Agricultural Science Digest

  • Chief EditorArvind kumar

  • Print ISSN 0253-150X

  • Online ISSN 0976-0547

  • NAAS Rating 5.52

  • SJR 0.156

Frequency :
Bi-monthly (February, April, June, August, October and December)
Indexing Services :
BIOSIS Preview, Biological Abstracts, Elsevier (Scopus and Embase), AGRICOLA, Google Scholar, CrossRef, CAB Abstracting Journals, Chemical Abstracts, Indian Science Abstracts, EBSCO Indexing Services, Index Copernicus
Agricultural Science Digest, volume 44 issue 4 (august 2024) : 591-602

Machine Learning Models for Plant Disease Prediction and Detection: A Review

Shivappa M. Metagar1, Gyanappa A. Walikar2,*
1School of Computer Science and Engineering, REVA University, Bengaluru-560 064, Karnataka, India.
2School of Electronics and Communication Engineering, REVA University, Bengaluru-560 064, Karnataka, India.
Cite article:- Metagar M. Shivappa, Walikar A. Gyanappa (2024). Machine Learning Models for Plant Disease Prediction and Detection: A Review . Agricultural Science Digest. 44(4): 591-602. doi: 10.18805/ag.D-5893.

In the agriculture field farmers are dependent on crops and once it is caused by disease, they can lose the proper yield. Plant illnesses are the common cause of low yields and reduced income for farmers. So, to overcome this, machine learning approach in the agriculture field is showing exponential improvement for interdisciplinary research, but in modern disease prediction systems, it is a different process that can takes more time to identify and understand the type of disease. Disease prediction is related to computer vision and machine learning to detect types of leaf disease on different plants. It’s a long-term system that includes a variety of real-world scenarios such as, Prediction system for vine leaf disease, pomegranate leaf disease, corn leaf disease, etc. Disease prediction is the accurate determination of the disease state of plant leaves. Accurate disease prediction is one of the key requirements in data science. Presently, machine learning based methods have improved prediction accuracy for plant leafs like grapes, pomegranates, maize. However, the disease prediction performance is still required to be improved in this challenging environment. Existing disease prediction models require high computational time and storage facilities in the agriculture field. To overcome this, we have proposed a comparative study of ML for prediction and classification of crop diseases to improve the efficiency of early prediction of crop diseases.

Modern disease prediction systems are another process that can take a long time to understand the type of disease. Disease prediction is related to computer vision and machine learning and involves detecting the type of disease in different plants. This is a long-term research problem with many real-world applications, like pomegranate leaf disease, grape leaf disease etc. Disease prediction is related to finding the accurate disease of the plant. Accurate disease prediction is one of the crucial requirements in the field of data science. The performance of existing methods is not improved for disease prediction in this challenging environment. A prediction scheme is proposed, an ML model that improves the efficiency of disease prediction. With the advancement of new advancements, the area of study of agriculture becomes more important as it is also utilized as a meal for a multitude of the population but additionally in a few of additional uses. Floraiscrucial in our lives because they furnish a source of power and help to surmount the issue of climate change. Today, flora is impacted by a few diseases, as an example those that cause harsh economic, social and ecological damage, amongst other people. Therefore, it is of great importance to accurately and rapidly detect plant diseases.
       
The authors (Amrita and Raul, 2019) have explained the visual observations are often used to determine the severity of disease in production areas. Image processing has made the greatest progress in agriculture. Diverse neural links approaches as an example back propagation and considerable component examination (PCA) have been utilized to recognize fungal diseases. Discover plant leaf diseases by enhancing the need rate in classification approaches. So far, responsible lenders can be found in this place. A linear SVM is utilized and this is a multi-class classification that categorizes the information into only two classes, but it has been unproductive and outcomes in less precise classification. Pests result in the destruction of crops or plant parts, lowering meal fabrication and guiding to meal insecurity.
       
Below equations and methods are used to find the type of the disease and accuracy percentage of disease in the plant and machine learning algorithms are used to find the type of the disease using classification algorithms and predicting the percentage of the disease attacked.
 
