The goal is to more accurately detect diseases early to control crop damage and losses. A dataset of 13 sugarcane diseases is used to evaluate the approach.
A deep learning-based mobile app system for visual identification of tomato p...IJECEIAES
Tomato is one of many horticulture crops in Indonesia which plays a vital role in supplying public food needs. However, tomato is a very susceptible plant to pests and diseases caused by bacteria and fungus. The infected diseases should be isolated as soon as it was detected. Therefore, developing a reliable and fast system is essential for controlling tomato pests and diseases. The deep learning-based application can help to speed up the identification of tomato disease as it can perform direct identification from the image. In this research, EfficientNetB0 was implemented to perform multi-class tomato plant disease classification. The model was then deployed to an android-based application using machine learning (ML) kit library. The proposed system obtained satisfactory results, reaching an average accuracy of 91.4%.
The document proposes a Vulture-based Auto-metric Graph Neural Network (VAGNN) framework for rice leaf disease classification. It involves several stages: image acquisition from a dataset, pre-processing using Anisotropic Diffusion Filter Based Unsharp Masking and crispening, segmentation using Bayesian Fuzzy Clustering, and classification of rice leaf diseases into bacterial blight, brown spot, blast, and tungro using the VAGNN. The performance of the proposed VAGNN framework is analyzed and compared to existing methods.
This document presents a method for recognizing five fungal diseases of wheat (leaf rust, stem rust, yellow rust, powdery mildew, and septoria) using deep learning on images. A dataset of 2414 wheat disease images (WFD2020) was created with over 80% representing single diseases and over 12% healthy plants. A convolutional neural network with the EfficientNet architecture achieved the best accuracy of 94.2% for identification. The recognition method was implemented as a Telegram bot, allowing users to assess wheat plants for disease in field conditions using mobile devices.
Detection of diseases in rice leaf using convolutional neural network with tr...IJECEIAES
Rice is the most cultivated crop in the agricultural field and is a major food source for more than 60% of the population in India. The occurrence of disease in rice leaves, majorly affects the rice quality, production and also the farmers’ income. Nowadays, new variety of diseases in rice leaves are identified and detected periodically throughout the world. Manual monitoring and detection of plant diseases proves to be time consuming for the farmer and also a costly affair for using chemicals in the disease treatment. In this paper, a deep learning method of convolutional neural networks (CNN) with a transfer learning technique is proposed for the detection of a variety of diseases in rice leaves. This method uses the ResNeXt network model for classifying the images of disease-affected plants. The proposed model’s performance is evaluated using accuracy, precision, recall, F1-score and specificity. The experimental results of ResNeXt model measured for accuracy, precision, recall, F1-score, and specificity, are respectively 99.22%, 92.87%, 91.97%, 90.95%, and 99.05%, which proves greater accuracy improvement than the existing methods of SG2-ADA, YOLOV5, InceptionResNetV2 and Raspberry Pi.
Image based anthracnose and red-rust leaf disease detection using deep learningTELKOMNIKA JOURNAL
Deep residual learning frameworks have achieved great success in image classification. This article presents the use of transfer learning which is applied on mango leaf image dataset for its disease’s detection. New methodology and training have been used to facilitate the easy and rapid implementation of the mango leaf disease detection system in practice. Proposed system can be used to identify the mango leaf for whether it is healthy or infected with the diseases like anthracnose or red rust. This paper describes all the steps which are considered during the experimentation and design. These steps include leaf image data collection, its preparation, data assessment by agricultural experts, and selection and tranning of deep neural network architectures. A deep residual framework, residual neural network (ResNET), was used to perform deep convolutional neural network training. ResNETs are easy to optimize and can achieve better accuracies. The experimental results obtained from “ResNET architectures, such as ResNet18, ResNet34, ResNet50, and ResNet101” show the accuracies from 94% to 98%. ResNET18 architecture selected from above for system design as it gives 98% accuracy for mango leaf disease’s detection. System will help farmers to identify leaf diseases in quick and efficient manner and facilitate decision-making in this front.
This document describes a system for predicting and detecting grape diseases using IoT sensors, image recognition, and machine learning models. Environmental sensors collect data on humidity, temperature, and soil moisture that is sent to the cloud and used to predict disease probability with a linear regression model. Images of grape leaves are also analyzed with a convolutional neural network model to detect three main diseases. The system is intended to help farmers monitor their crops, detect diseases early, and determine appropriate treatments to prevent economic losses from grape diseases.
BIOINFORMATICS AND ITS APPLICATIONS IN ENVIRONMENTAL SCIENCE AND HEALTH AND I...Dr Varruchi Sharma
Bioinformatics in integration to computational biology is a novel field which applies computer to biology, with which biologists are able to make detailed use of biological data for its advancement. In bioinformatics, the computers are used for the storage followed by the processing and analyzing, along with retrieval of large amounts of biologic and genomic data. In recent years, the field of Bioinformatics is gaining more interest. Earlier, the methodology adopted by the researchers to generate, collect followed by the analysis of various types of scientific data, which is the most time consuming and quite expensive for the work to be carried out. On the other hand with the help of computational tools & techniques, software & databases, one can process a large amount of biological data in a short span such as computer-aided drug designing (CADD). Environment and its protection in today’s word are the most challenging. The problems associated with its protection, planning can be resolved by the best bases of Information technology.
Plant Leaf Diseases Identification in Deep LearningCSEIJJournal
Crop diseases constitute a big threat to plant existence, but their rapid identification remains difficult in
many parts of the planet because of the shortage of the required infrastructure. In computer vision, plant
leaf detection made possible by deep learning has paved the way for smartphone-assisted disease
diagnosis. employing a public dataset of 4,306 images of diseased and healthy plant leaves collected under
controlled conditions, we train a deep convolutional neural network to spot one crop species and
4 diseases (or absence thereof). The trained model achieves an accuracy of 97.35% on a held-out test set,
demonstrating the feasibility of this approach. Overall, the approach of coaching deep learning models on
increasingly large and publicly available image datasets presents a transparent path toward smartphone-
assisted crop disease diagnosis on a large global scale. After the disease is successfully predicted with a
decent confidence level, the corresponding remedy for the disease present is displayed that may be taken as
a cure.
Bacterial foraging optimization based adaptive neuro fuzzy inference system IJECEIAES
Life of human being and animals depend on the environment which is surrounded by plants. Like human beings, plants also suffer from lot of diseases. Plant gets affected by completely including leaf, stem, root, fruit and flower; this affects the normal growth of the plant. Manual identification and diagnosis of plant diseases is very difficult. This method is costly as well as time-consuming so it is inefficient to be highly specific. Plant pathology deals with the progress in developing classification of plant diseases and their identification. This work clarifies the identification of plant diseases using leaf images caused by bacteria, viruses and fungus. By this method it can be identified and control the diseases. To identify the plant leaf disease Adaptive Neuro Fuzzy Inference System (ANFIS) was proposed. The proposed method shows more refined results than the existing works.
Diseases in edible and industrial plants remains a major concern, affecting producers and consumers. The problem is further exacerbated as there are different species of plants with a wide variety of diseases that reduce the effectiveness of certain pesticides while increasing our risk of illness. A timely, accurate and automated detection of diseases can be beneficial. Our work focuses on evaluating deep learning (DL) approaches using transfer learning to automatically detect diseases in plants. To enhance the capabilities of our approach, we compiled a novel image dataset containing 87,570 records encompassing 32 different plants and 74 types of diseases. The dataset consists of leaf images from both laboratory setups and cultivation fields, making it more representative. To the best of our knowledge, no such datasets have been used for DL models. Four pretrained computer vision models, namely VGG-16, VGG-19, ResNet-50, and ResNet-101 were evaluated on our dataset. Our experiments demonstrate that both VGG-16 and VGG-19 models proved more efficient, yielding an accuracy of approximately 86% and a f1-score of 87%, as compared to ResNet-50 and ResNet-101. ResNet-50 attains an accuracy and a f1-score of 46.9% and 45.6%, respectively, while ResNet-101 reaches an accuracy of 40.7% and a f1-score of 26.9%.
IRJET- Semi-Automatic Leaf Disease Detection and Classification System for So...IRJET Journal
This document presents a semi-automatic system for detecting and classifying leaf diseases in soybean plants. The system uses image processing and machine learning techniques. It first segments leaf images into clusters using k-means clustering. It then extracts color and texture features from the clusters. Support vector machines are used to classify leaves as healthy or diseased, and to further classify diseased leaves into categories like downy mildew or leaf blight. The system achieves acceptable average accuracy levels that are better than existing methods. It provides a way to identify leaf diseases early in an automated manner to improve crop yields and food security.
Similar to Survey on Plant Disease Detection using Deep Learning based Frameworks (20)
The Statutory Interpretation of Renewable Energy Based on Syllogism of Britis...AI Publications
The current production for energy consumption generates harmful impacts of carbon dioxide to the environment causing instability to sustainable development goals. The constitutional reforms of British Government serve to be an important means of resolving any encountered incompatibilities to political environment. This study aims to evaluate green economy using developed equation for renewable energy towards political polarization of corporate governance. The Kano Model Assessment is used to measure the equivalency of 1970 Patents Act to UK Intellectual Property tabulating the criteria for the fulfillment of sustainable development goals in respect to the environment, artificial intelligence, and dynamic dichotomy of administrative agencies and presidential restriction, as statutory interpretation development to renewable energy. The constitutional forms of British government satisfy the sustainable development goals needed to fight climate change, advocate healthy ecosystem, promote leadership of magnates, and delegate responsibilities towards green economy. The presidential partisanship must be observed to delineate parties of concerns and execute the government prescriptions in equivalence to the dichotomous relationship of technology and the environment in fulfilling the rights and privileges of all citizens. Hence, the political elites can execute corporate governance towards sustainable development of renewable energy promoting environmental parks and zero emission target of carbon dioxide discharges. The economic theory developed in statutory interpretation for renewable energy serves as a tool to reduce detrimental impacts of carbon dioxide to the environment, mitigate climate change, and produce artefacts of bioenergy and artificial intelligence promoting sustainable development. It is suggested to explore other vulnerabilities of artificial intelligence to prosper economic success.
Enhancement of Aqueous Solubility of Piroxicam Using Solvent Deposition SystemAI Publications
Piroxicam is a non-steroidal anti-inflammatory drug that is characterized by low solubility-high permeability. The present study was designed to improve the dissolution rate of piroxicam at the physiological pH's through its increased solubility by using solvent deposition system.
Analysis of Value Chain of Cow Milk: The Case of Itang Special Woreda, Gambel...AI Publications
Ethiopia has a long and rich history of dairy farming, which was mostly carried out by small and marginal farmers who raised cattle, camels, goats, and sheep, among other species, for milk. Finding the Itang Special Woreda cow milk value chain is the study's main goal. In order to gather primary data, 204 smallholder dairy farmer households were randomly selected, and the market concentration ratio was calculated using 20 traders. Descriptive statistics, econometric models, and rank analysis were used to achieve the above specified goals. Out of all the participants in the milk value chain, producers, cafés, hotels, and dairy cooperatives had the largest gross marketing margins, accounting for 100% of the consumer price in channels I and II, 55% in channels III and V, and 25.5% in channels V. The number of children under five, the number of milking cows owned, the amount of money from non-dairy sources, the frequency of extension service contacts, the amount of milk produced each day, and the availability of market information were found to have an impact on smallholders' involvement in the milk market. Numerous obstacles also limited the amount of milk produced and marketed. The poll claims that general health issues, sickness, predators, and a lack of veterinary care are plaguing farmers. In order to address the issue of milk perishability, the researchers recommended the host community and organization to construct an agro milk processor, renovate the dairy cooperative in the study region, and restructure the current conventional marketing to lower the transaction and cost of milk marketing.
Minds and Machines: Impact of Emotional Intelligence on Investment Decisions ...AI Publications
In the evolving landscape of financial decision-making, this study delves into the intricate relationships among Emotional Intelligence (EI), Artificial Intelligence (AI), and Investment Decisions (ID). By scrutinizing the direct influence of human emotional intelligence on investment choices and elucidating the mediating role of AI in this process, our research seeks to unravel the complex interplay between minds and machines. Through empirical analysis, we reveal that EI not only directly impacts ID but also exerts its influence indirectly through AI-mediated pathways. The findings underscore the pivotal role of emotional awareness in investor decision-making, augmented by the technological capabilities of AI. It suggests that most investors are influenced by the identified emotional intelligence when making investment decisions. Furthermore, AI substantially impacts investors' decision-making process when it comes to investing; nevertheless, AI partially mediates the relationship between emotional intelligence and investment decisions. This nuanced understanding provides valuable insights for financial practitioners, policymakers, and researchers, emphasizing the need for holistic strategies that integrate emotional and technological dimensions in navigating the intricacies of modern investment landscapes. As the synergy between human intuition and artificial intelligence becomes increasingly integral to financial decision-making, this study contributes to the ongoing discourse on the symbiotic relationship between minds and machines in investments.0
Bronchopulmonary cancers are common cancers with a poor prognosis. It is the leading cause of death by cancer in Algeria and in the world. Behind this unfavorable prognosis hides numerous disparities according to age, sex, and exposure to risk factors, ranking 4th among incident cancers and developing countries including Algeria, all sexes combined. It ranks 2nd cancers in men and 3rd among women. Whatever the age observed, the incidence of this cancer is higher in men than in women, however the gap is narrowing to the detriment of the latter. The results of scientific research agree to relate trends in incidence and mortality rates to tobacco consumption, including passive smoking. Furthermore, other risk factors are mentioned such as exposure to asbestos in the workplace or to radon for the general population, or even genetic predisposition. However, the weight of these etiological and/or predisposing factors is in no way comparable to that of tobacco in the genesis of lung cancer and the resulting mortality. We provide a literature review in our article on the descriptive and analytical epidemiology of lung cancer.
Further analysis on Organic agriculture and organic farming in case of Thaila...AI Publications
The objective of this paper is to present Further analysis on Organic agriculture and organic farming in case of Thailand agriculture and enhancing farmer productivity. In view of the demand for organic fertilizers, efforts should also be made to enhance and to develop more effective of compost, bio-fertilizer, and bio-pesticides currently used by farmers. Likewise, emphasis should also be laid on the cultivation of legumes and other crops that can enhance the fertility of the soil, as practiced by farmers in many developing countries to fertilize their lands. On the other hand, most of the farmers who practice this farm system found that they are adopting a number of SLMs and interested in joining the meeting or training to gain more and more knowledge.
Current Changes in the Role of Agriculture and Agri-Farming Structures in Tha...AI Publications
The objective os this study is to present Current Changes in the Role of Agriculture and Agri-Farming Structures in Thailand and Vietnam with SLM practices. Farmer’s adoption and investment in SLM is a key for controlling land degradation, enhancing the well-being of society, and ensuring the optimal use of land resources for the benefit of present and future generations (World Bank, 2006; FAO, 2018). And agriculture remains an essential element of lives of many farmers in term of the strong cultural and symbolic values that attach current working generation to do and to spend time for it but not intern of income generating.
Growth, Yield and Economic Advantage of Onion (Allium cepa L.) Varieties in R...AI Publications
Haphazard and low soil fertility, low yielding verities and poor agronomic practices are among the major factors constraining onion production in the central rift valley of Ethiopia. Therefore, a field experiment was conducted in East Showa Zone of Adami Tulu Jido Combolcha district in central rift valley areas at ziway from October 2021 to April 2022 to identify appropriate rate of NPSB fertilizer and planting pattern of onion varieties. The experiment was laid out in split plot design of factorial arrangement in three replications. The main effect of NPSB blended fertilizer rates and varieties (red coach and red king) significantly (p<0.01) influenced plant height, leaf length, leaf diameter, leaf number and fresh leaf weight, shoot dry matter per plant, and harvest index. Total dry biomass, bulb diameter, neck diameter, average fresh bulb weight, bulb dry matter, marketable bulb yield, and total bulb yield were significantly (p<0.01) influenced only by the main effect of NPSB blended fertilizer rates. In addition, unmarketable bulb yield was statistically significantly affected (p≥0.05) by the blended fertilizer rates and planting pattern. Moreover, days to 90% maturity of onion was affected by the main factor of NPSB fertilizer rate, variety and planting pattern. The non-fertilized plants in the control treatment were inferior in all parameters except unmarketable bulb yield and harvest index. Significantly higher marketable bulb yield (41 t ha-1) and total bulb yield (41.33 t ha-1) was recorded from 300 kg ha-1 NPSB blended fertilizer rate applied. Double row planting method and hybrid red coach onion variety had also gave higher growth and yields. The study revealed that the highest net benefit of Birr, 878,894 with lest cost of Birr 148,006 by the combinations of 150 kg blended NPSB ha-1 with double row planting method (40cm*20cm*7cm) and red coach variety which can be recommendable for higher marketable bulb yield and economic return of hybrid onion for small scale farmers in the study area. Also, for resource full producers (investors), highest net benefit of Birr 1,205,372 with higher cost (159,628 Birr) by application of 300 kg NPSB ha-1 is recommended as a second option. However, the research should be replicated both in season and areas to more verify the recommendations.
Evaluation of In-vitro neuroprotective effect of Ethanolic extract of Canariu...AI Publications
The ethanolic extract of canarium solomonense leaves (ecsl) was studied for its neuroprotective activity. The neuroprotective activity of ECSL was found to have a significant impact on neuronal cell death triggered by hydrogen peroxide (MTT assay) in human SH-SY5Y neuroblastoma cells. Scopolamine, a muscarinic receptor blocker, is frequently used to induce cognitive impairment in laboratory animals. Injections of scopolamine influence multiple cognitive functions, including motor function, short-term memory, and attention. Using the Morris water maze, the Y maze, and the passive avoidance paradigm, memory enhancing activity in scopolamine-induced amnesic rats was evaluated. Using the Morris water maze, the Y maze, and the passive avoidance paradigm, ECSL was found to have a substantial effect on the memory of scopolamine- induced amnesic rats. Our experimental data indicated that ECSL can reverse scopolamine induced amnesia and assist with memory issues.
The goal of neuroprotection is to shield neurons against damage, whether that damage is caused by environmental factors, pathogens, or neurodegenerative illnesses. Inhibiting protein-based deposit buildup, oxidative stress, and neuroinflammation, as well as rectifying abnormalities of neurotransmitters like dopamine and acetylcholine, are some of the ways in which medicinal herbs have neuroprotective effects [1-3]. This review will focus on the ways in which medicinal herbs may protect neurons.