Evaluation models
 
Various types of measures are introduced to check the performance of vision-based and classification techniques. Accuracy, precision, recall and F1 scores are the most used checking measures for classification models. Parameters such as precession, recall and F (8), true positive (TP), false positive (FP), false negative (FN) and true negative (TN) for the proposed model the authors (Thakur et al., 2022) were calculated.
 
Accuracy
 
It’s defined as the ratio of the complete number of right predictions to the complete number of samples (T). Precision is utilized interchangeably with recognition rate (RR), hit rate (SR) or precision rate (CR) in the introduction.
                               
..........(1) 

Precision
 
Precision is defined as the percentage of accurate positives discovered over the complete number of predicted determined samples.
 
 ..........(2)

Recall
 
Recall is defined as the ratio of correctly predicted positive outcomes to actual positive outcomes.
 
..........(3)  
                                
F1-score
 
The harmonic mean of precision and recall is defined as the F1-score.
 
..........(4)  
 
Specificity
 
Specificity is defined as the ratio of the exact pre-detected negative to the actual negative.
                 
..........(5)  

mAP
 
The intended precision was defined as the place below the accuracy-retract arc(AP). The intend ordinary exactness (mAP) is the ordinary of the intend precision APi, i ∈ 1……, n Over a batch of n samples.
 
..........(6)       

This paper is structured according to the following manner. In section I, Brief introduction about plant leaf disease detection concepts, In the II section related work is outlined in detail, like supervised and unsupervised machine learning and in supervised machine learning again first section is regression algorithm, decision tree, random forest, classification algorithms like KNN, Naive Bayas, SVM and regression algorithm, in section III brief summary of all the machine learning algorithms, In section IV final conclusion is set.

Types of Machine Learning and its algorithms are used to classify and detect plant disease.
       
In Fig 1, the various types of supervised and unsupervised machine learning algorithms are listed that are used to find the different types of diseases and also classifying various types of the disease in plant.
 

Fig 1: Main Structure of the machine learning types and its algorithms.


 
• Traditional methods are the manual checking methods and takes more time and the plant disease detection made based on symptoms of the plant.
• The use of ML methods such as SVM, K-NN and Naive Bayas is used to separate diseased and uninfected leaves.
• Currently, machine learning-based methods have improved the accuracy of predictions for crops such as grapes, pomegranates, corn; however, disease prediction performance still needs to be improved in a harsh environment.
       
In the below line have explained about the different machine learning algorithms and uses of algorithms for implementation of various tasks in the agriculture field for identifying the various types of disease and percentage of the disease attacked to the plant. 
 
Supervised machine learning
 
Well trained machines are used for supervised machine learning “labeled” training dataset based on this training dataset output will be predicted by machines. Labeled data means that some input data has been labeled with the correct output in the trained dataset. In supervised machine learning, training data is fed to a machine that functions as a supervisor that can teach the machine to correctly predict output given a given set of input data. It applies to the same concepts that students learn under the supervision of their homeroom teachers. It’s a procedure that feeds the accurate input along with the result information to the artificial intelligence algorithm. The goal of a supervised acquiring procedure is to locate a mapping operate that maps the input factor (X) to the product factor (Y).
 
Regression
 
The equation used for linear regression can be written as:
 
Y = Mx+C  OR  y=bo+b*x+e
 
Where,
M and C = Gradient and constant values (to be determined) defining the straight line.
bo = Intecept,
b = Regression weight or coefficient associated with the predictor variable x.
e = Residual error.
       
It’s a technique for locating the relationship between autonomous factors or characteristics and a measured factor or result and it’s utilized as a way for predictive modeling in device learning, whereat a procedure is utilized to forecast continual result.
       
Investigating machine learning regression techniques for leaf rust detection using ultrasound measurement in this paper the authors (Davoud et al., 2016) have discussed the composite impact of symptoms and disease stages on the main characteristics of the plant leading to limiting the severity of the disease detected by different techniques. In addition, ML techniques are used to detect plant diseases; the influence of these symptoms on their performance is not taken into account. Spectra of infected and uninfected leaves under various disease symptoms were measured with a non-imaging spectrophotometer in the electrical region of 350-2500 nm.
       