A phytochemical and pharmacological review on canarium solomonenseAI Publications
The genus Canarium L. consists of 75 species of aromatic trees which are found in the rainforests of tropical Asia, Africa and the Pacific. The medicinal uses, botany, chemical constituents and pharmacological activities are now reviewed. Various compounds are tabulated according to their classes their structures are given. Traditionally canarium solomonense have been used to treat a broad array of illnesses. Pharmacological actions for canarium solomonense as discussed in this review include antibacterial, antimicrobial, antioxidant, anti-inflammatory, hepatoprotective and antitumor activity.
Influences of Digital Marketing in the Buying Decisions of College Students i...AI Publications
This research investigates the influence of digital marketing channels on purchasing decisions among college students in Ramanathapuram District. The study highlights that social media marketing, online advertising, and mobile marketing exhibit substantial positive effects on purchase decisions. However, email marketing's impact appears to be more complex. Moreover, the study explores how demographic variables like gender and academic level shape these effects. Notably, freshman students display varying susceptibility to specific digital marketing messages compared to their junior, senior, or graduate counterparts. These findings offer crucial insights for marketers aiming to tailor their strategies effectively to the preferences and behaviors of college students. By understanding the differential impacts of various digital marketing channels and considering demographic nuances, marketers can refine their approaches, optimize engagement, and ultimately enhance the effectiveness of their campaigns in targeting this demographic.
A Study on Performance of the Karnataka State Cooperative Agriculture & Rural...AI Publications
The Karnataka State Co-operative Agriculture and Rural Development Bank Limited is the apex bank of all the primary co-operative agriculture and rural development banks in the state. All the PCARD Banks in the state are affiliated to it. The KSCARD Bank provides financial accommodation to the PCARD Banks for their lending operations. In order to quick sanction and disbursement of loans and supervision over the PCARD Banks the KSCARD Bank has opened district level branches. Bank has established Women Development Cell to promote entrepreneurship among women in 2005. The Bank is identifying women borrowers in the rural areas by assigning suitable projects to motivate their self-confidence to lead independent life. Progress made in financing women entrepreneurs women.
Breast hamartoma is a rare, well-circumscribed, benign lesion made up of a variable quantity of glandular, adipose and fibrous tissue. This is a lesion that can affect women at any age from puberty. With the increasingly frequent use of imaging methods such as mammography and ultrasound as well as breast biopsy, cases of hamartoma diagnosed are increasing. The diagnosis of these lesions is made by mammography. The histological and radiological aspects are variable and depend on its adipose tissue content. The identification of these lesions is important in order to avoid surgical excisions. We report radio-clinical and pathological records of breast hamartoma.
A retrospective study on ovarian cancer with a median follow-up of 36 months ...AI Publications
Ovarian cancer is relatively common but serious and has a poor prognosis. The aim of this study is to highlight the epidemiological, diagnostic, therapeutic and evolutionary aspects of this malignant pathology managed at the Bejaia university hospital center. This is a retrospective and descriptive study over a period of 3 years (2019 - 2022) carried out on 20 patients who developed ovarian cancer. The average age of the patients was 50 years old, 53.23% of whom were over 45 years old. The CA-125 blood test was positive in 18 out of 20 patients. The tumors were discovered on ultrasound in 87.10% of cases and at laparotomy in 12.90%. Total hysterectomy with bilateral adnexectomy was the most performed procedure (64.52%). The early postoperative course was simple. 15 patients underwent second look surgery (16.13%) for locoregional recurrences. Epithelial tumors were the most frequent histological type (93.55%), including 79% in the advanced stage ( IIIc -IV) and 21% in the early stage (Ia- Ib ). Adjuvant chemotherapy was administered in 80% of patients. With a median follow-up of 36 months, 2 patients were lost to follow-up. The evolution was favorable in 27.42% and in 25.81% deaths occurred late postoperatively. Ovarian cancer is not common but serious given the advanced stages and the high rate of late postoperative deaths which were largely observed in patients deprived of adequate neoadjuvant or adjuvant chemotherapy.
More analysis on environment protection and sustainable agriculture - A case ...AI Publications
This study presents a case of tea and coffee crops , esp. environment protection and sustainable agriculture in Son La and Thai Nguyen of Vietnam. Research results show us that The process of having an agricultural product goes through many steps such as planting, planning, harvesting, packing, transporting, storing and distributing. - The State adopts policies to encourage innovation of agricultural production models and methods towards sustainability, adapting to climate change, saving water, and limiting the use of inorganic fertilizers and pesticides. chemicals and products for environmental treatment in agriculture; develop environmentally friendly agricultural models. Our research limitation is that we can expand for other crops, industries and markets as well.
Assessment of Growth and Yield Performance of Twelve Different Rice Varieties...AI Publications
The present investigation entitled “Assessment of growth and yield performance of twelve different rice varieties under north Konkan coastal zone of Maharashtra” was carried out during the kharif season of the year 2021 and 2022 on the field of ASPEE, Agricultural Research and Development Foundation, Tansa Farm, At Nare, Taluka Wada, District Palghar, Maharashtra, India. The experiment was laid out in Randomized Block Design (RBD). The twelve varieties namely Zini, Jaya, Dandi, Rahghudya, Govindbhog, Dangi, Gurjari, VNR-7, VNR-8, VNR-9, Karjat-3, and Karjat-5 were replicated thrice. The plant height (cm), number of tillers per plant, number of panicles per plant, number of panicles (m²), and length of panicle (cm) were noted to the maximum with cv. “VNR-7”. The highest number of seeds per panicle, test weight (gm), grain yield (q/ha), and straw yield (q/ha) were recorded with the cv. “VNR-7”. While the lowest number of days to 50% flowering was also recorded with cv. “VNR-7” during the year 2021 and 2022.
Cultivating Proactive Cybersecurity Culture among IT Professional to Combat E...AI Publications
In the current digital landscape, cybercriminals continually evolve their techniques to execute successful attacks on businesses, thus posing a great challenge to information technology (IT) professionals. While traditional cybersecurity approaches like layered defense and reactive security have helped IT professionals cope with traditional threats, they are ineffective in dealing with evolving cyberattacks. This paper focuses on the need for a proactive cybersecurity culture among IT professionals to enable them combat evolving threats. The paper emphasis that building a proactive security approach and culture can help among IT professionals anticipate, identify, and mitigate latent threats prior to them exploiting existing vulnerabilities. This paper also points out that as IT professionals use reactive security when dealing with traditional attacks, they can use it collaboratively with proactive security to effectively protect their networks, data, and systems and avoid heavy costs of dealing with cyberattack’s aftermaths and business recovery.
The Impacts of Viral Hepatitis on Liver Enzymes and BilrubinAI Publications
Viral hepatitis is an infection that causes liver inflammation and damage. Several different viruses cause hepatitis, including hepatitis A, B, C, D, and E. The hepatitis A and E viruses typically cause acute infections. The hepatitis B, C, and D viruses can cause acute and chronic infections. Hepatitis A causes only acute infection and typically gets better without treatment after a few weeks. The hepatitis A virus spreads through contact with an infected person’s stool. Protection by getting the hepatitis A vaccine. Hepatitis E is typically an acute infection that gets better without treatment after several weeks. Some types of hepatitis E virus are spread by drinking water contaminated by an infected person’s stool. Other types are spread by eating undercooked pork or wild game. Hepatitis B can cause acute or chronic infection. Recommendation for screening for hepatitis B in pregnant women or in those with a high chance of being infected. Protection from hepatitis B by getting the hepatitis B vaccine. Hepatitis C can cause acute or chronic infection. Doctors usually recommend one-time screening of all adults ages 18 to 79 for hepatitis C. Early diagnosis and treatment can prevent liver damage. The hepatitis D virus is unusual because it can only infect those who have a hepatitis B virus infection. A coinfection occurs when both hepatitis D and hepatitis B infections at the same time. A superinfection occurs already have chronic hepatitis B and then become infected with hepatitis D. The aim of this study is to find the effect of each type of viral hepatitis on the bilirubin (TB , DSB) , and liver enzymes; AST, ALT, ALP,GGT among viral hepatitis patients. 200 patients were selected from the viral hepatitis units in the central public health laboratory in Baghdad city, all the chosen cases were confirmed as a positive samples , they are classified into four equal group each with fifty individual and with a single serological viral hepatitis type either; anti-HAV( IgM ) , HBs Ag , anti-HCV ,or anti-HEV(IgM ). All patients were tested for; serum bilirubin ( TB ,D.SB ) , AST , ALT , ALP , GGT. Another fifty quite healthy and normal person was selected as a control group for comparison. . Liver enzymes and bilirubin changes are more pronounced in HAV, HEV than HCV and HBVAST and ALT lack some sensitivity in detecting HCV ,HBV and mild elevations of ALT or AST in asymptomatic patients can be evaluated efficiently by considering ,hepatitis B, hepatitis C. ALT is generally a more sensitive indicator of acute liver cell damage than AST, It is relatively specific for hepatocyte necrosis with a marked elevations in viral hepatitis. Liver enzymes and bilirubin changes are more pronounced in HAV, HEV than HCV and HBV.AST and ALT lack some sensitivity in detecting HCV ,HBV and mild elevations of ALT or AST in asymptomatic patients can be evaluated efficiently by considering ,hepatitis B, hepatitis C. ALT is generally a more sensitive indicator of acute liver
Determinants of Women Empowerment in Bishoftu Town; Oromia Regional State of ...AI Publications
The purpose of this study was to determine the status of women's empowerment and its determinants using women's asset endowment and decision-making potential as indicators. To determine representative sample size, this study used a two-stage sampling technique, and 122 sample respondents were selected at random. To analyze the data in this study, descriptive statistics and a probit model were used. The average women's empowerment index was 0.41, indicating a relatively lower status of women's empowerment in the study area. According to the study's findings, only 40.9% of women were empowered, while the remaining 59.1% were not. The probit model results show that women's access to the media, women's income, and their husbands' education status have a significant and positive impact on the status of women's empowerment, while the family size of households has a negative impact. As a result, it is important to enhance women's access to the media and income, promote family planning and contraception, and improve men's educational status in order to improve the status of women's empowerment.
Pictorial and detailed description of patellar instability with sign and symptoms and how to diagnose , what investigations you should go with and how to approach with treatment options . I have presented this slide in my 2nd year junior residency in orthopedics at LLRM medical college Meerut and got good reviews for it
After getting it read you will definitely understand the topic.
Travel vaccination in Manchester offers comprehensive immunization services for individuals planning international trips. Expert healthcare providers administer vaccines tailored to your destination, ensuring you stay protected against various diseases. Conveniently located clinics and flexible appointment options make it easy to get the necessary shots before your journey. Stay healthy and travel with confidence by getting vaccinated in Manchester. Visit us: www.nxhealthcare.co.uk
The biomechanics of running involves the study of the mechanical principles underlying running movements. It includes the analysis of the running gait cycle, which consists of the stance phase (foot contact to push-off) and the swing phase (foot lift-off to next contact). Key aspects include kinematics (joint angles and movements, stride length and frequency) and kinetics (forces involved in running, including ground reaction and muscle forces). Understanding these factors helps in improving running performance, optimizing technique, and preventing injuries.
How to Control Your Asthma Tips by gokuldas hospital.Gokuldas Hospital
Respiratory issues like asthma are the most sensitive issue that is affecting millions worldwide. It hampers the daily activities leaving the body tired and breathless.
The key to a good grip on asthma is proper knowledge and management strategies. Understanding the patient-specific symptoms and carving out an effective treatment likewise is the best way to keep asthma under control.
Breast cancer: Post menopausal endocrine therapyDr. Sumit KUMAR
Breast cancer in postmenopausal women with hormone receptor-positive (HR+) status is a common and complex condition that necessitates a multifaceted approach to management. HR+ breast cancer means that the cancer cells grow in response to hormones such as estrogen and progesterone. This subtype is prevalent among postmenopausal women and typically exhibits a more indolent course compared to other forms of breast cancer, which allows for a variety of treatment options.
Diagnosis and Staging
The diagnosis of HR+ breast cancer begins with clinical evaluation, imaging, and biopsy. Imaging modalities such as mammography, ultrasound, and MRI help in assessing the extent of the disease. Histopathological examination and immunohistochemical staining of the biopsy sample confirm the diagnosis and hormone receptor status by identifying the presence of estrogen receptors (ER) and progesterone receptors (PR) on the tumor cells.
Staging involves determining the size of the tumor (T), the involvement of regional lymph nodes (N), and the presence of distant metastasis (M). The American Joint Committee on Cancer (AJCC) staging system is commonly used. Accurate staging is critical as it guides treatment decisions.
Treatment Options
Endocrine Therapy
Endocrine therapy is the cornerstone of treatment for HR+ breast cancer in postmenopausal women. The primary goal is to reduce the levels of estrogen or block its effects on cancer cells. Commonly used agents include:
Selective Estrogen Receptor Modulators (SERMs): Tamoxifen is a SERM that binds to estrogen receptors, blocking estrogen from stimulating breast cancer cells. It is effective but may have side effects such as increased risk of endometrial cancer and thromboembolic events.
Aromatase Inhibitors (AIs): These drugs, including anastrozole, letrozole, and exemestane, lower estrogen levels by inhibiting the aromatase enzyme, which converts androgens to estrogen in peripheral tissues. AIs are generally preferred in postmenopausal women due to their efficacy and safety profile compared to tamoxifen.
Selective Estrogen Receptor Downregulators (SERDs): Fulvestrant is a SERD that degrades estrogen receptors and is used in cases where resistance to other endocrine therapies develops.
Combination Therapies
Combining endocrine therapy with other treatments enhances efficacy. Examples include:
Endocrine Therapy with CDK4/6 Inhibitors: Palbociclib, ribociclib, and abemaciclib are CDK4/6 inhibitors that, when combined with endocrine therapy, significantly improve progression-free survival in advanced HR+ breast cancer.
Endocrine Therapy with mTOR Inhibitors: Everolimus, an mTOR inhibitor, can be added to endocrine therapy for patients who have developed resistance to aromatase inhibitors.
Chemotherapy
Chemotherapy is generally reserved for patients with high-risk features, such as large tumor size, high-grade histology, or extensive lymph node involvement. Regimens often include anthracyclines and taxanes.
PGx Analysis in VarSeq: A User’s PerspectiveGolden Helix
Since our release of the PGx capabilities in VarSeq, we’ve had a few months to gather some insights from various use cases. Some users approach PGx workflows by means of array genotyping or what seems to be a growing trend of adding the star allele calling to the existing NGS pipeline for whole genome data. Luckily, both approaches are supported with the VarSeq software platform. The genotyping method being used will also dictate what the scope of the tertiary analysis will be. For example, are your PGx reports a standalone pipeline or would your lab’s goal be to handle a dual-purpose workflow and report on PGx + Diagnostic findings.
The purpose of this webcast is to:
Discuss and demonstrate the approaches with array and NGS genotyping methods for star allele calling to prep for downstream analysis.
Following genotyping, explore alternative tertiary workflow concepts in VarSeq to handle PGx reporting.
Moreover, we will include insights users will need to consider when validating their PGx workflow for all possible star alleles and options you have for automating your PGx analysis for large number of samples. Please join us for a session dedicated to the application of star allele genotyping and subsequent PGx workflows in our VarSeq software.
Giloy in Ayurveda - Classical Categorization and SynonymsPlanet Ayurveda
Giloy, also known as Guduchi or Amrita in classical Ayurvedic texts, is a revered herb renowned for its myriad health benefits. It is categorized as a Rasayana, meaning it has rejuvenating properties that enhance vitality and longevity. Giloy is celebrated for its ability to boost the immune system, detoxify the body, and promote overall wellness. Its anti-inflammatory, antipyretic, and antioxidant properties make it a staple in managing conditions like fever, diabetes, and stress. The versatility and efficacy of Giloy in supporting health naturally highlight its importance in Ayurveda. At Planet Ayurveda, we provide a comprehensive range of health services and 100% herbal supplements that harness the power of natural ingredients like Giloy. Our products are globally available and affordable, ensuring that everyone can benefit from the ancient wisdom of Ayurveda. If you or your loved ones are dealing with health issues, contact Planet Ayurveda at 01725214040 to book an online video consultation with our professional doctors. Let us help you achieve optimal health and wellness naturally.
Histololgy of Female Reproductive System.pptxAyeshaZaid1
Dive into an in-depth exploration of the histological structure of female reproductive system with this comprehensive lecture. Presented by Dr. Ayesha Irfan, Assistant Professor of Anatomy, this presentation covers the Gross anatomy and functional histology of the female reproductive organs. Ideal for students, educators, and anyone interested in medical science, this lecture provides clear explanations, detailed diagrams, and valuable insights into female reproductive system. Enhance your knowledge and understanding of this essential aspect of human biology.
These lecture slides, by Dr Sidra Arshad, offer a simplified look into the mechanisms involved in the regulation of respiration:
Learning objectives:
1. Describe the organisation of respiratory center
2. Describe the nervous control of inspiration and respiratory rhythm
3. Describe the functions of the dorsal and respiratory groups of neurons
4. Describe the influences of the Pneumotaxic and Apneustic centers
5. Explain the role of Hering-Breur inflation reflex in regulation of inspiration
6. Explain the role of central chemoreceptors in regulation of respiration
7. Explain the role of peripheral chemoreceptors in regulation of respiration
8. Explain the regulation of respiration during exercise
9. Integrate the respiratory regulatory mechanisms
10. Describe the Cheyne-Stokes breathing
Study Resources:
1. Chapter 42, Guyton and Hall Textbook of Medical Physiology, 14th edition
2. Chapter 36, Ganong’s Review of Medical Physiology, 26th edition
3. Chapter 13, Human Physiology by Lauralee Sherwood, 9th edition
5-hydroxytryptamine or 5-HT or Serotonin is a neurotransmitter that serves a range of roles in the human body. It is sometimes referred to as the happy chemical since it promotes overall well-being and happiness.
It is mostly found in the brain, intestines, and blood platelets.
5-HT is utilised to transport messages between nerve cells, is known to be involved in smooth muscle contraction, and adds to overall well-being and pleasure, among other benefits. 5-HT regulates the body's sleep-wake cycles and internal clock by acting as a precursor to melatonin.
It is hypothesised to regulate hunger, emotions, motor, cognitive, and autonomic processes.
2. Mandal / Survey on Plant Disease Detection using Deep Learning based Frameworks
Int. J. Med. Phar. Drug Re., 7(2), 2023
Online Available at: https://www.aipublications.com/ijmpd/ 28
techniques for image processing for identifying plant
diseases has emerged as a popular study area.
Fig. 1: Some images from various datasets of various plant diseases. From [10] 1.a: Grey Leaf Spot, 1.b: Northern Leaf Spot,
1.c: Northern Leaf Blight. From [9] 1.d: Coffee Blister Spot, 1.e: Rice Leaf Scald, 1.f: Cashew Powdery Mildew. From [7] 1.g:
Cherry Powdery Mildew, 1.h: Strawberry Leaf Scorch, 1.i: Peach Bacterial Spot. From [8] 1.j: Tomato Septoria Leaf Spot,
1.k: Potato Early Blight, 1.l: Grape Leaf Black Rot.
While using tiny data sets and creating
theoretical conclusions, traditional image processing
algorithms produced acceptable results and
performance for plant disease identification using leaf
pictures. Deep learning is being vividly used for script
identification [30-38] and also for human disease
detection [39-44]. Deep learning has revolutionised
the field of computer vision, specifically in the field of
object detection and image classification. Deep
learning along with transfer learning is now regarded
as a promising tool to enhance the ability of plant
disease detection systems in order to achieve better
results, widen the scope of disease detection, and
implement a useful real-time system for identification
of plant diseases.
There are plenty of reviews and survey
articles available [45-53] but this article surveys the
most recent advancement in the field of plant disease
detection using various deep learning techniques. To
track this recent advancement, articles that are openly
accessible and published in 2022 and 2023 have been
selected as references.
This paper contains a total of 5 sections.
Section 2 introduces the various datasets used by the
articles which are under the survey. The section 3
presents the surveys of 15 selected articles on recent
advancement of plant disease detection. The next
section discusses the future scope available on the
topic. The last section provides a conclusion.
II. DATASET
Typically, for deep learning dataset comprises
three subsets: the training set, validation set, and test
set. The training set facilitates the learning process of
the model, while the validation set is commonly
utilised to fine-tune hyperparameters during the
training phase. On the other hand, the test set contains
data samples that the model has not previously
encountered, and it serves as a means to assess the
performance of the deep learning model. In this
3. Mandal / Survey on Plant Disease Detection using Deep Learning based Frameworks
Int. J. Med. Phar. Drug Re., 7(2), 2023
Online Available at: https://www.aipublications.com/ijmpd/ 29
section, the available datasets and how they have been
developed i.e., the source of the images are discussed.
Khan et al. [11] used a dataset [12]. Six distinct
diseases for cucumber leaf, including downy mildew,
powdery mildew, mosaic, anthracnose, angular spot,
and blight, are included in this dataset. Initially, each
class comprises 100 to 150 photos, along with them
they created a straightforward method for data
augmentation that consists of four operations: vertical
and horizontal flip, rotation of 45 and 60 degrees. The
number of photos in each class is increased to 2000 by
using this approach, which is applied to each class of
cucumber illness. This enhanced dataset is used to
train deep models in subsequent rounds.
A well known dataset called “PlantVillage”
which was originally published as [14] but later
republished in a paper and available as [7]. This
dataset contains a total of 54303 images that includes
images of 14 different plants and 38 different diseases.
Here is some example shown in Fig. 2 collected from
a dataset. The article [13] used 2152 images of 3 classes
of potato leaves taken from [14] and 1700 images self
collected of two potato leaf disorders. This dataset is
also used as a part or as a whole in the articles [15],
[16], [17], [18], [58], [59].
Fig. 2: Some example images of - 2.1.a: Healthy tomato leaf, 2.1.b: Tomato leaf with Leaf Mold, 2.1.c: Tomato leaf with Early
Blight, 2.1.d: Tomato leaf with Mosaic virus, 2.2.a: Healthy apple leaf, 2.2.b: Apple leaf with Cedar Apple Rust, 2.2.c: Apple
leaf with Black Rot, 2.2.d: Apple leaf with Apple Scab, 2.3.a: Healthy grape leaf, 2.3.b: Grape leaf with Esca (Black Measles),
2.3.c: Grape leaf with Black Rot, 2.3.d: Grape leaf with Leaf Blight, 2.4.a: Healthy corn leaf, 2.4.b: Corn leaf with Common
Rust, 2.4.c: Corn leaf with Gray Leaf Spot, 2.4.d: Corn Leaf with Northern Leaf Blight, 2.5.a: Health Peach Leaf, 2.5.b: Peach
leaf with Bacterial spot, 2.5.c: Healthy potato leaf, 2.5.d: Potato leaf with Late Blight.
Along with [7], the article [15] used datasets
[19], [20], [21], [22] to create a dataset consisting 58
plant disease classes and one no-leaf class. [23] used a
custom made dataset [24] having three classes of corn
diseases. A guava leaf dataset [26] of four disease
classes is used by [25]. In the article [27] about wheat
diseases, the authors used their own dataset of 19160
images in five different classes, a small part of which
is available at [28].
Along with the dataset PlantVillage dataset
[14], the article [16] used Plantdoc dataset [8],
Digipathos dataset [9], NLB dataset [29] and CD&S
dataset [10]. CD&S dataset is a custom dataset of
images acquired from the Purdue Agronomy Center
for Research and Education (ACRE) consisting of
three classes of diseases: Northern Leaf Blight,
Northern Leaf Spot and Gray Leaf Spot.
4. Mandal / Survey on Plant Disease Detection using Deep Learning based Frameworks
Int. J. Med. Phar. Drug Re., 7(2), 2023
Online Available at: https://www.aipublications.com/ijmpd/ 30
Algani et al. [54] used a dataset for citrus fruits
and leaves [60]. Yong et al. [55] used another dataset
[61] of oil palm seedlings for their work. Ma et al. [56]
created their own dataset collecting images from Jilin
Academy of Agricultural Sciences. Guerrero-Ibañez
and Reyes-Muñoz [57] used a public dataset [62] of
tomato leaves with 11000 images of 10 categories.
They have also added 2500 images of their own
collection.
The consolidated summary of the available
plant disease datasets are tabulated in Table 1.
Table 1: Summary of the state of the art plant disease datasets.
Author(s) Year Dataset specification
Zhang et al. [12] 2017 Six classes of cucumber leaf.
Hughes and Salath [14] 2015 38 disease classes of 14 different plants.
J and Gopal [7] 2019 38 disease classes of 14 different plants.
Singh et al. [8] 2020 17 classes of disease of 13 different plants.
Barbedo et al. [9] 2018 171 disease class and 21 different plants.
Ahmed [10] 2021 3 classes of corn disease.
Hu et al. [19] 2019 3 classes of tea leaf disease.
Kour and Arora [20] 2019 2 classes with 16 subclasses of 8 different
plants.
Krohling et al. [21] 2019 Healthy and diseased Arabica coffee leaves
Parraga-Alava et al. [22] 2019 Healthy and diseased Robusta coffee leaves
Ahmad et al. [24] 2021 3 classes of corn disease.
Rajbongshi et al. [26] 2022 Images of guava diseases of six classes.
Long et al. [28] 2022 999 wheat disease images with five classes.
Wiesner-Hanks et al. [29] 2018 Images of northern leaf blight of maize.
Rauf et al. [60] 2019 Citrus fruits and leaves dataset.
Azmi et al. [61] 2020 Oil Palm Seedlings images.
B et al. [62] 2020 10 classes of tomato leaves including healthy
leaves.
III. STATE-OF-THE-ART METHODS
In this section, recent studies that employ
popular machine learning architectures for
identifying and classifying leaf diseases are presented.
Additionally, some related works are discussed which
introduce the modified or improved versions of deep
learning architectures to achieve better results.
This study of Khan et al. [11] proposes an
Entropy-ELM-based system for deep learning to
identify illnesses of cucumber leaves. Pre-trained deep
models: VGG16, ResNet50, ResNet101 and
DenseNet201 are trained in the suggested framework,
and one of them is chosen based on accuracy. This
model is then used to select the best features using the
suggested Entropy-Elm technique. The feature
selection strategy is applied in the step opposite,
which involves fusing the characteristics of all pre-
trained models. The final stage combines the features
from the previous two phases to perform
classification. Using a dataset of enhanced cucumber
leaves, the proposed framework was tested, and its
accuracy was 98.48%. In this article total nine
classifiers are used among them there are four types of
SVM: Linear, Cubic, Quadratic and MG SVM and five
types of KNN: Fine, Weighted, Subspace, Cosine,
Cubic and Medium KNN. Each classifier's
performance is calculated using a variety of metrics,
including F1-Score, precision rate, recall rate, time,
and accuracy.
5. Mandal / Survey on Plant Disease Detection using Deep Learning based Frameworks
Int. J. Med. Phar. Drug Re., 7(2), 2023
Online Available at: https://www.aipublications.com/ijmpd/ 31
Mahum et al. [13] proposed a model that uses
the efficient DenseNet 201 architecture. This contains
an extra transition layer than the original DenseNet
architecture. This improves the compactness and
reduces the computation load. The cross entropy loss
function is reweighted by the architecture to address
the problem of class imbalance inside the dataset. The
limited size of the training and testing images lets the
model identify illnesses in potato leaves effectively
and efficiently. Due to the use of an additional
transition layer and preprocessed images, the system
also achieves 97.2% accuracy while being
computationally quick.
In the article by Pandian et al. [15] a deep
convolutional neural network with 14 layers (14-
DCNN) has been proposed. To get a balanced dataset
along with various public dataset, image
augmentation processes like deep convolutional
generative adversarial network, neural style transfer
and basic image manipulation were used. The coarse-
to-fine searching strategy with random search were
used to enhance the proposed DCNN model's training
performance and to choose the most appropriate
hyperparameter values. The training and validation
accuracy of the 14-DCNN model were 99.993% and
99.985%, respectively. Since there are less
convolutional and pooling operations in the
suggested 14-DCNN than there are in transfer
learning approaches, the training time was shorter
than that of the transfer learning techniques.
Divyanth et al. [23] used three semantic
segmentation models: SegNet, UNet and
DeepLabV3+ in two stages. Stage one is used to extract
the leaf image from the complex background and
stage two is used for detection. They have compared
the segmentation models by their performance and
found UNet performed better for stage one and
DeepLabV3+ model in the stage two. They have also
calculated the severity of the disease by calculating the
area of the disease lesions with improved results.
Nandi et al. [25] have used five CNN models:
VGG-16, GoogleNet, ResNet-18, MobileNet-v2 and
Efficient Net. They have applied model quantization
techniques on above CNN models and found that
GoogleNet achieved the lowest size with 97%
accuracy. The EfficientNet model achieved 99%
accuracy with reasonably low size after quantization.
Long et al. [27] used RMSProp optimizer
while training their model CerealConv which gave a
classification accuracy of 97.05%. When compared to
trained pathologists on a sample of the bigger
dataset's photos, the model produced an accuracy
score that was 2% higher.
Algani et al. [54] used CNN with Ant Colony
Optimization (ACO-CNN). In their study the ACO-
CNN model outperformed the C-GAN, CNN, and
SGD models in terms of accuracy, precision, recall,
and F1-score. The accuracy rates for C-GAN, CNN,
and SGD are 99.6%, 99.97%, and 85%, respectively.
The F1 score has attained the greatest rate compared
to other models since the accuracy rate in the ACO-
CNN model is 99.98%.
Yong et al. [55] worked particularly for the
detection of Basal Stem Rot. They presented
hyperspectral imaging and a deep learning based
approach. The method involves dividing the
seedling's top-down view into the regions and
analysing spectral changes across leaf positions.
Segmented images of the plant were generated to
assess the impact of background images on detection
accuracy using a Mask Region-based Convolutional
Neural Network (RCNN). They trained their system
using VGG16 and Mask RCNN and obtained the
highest precision of 94.32% using VGG16.
Ma et al. [56] extracted multidimensional
features from both spatial and channel perspectives
using an attention module that was integrated into the
cross-stage partial network backbone. Additionally,
they incorporated a spatial pyramid pooling module
that utilises dilated convolutions into the network to
expand the range of crop-disease-related information
collected from images of crops. Their proposed model
CCA-YOLO obtained an average precision of 90.15%.
Guerrero-Ibanez and Reyes-Muñoz [57]
designed a CNN-based architecture that incorporates
GAN (Generative Adversarial Network)-based data
augmentation techniques for early identification and
classification of diseases in tomato leaves. They
achieved a highest accuracy of 99.64% in disease
classification.
Saeed et al. [58] discussed the identification of
tomato leaf diseases by categorising images of healthy
and unhealthy tomato leaves utilising the pre-trained
CNNs - Inception V3 and Inception ResNet V2. They
6. Mandal / Survey on Plant Disease Detection using Deep Learning based Frameworks
Int. J. Med. Phar. Drug Re., 7(2), 2023
Online Available at: https://www.aipublications.com/ijmpd/ 32
trained these models using a public dataset known as
PlantVillage and obtained a highest accuracy of
99.22% in the validation.
Joshi and Bhavsar [59] used standard deep
learning models to classify nine categories of leaf
diseases. They also developed a CNN framework to
classify the same. Compared with the standard
models they obtained better results in their developed
model. They reported the highest classification
accuracy of 95%.
Ahmad et al. [16] assessed the effectiveness of
five standard deep learning models in identifying
plant diseases across diverse environmental
conditions. These models were trained using corn
disease images of public datasets. They observe that
using DenseNet169 yielded the highest generalisation
performance for identifying plant diseases, achieving
validation accuracy of 81.60%.
A fine-tuning method to the developed CNN
models was discussed in [17] to classify tomato leaf
disease. Authors performed a hyperparameter
optimization using the particle swarm optimization
algorithm (PSO). The weights of these architectures
are optimised using grid search optimization. They
also proposed a triple and quintuple ensemble model
and classifies the datasets using a cross-validation
approach. Using the ensembles method they reported
the highest classification accuracy of 99.60%.
Francis et al. [18] described the application of
standard deep learning models in agriculture for
automatically generating features and developing a
predictive system. The authors emphasised the
importance of segmentation of diseased areas, transfer
learning, and fine-tuning the model. They initially
trained on a dataset of healthy and diseased apple
leaves and evaluated the performance of multiple
MobileNet models with varying depth and resolution
multipliers. They obtained a highest accuracy of
99.7% using the combination of Mobilenet and K
means clustering method.
In Table 2 the chronological major
improvements in the techniques of plant disease
detection and classification is presented.
Table 2: Notable improvement in plant leaf disease detection and classification.
Author(s)
Month &
Year
Method Result Remarks
Khan et al. [11] Jan’ 2022 Entropy-ELM 98.4%
Entropy-ELM is used for
feature selection. Classification
done using F-DenseNet201
Mahum et al. [13] Apr’ 2022
Efficient-
DenseNet201
97.2%
Reduced the impact of class
imbalance by using a
reweighted cross-entropy loss
function.
Pandian et al. [15] Jul’ 2022 14-DCNN
Classification
Accuracy 99.96%
and Precision
99.79%
Optimised the value of the
hyperparameter
Divyanth et al.
[23]
Aug’ 2022
SegNet, UNet and
DeepLabV3+
For estimating
disease severity,
R2 value obtained
= 0.96
Disease severity estimation
done.
Nandi et al. [25] Sep’ 2022
VGG-16, GoogleNet,
ResNet-18,
MobileNet-v2 and
Efficient Net with
model quantization
techniques
GoogleNet 97%
EfficientNet 99%
Model optimization used.
Long et al. [27] Nov’ 2022
CerealConv with
RMSProp optimizer
97.05%
Used masked images to verify
the working of the model.
7. Mandal / Survey on Plant Disease Detection using Deep Learning based Frameworks
Int. J. Med. Phar. Drug Re., 7(2), 2023
Online Available at: https://www.aipublications.com/ijmpd/ 33
Algani et al. [54] Dec’ 2022 ACO-CNN 99.98%
Obtained better results than C-
GAN, CNN and SDG models.
Yong et al. [55] Dec’ 2022
VGG-16 and Mask
RCNN
94.32% Hyperspectral imaging used.
Ma et al. [56] Jan’ 2023 CCA-YOLO 90.15%
Dual-attention module used
with the CSPNet backbone
network
Guerrero-Ibañez
and Reyes-Muñoz
[57]
Jan, 2023
CNN with GAN
data augmentation
99.64%
GAN based data
augmentation techniques
used.
Saeed et al. [58] Jan’ 2023
Inception V3 and
Inception ResNet V2
99.22% Transfer learning used.
Joshi and Bhavsar
[59]
Jan’ 2023 Night-CNN 95% It is relatively quick.
Ahmad et al. [16] Jan’ 2023
VGG16, ResNet50,
InceptionV3,
DenseNet169, and
Xcep-
tion
Average
generalised
testing accuracy
of 81.60%
Generalised performance
computed.
Ulutaş and
Aslantaş [17]
Feb’ 2023 Ensemble CNN 99.60%
Particle swarm optimization
algorithm used.
Francis et al. [18] Feb’ 2023
Four variants of
MobileNet models
with and without K-
means algorithm.
99.6% without K-
means, 99.7%
with K-means
With K-means and without K-
means algorithms compared.
IV. FUTURE SCOPE
● In future, features can be improved using the
Butterfly metaheuristic algorithm and the
EfficientNet deep model can be implemented for
plant disease detection. Graph CNN and
reinforcement learning can also be applied to get
better results.
● Many domains, including human illness
detection, activity and gesture recognition in
security systems, and other plant disease
detection issues, can use the Efficient DenseNet
201 model with certain adjustments to its
architecture. With the adjustment of the
parameters it might be possible to reduce the
number of training images and training time with
similar or higher accuracy.
● The use of the 14-DCNN model can be extended
to analyse disease severity and disease detection
using other parts of a plant.
● By measuring the percentage of impacted regions
and recommending necessary corrective actions,
DL models can be expanded to anticipate severity.
● High accuracy can be achieved for real field plant
images with diverse backgrounds.
● Mobile application based plant disease detection
systems can be achieved which can run with low
hardware resources and with fast detection
abilities.
V. CONCLUSION
This study highlighted and analysed various
methodologies based on performance, datasets, plant
leaf patterns, and diverse classes of disease. It also
analysed the limitations of the state of the art and
directed towards the potential improvement. The
study's conclusion highlights the significance of
incorporating computer vision, machine learning, and
deep learning into automated devices such as smart
mobiles in modern agriculture. In future research,
attention should be given to expanding the disease
detection system from laboratory settings to field
conditions to maintain high accuracy in identification
and prioritising research on novel image processing
algorithms to facilitate the segmentation and
8. Mandal / Survey on Plant Disease Detection using Deep Learning based Frameworks
Int. J. Med. Phar. Drug Re., 7(2), 2023
Online Available at: https://www.aipublications.com/ijmpd/ 34
extraction of leaf lesion features in complicated
scenarios.
REFERENCES
[1] J. Fletcher, F. D, and L. Je, “Healthy plants: necessary for
a balanced ‘One Health’ concept.,” Veterinaria Italiana,
vol. 45, no. 1, pp. 79–95, Jan. 2009.
[2] “One Health Basics | One Health | CDC.”
https://www.cdc.gov/onehealth/basics/ (accessed
Jan. 15, 2023).
[3] “About,” Food and Agriculture Organization of the United
Nations. https://www.fao.org/plant-health-
2020/about/en/ (accessed Jan. 15, 2023).
[4] S. Savary, L. Willocquet, S. J. Pethybridge, P. D. Esker,
N. McRoberts, and A. Nelson, “The global burden of
pathogens and pests on major food crops,” Nature
Ecology and Evolution, vol. 3, no. 3, pp. 430–439, Feb.
2019, doi: 10.1038/s41559-018-0793-y.
[5] “Climate change fans spread of pests and threatens
plants and crops, new FAO study.”
https://www.fao.org/news/story/en/item/1402920/
icode/ (accessed Jan. 15, 2023).
[6] M. A. Ebrahimi, M. H. Khoshtaghaza, S. Minaei, and B.
Jamshidi, “Vision-based pest detection based on SVM
classification method,” Computers and Electronics in
Agriculture, vol. 137, pp. 52–58, May 2017, doi:
10.1016/j.compag.2017.03.016.
[7] A. P. J and G. GOPAL, “Data for: Identification of Plant
Leaf Diseases Using a 9-layer Deep Convolutional
Neural Network.” Mendeley Data, Apr. 18, 2019.
[Online]. Available:
https://data.mendeley.com/datasets/tywbtsjrjv/1
doi: 10.17632/tywbtsjrjv.1
[8] D. Singh, N. Jain, P. Jain, P. Kayal, S. Kumawat, and N.
Batra, “PlantDoc: A Dataset for Visual Plant Disease
Detection.” Association for Computing Machinery,
2020. [Online]. Available:
https://doi.org/10.1145/3371158.3371196
doi:10.1145/3371158.3371196
[9] J. G. A. Barbedo et al., “Annotated Plant Pathology
Databases for Image-Based Detection and Recognition
of Diseases,” IEEE Latin America Transactions, vol. 16,
no. 6, pp. 1749–1757, Aug. 2018, doi:
10.1109/tla.2018.8444395.
[10] A. Ahmad, “CD&S Dataset.” Aug. 01, 2021. [Online].
Available: https://osf.io/s6ru5/
doi:10.17605/OSF.IO/S6RU5
[11] M. A. Khan et al., “Cucumber Leaf Diseases Recognition
Using Multi Level Deep Entropy-ELM Feature
Selection,” Applied Sciences, vol. 12, no. 2, p. 593, Jan.
2022, doi: 10.3390/app12020593.
[12] S. Zhang, X. Wu, Z.-H. You, and L. Zhang, “Leaf image
based cucumber disease recognition using sparse
representation classification,” Computers and Electronics
in Agriculture, vol. 134, pp. 135–141, Mar. 2017, doi:
10.1016/j.compag.2017.01.014.
[13] R. Mahum et al., “A novel framework for potato leaf
disease detection using an efficient deep learning
model,” Human and Ecological Risk Assessment, pp. 1–24,
Apr. 2022, doi: 10.1080/10807039.2022.2064814.
[14] D. P. Hughes and M. Salath, “An open access repository
of images on plant health to enable the development of
mobile disease diagnostics,” CoRR, vol. abs/1511.08060,
2015, [Online]. Available:
https://arxiv.org/abs/1511.08060
[15] J. A. Pandian, V. Kumar, O. Geman, M. Hnatiuc, M.
Arif, and K. K, “Plant Disease Detection Using Deep
Convolutional Neural Network,” Applied Sciences, vol.
12, no. 14, p. 6982, Jul. 2022, doi: 10.3390/app12146982.
[16] A. Ahmad, A. E. Gamal, and D. Saraswat, “Toward
Generalization of Deep Learning-Based Plant Disease
Identification Under Controlled and Field Conditions,”
IEEE Access, vol. 11, pp. 9042–9057, Jan. 2023, doi:
10.1109/access.2023.3240100.
[17] H. Ulutaş and V. Aslantaş, “Design of Efficient Methods
for the Detection of Tomato Leaf Disease Utilizing
Proposed Ensemble CNN Model,” Electronics, vol. 12,
no. 4, p. 827, Feb. 2023, doi:
10.3390/electronics12040827.
[18] M. Francis, K. S. M. Anbananthen, D. Chelliah, S.
Kannan, S. Subbiah, and J. Krishnan, “Smart Farm-Care
using a Deep Learning Model on Mobile Phones,”
Emerging Science Journal, vol. 7, no. 2, pp. 480–497, Feb.
2023, doi: 10.28991/esj-2023-07-02-013.
[19] G. Hu, H. Wu, Y. Zhang, and M. Wan, “Data for: A Low
Shot Learning Method for Tea Leaf’s Disease
Identification.” Mendeley Data, Jun. 27, 2019. [Online].
Available:
https://data.mendeley.com/datasets/dbjyfkn6jr/1
doi: 10.17632/dbjyfkn6jr.1
[20] V. Preet Kour and S. Arora, “PlantaeK: A leaf database
of native plants of Jammu and Kashmir.” Mendeley
Data, Oct. 29, 2019. [Online]. Available:
https://data.mendeley.com/datasets/t6j2h22jpx/2
doi: 10.17632/t6j2h22jpx.2
[21] R. A. Krohling, G. J. M. Esgario, and J. A. Ventura,
“BRACOL - A Brazilian Arabica Coffee Leaf images
dataset to identification and quantification of coffee
diseases and pests.” Mendeley Data, 2019. [Online].
Available:
https://data.mendeley.com/datasets/yy2k5y8mxg/1
doi: 10.17632/yy2k5y8mxg.1
[22] J. Parraga-Alava, K. Cusme, A. Loor, and E. Santander,
“RoCoLe: A robusta coffee leaf images dataset.”
Mendeley Data, 2019. [Online]. Available:
https://data.mendeley.com/datasets/c5yvn32dzg/2
doi: 10.17632/c5yvn32dzg.2
9. Mandal / Survey on Plant Disease Detection using Deep Learning based Frameworks
Int. J. Med. Phar. Drug Re., 7(2), 2023
Online Available at: https://www.aipublications.com/ijmpd/ 35
[23] L. G. Divyanth, A. Ahmad, and D. Saraswat, “A two-
stage deep-learning based segmentation model for crop
disease quantification based on corn field imagery,”
Smart Agricultural Technology, vol. 3, p. 100108, Aug.
2022, doi: 10.1016/j.atech.2022.100108.
[24] A. Ahmad, D. Saraswat, A. E. Gamal, and G. S. Johal,
“CD&S Dataset: Handheld Imagery Dataset Acquired
Under Field Conditions for Corn Disease Identification
and Severity Estimation,” arXiv (Cornell University),
Oct. 2021, doi: 10.48550/arxiv.2110.12084.
[25] R. N. Nandi, A. H. Palash, N. Siddique, and M. G.
Zilani, “Device-friendly Guava fruit and leaf disease
detection using deep learning,” arXiv (Cornell
University), Sep. 2022, doi: 10.48550/arxiv.2209.12557.
[26] A. Rajbongshi, S. Sazzad, R. Shakil, B. Akter, and U.
Sara, “A comprehensive guava leaves and fruits dataset
for guava disease recognition,” Data in Brief, vol. 42, p.
108174, Apr. 2022, doi: 10.1016/j.dib.2022.108174.
[27] M. Long, M. Hartley, R. J. Morris, and J. H. Brown,
“Classification of wheat diseases using deep learning
networks with field and glasshouse images,” Plant
Pathology, Nov. 2022, doi: 10.1111/ppa.13684.
[28] M. C. Long, “Wheat disease images (small dataset),”
Zenodo, Jan. 2023, doi: 10.5281/zenodo.7573133.
[29] T. Wiesner-Hanks et al., “Image set for deep learning:
field images of maize annotated with disease
symptoms,” BMC Research Notes, vol. 11, no. 1, Jul. 2018,
doi: 10.1186/s13104-018-3548-6.
[30] M. Ghosh, S. M. Obaidullah, F. Gherardini, and M.
Zdimalova, “Classification of Geometric Forms in
Mosaics Using Deep Neural Network,” Journal of
Imaging, vol. 7, no. 8, p. 149, Aug. 2021, doi:
10.3390/jimaging7080149.
[31] M. Ghosh, H. Mukherjee, S. M. Obaidullah, and K. Roy,
“STDNet: A CNN-based approach to single-/mixed-
script detection,” Innovations in Systems and Software
Engineering, Apr. 2021, doi: 10.1007/s11334-021-00395-
6.
[32] M. Ghosh, S. B. Roy, H. Mukherjee, S. M. Obaidullah,
X.-Z. Gao, and K. Roy, “Movie Title Extraction and
Script Separation Using Shallow Convolution Neural
Network,” IEEE Access, vol. 9, pp. 125184–125201, Sep.
2021, doi: 10.1109/access.2021.3110858.
[33] M. Ghosh, G. Baidya, H. Mukherjee, S. M. Obaidullah,
and K. Roy, “A Deep Learning-Based Approach to
Single/Mixed Script-Type Identification,” Lecture Notes
in Networks and Systems, pp. 121–132, Nov. 2021, doi:
10.1007/978-981-16-4287-6_9.
[34] M. Ghosh, S. Chatterjee, H. Mukherjee, S. Sen, and S. M.
Obaidullah, “Text/Non-text Scene Image Classification
Using Deep Ensemble Network,” Advances in Intelligent
Systems and Computing, pp. 561–570, Nov. 2021, doi:
10.1007/978-981-16-5207-3_47.
[35] M. Ghosh, S. B. Roy, H. Mukherjee, S. M. Obaidullah, K.
C. Santosh, and K. Roy, “Understanding movie poster:
transfer-deep learning approach for graphic-rich text
recognition,” The Visual Computer, vol. 38, no. 5, pp.
1645–1664, Mar. 2021, doi: 10.1007/s00371-021-02094-6.
[36] S. M. Obaidullah, M. Ghosh, H. Mukherjee, K. Roy, and
U. Pal, “SEN: Stack Ensemble Shallow Convolution
Neural Network for Signature-based Writer
Identification,” 2022 26th International Conference on
Pattern Recognition (ICPR), Aug. 2022, doi:
10.1109/icpr56361.2022.9956456.
[37] V. Gnanaprakash, N. Kanthimathi, and N. Saranya,
“Automatic number plate recognition using deep
learning,” IOP Conference Series, vol. 1084, no. 1, p.
012027, Mar. 2021, doi: 10.1088/1757-
899x/1084/1/012027.
[38] R. Dixit, R. Kushwah, and S. Pashine, “Handwritten
Digit Recognition using Machine and Deep Learning
Algorithms,” International Journal of Computer
Applications, vol. 176, no. 42, pp. 27–33, Jul. 2020, doi:
10.5120/ijca2020920550.
[39] I. Kamran, S. Naz, M. I. Razzak, and M. Imran,
“Handwriting dynamics assessment using deep neural
network for early identification of Parkinson’s disease,”
Future Generation Computer Systems, vol. 117, pp. 234–
244, Apr. 2021, doi: 10.1016/j.future.2020.11.020.
[40] A. Lasker, M. Ghosh, S. M. Obaidullah, C. Chakraborty,
T. Goncalves, and K. Roy, “Ensemble Stack
Architecture for Lungs Segmentation from X-ray
Images,” Springer eBooks, pp. 3–11, Jan. 2022, doi:
10.1007/978-3-031-21753-1_1.
[41] A. Lasker, M. Ghosh, S. M. Obaidullah, C. Chakraborty,
and K. Roy, “LWSNet - a novel deep-learning
architecture to segregate Covid-19 and pneumonia
from x-ray imagery,” Multimedia Tools and Applications,
Dec. 2022, doi: 10.1007/s11042-022-14247-3.
[42] A. Lasker, M. Ghosh, S. M. Obaidullah, C. Chakraborty,
and K. Roy, “A Deep Learning-based Framework for
COVID-19 Identification using Chest X-Ray Images,”
River Publishers eBooks, pp. 23–46, Feb. 2023, doi:
10.1201/9781003393658-2.
[43] L. Hao, F.-Y. Dao, Z.-X. Guan, H. Yang, Y.-W. Li, and H.
Lin, “Deep-Kcr: accurate detection of lysine
crotonylation sites using deep learning method,”
Briefings in Bioinformatics, vol. 22, no. 4, Jul. 2021, doi:
10.1093/bib/bbaa255.
[44] A. R. Khan, M. Hussain, and M. I. Malik, “Cardiac
Disorder Classification by Electrocardiogram Sensing
Using Deep Neural Network,” Complexity, vol. 2021, pp.
1–8, Mar. 2021, doi: 10.1155/2021/5512243.
[45] L. Li and S. Zhang, “Plant Disease Detection and
Classification by Deep Learning—A Review,” IEEE
Access, vol. 9, pp. 56683–56698, Apr. 2021, doi:
10.1109/access.2021.3069646.
10. Mandal / Survey on Plant Disease Detection using Deep Learning based Frameworks
Int. J. Med. Phar. Drug Re., 7(2), 2023
Online Available at: https://www.aipublications.com/ijmpd/ 36
[46] A. Ahmad, D. Saraswat, and A. E. Gamal, “A survey on
using deep learning techniques for plant disease
diagnosis and recommendations for development of
appropriate tools,” Smart Agricultural Technology, vol. 3,
p. 100083, Jun. 2022, doi: 10.1016/j.atech.2022.100083.
[47] C. F. Jackulin and S. Murugavalli, “A comprehensive
review on detection of plant disease using machine
learning and deep learning approaches,” Measurement:
Sensors, vol. 24, p. 100441, Dec. 2022, doi:
10.1016/j.measen.2022.100441.
[48] M. Loey, A. El-Sawy, and M. Afify, “Deep Learning in
Plant Diseases Detection for Agricultural Crops: A
Survey,” International Journal of Service Science,
Management, Engineering, and Technology, vol. 11, no. 2,
pp. 41–58, Apr. 2020, doi: 10.4018/ijssmet.2020040103.
[49] P. Vasavi, A. Punitha, and T. V. N. Rao, “Crop leaf
disease detection and classification using machine
learning and deep learning algorithms by visual
symptoms: a review,” International Journal of Power
Electronics and Drive Systems, vol. 12, no. 2, p. 2079, Apr.
2022, doi: 10.11591/ijece.v12i2.pp2079-2086.
[50] M. Saleem, J. Potgieter, and K. M. Arif, “Plant Disease
Detection and Classification by Deep Learning,” Plants,
vol. 8, no. 11, p. 468, Oct. 2019, doi:
10.3390/plants8110468.
[51] L. Jinzhu, L. Tan, and H. Jiang, “Review on
Convolutional Neural Network (CNN) Applied to
Plant Leaf Disease Classification,” Agriculture, vol. 11,
no. 8, p. 707, Jul. 2021, doi:
10.3390/agriculture11080707.
[52] R. Jogekar and N. Tiwari, “A Review of Deep Learning
Techniques for Identification and Diagnosis of Plant
Leaf Disease,” Smart Innovation, Systems and
Technologies, pp. 435–441, Jan. 2021, doi: 10.1007/978-
981-15-5224-3_43.
[53] J. Liu and X. Wang, “Plant diseases and pests detection
based on deep learning: a review,” Plant Methods, vol.
17, no. 1, Feb. 2021, doi: 10.1186/s13007-021-00722-9.
[54] Y. M. A. Algani, O. J. M. Caro, L. M. Robladillo-Bravo,
C. Kaur, M. S. AlAnsari, and B. K. Bala, “Leaf disease
identification and classification using optimized deep
learning,” Measurement: Sensors, vol. 25, p. 100643, Dec.
2022, doi: 10.1016/j.measen.2022.100643.
[55] L. Z. Yong, S. K. Bejo, M. Jahari, and F. M. Muharam,
“Automatic Disease Detection of Basal Stem Rot Using
Deep Learning and Hyperspectral Imaging,”
Agriculture, vol. 13, no. 1, p. 69, Dec. 2022, doi:
10.3390/agriculture13010069.
[56] W. Ma et al., “Crop Disease Detection against Complex
Background Based on Improved Atrous Spatial
Pyramid Pooling,” Electronics, vol. 12, no. 1, p. 216, Jan.
2023, doi: 10.3390/electronics12010216.
[57] J. A. Guerrero-Ibanez and A. Reyes-Muñoz,
“Monitoring Tomato Leaf Disease through
Convolutional Neural Networks,” Electronics, vol. 12,
no. 1, p. 229, Jan. 2023, doi:
10.3390/electronics12010229.
[58] A. Saeed, A. A. Abdel-Aziz, A. Mossad, M. A.
Abdelhamid, A. Y. Alkhaled, and M. Mayhoub, “Smart
Detection of Tomato Leaf Diseases Using Transfer
Learning-Based Convolutional Neural Networks,”
Agriculture, Jan. 2023, doi:
10.3390/agriculture13010139.
[59] B. M. Joshi, “Deep Learning Technology based Night-
CNN for Nightshade Crop Leaf Disease Detection,” Jan.
16, 2023.
https://www.ijisae.org/index.php/IJISAE/article/vie
w/2461
[60] H. T. Rauf, B. A. Saleem, M. I. U. Lali, M. S. Khan, M.
Sharif, and M. Abdollahi, “A citrus fruits and leaves
dataset for detection and classification of citrus diseases
through machine learning,” Data in Brief, vol. 26, p.
104340, Aug. 2019, doi: 10.1016/j.dib.2019.104340.
[61] A. N. N. Azmi, S. K. Bejo, M. Jahari, F. M. Muharam, I.
J. Yule, and N. A. Husin, “Early Detection of
Ganoderma boninense in Oil Palm Seedlings Using
Support Vector Machines,” Remote Sensing, vol. 12, no.
23, p. 3920, Nov. 2020, doi: 10.3390/rs12233920.
[62] “Tomato leaf disease detection,” Kaggle, Apr. 24, 2020.
https://www.kaggle.com/datasets/kaustubhb999/to
matoleaf