Adhao et al., (2017) have explained about the cotton is the most important cash crops in India and its influence on the economy. Cotton production is decreasing every year due to various disease attacks. Usually, crop diseases are caused by harmful insects and pathogens, reducing yields on a large scale if not promptly prevented. This work presents a system for the detection and control of cotton leaf disease.
 
Logistic regression
 
Calculating the probability, we used logistic regression to find the binary outcome: to check if something happened or not can be shown in Yes/No or Pass/Fail. Unbiased variables are analyzed to decide on a binary outcome, with consequences falling into one of two categories. The independent variables can be expressions or numbers, but the dependent variable is always an expression. Write like:
          
  
 
Calculating probability is X given independent variable, the Y dependent variable.
       
The convolutional neural network using optimized proposed logistic decision regression (Priyanka et al., 2022), have discussed the agricultural nature is very important to cultivate crops with the aid of machine learning and artificial intelligence. In this work, we will detect leaf diseases by implementing image classification and analysis algorithms. Conventional manual identification of medicinal plants is a quick process that requires the help of plant identification specialists to find plant diseases.
 
Decision tree
 
In machine learning, when we know the cost of each probability and the outcome it will produce, it can be calculated using the following formula:
 
Expected Value (EV) = (First possible outcome × Probability of outcome) + (Second possible outcome × Probability of outcome) - Cost
 
Steps used for making decision tree
 
Step-I: Take a set of rows list (dataset) which can get to make for making decision tree.
Step-II: Dataset calculation for uncertainty or impurity in dataset or checking the mixed dataset etc.
Step-III: List of all questions generation which need to be asked to that node.
       
It is perfect for classroom problems because it can schedule instructions to a specific level. It works like a diagram, isolating elements of information into two similar categories, from ‘stem’ to ‘branch’ to ‘leaf’ where the final categories look more similar. It creates categories within categories, in the spirit of natural classification with limited human supervision (Rajesh et al., 2020) have explained the detection and classification of foliar diseases according to the decision tree in, agricultural production depends on the economy.
       
In Machine Learning domain the authors (Nalin et al., 2023) have discussed the identification of plant disease by using different types of algorithms and they have been started for finding excellent result for data by using algorithm, this is an intriguing procedure in daily life application. The need for efficient algorithms is met when implementing these algorithms, the main objective of which is to focus on the prediction of plant diseases in the agricultural field in practice by providing resources in agricultural and business sectors. This bulletin’s conceptual engineering inculcates tracking each leaf inside a tree through a machine learning model.
       
In Fig 2, the authors explained the gist that we use the results to provide, digest and approve a version used to predict fateful events and suggest possible effects. Capabilities while building predictive modeling methods. Regression and neural networks are two of the most well-known and widely used predictive modeling techniques. In a word, several types of Bayesian assessment, selection wood and statistical profile processing are complementary techniques. Each of the many prediction models has an important function to play. As we all understand, a metamodel is a model that can be used many times and is created by teaching an algorithm to use the information that has been collected, processed and saved for later use in the future evaluation of the final result.
 

Fig 2: Domain based disease prediction and resource reference (Nalin et al., 2023).


 
Random forest algorithm
 
Random forest algorithm is a popular supervised machine learning technique; it is used to solve both classification and regression problems in machine learning.
 
Random forests converge
 
Given an ensemble of classifiers h1(x), h2(x) . . . hK (x) and with the training set drawn at. random from the distribution of the random vector Y, X, outline the margin characteristic as explained the in (Leo Breiman Statistics, 2001).
 
 mg [(X, Y) = avkI(hk (X) = Y ) - max j = Y avk I(hk (X) = j)].
       
In which I(•) is the indicator feature. The margin measures the volume to which the common wide variety of votes at X, Y for the proper magnificence exceeds the average vote for another elegance.
       
The extra self-belief within the category. The generalization errors are given via.
 
PE* = PX, Y [mg (X, Y ) <zero]
 
Where in the subscripts X, Y indicate that the possibility is over the X, Y space.
       
A hybrid approach to detect and classify apple diseases using a random forest classifier in (Hernández et al., 2020). Today, foreign trade has increased significantly in some countries. Range of overseas fruit products from trading countries, e.g., oranges, apples, etc. Manual evidence to distinguish infected fruit is extremely tedious. The authors have (Meghana et al., 2019) discussed the diagnosis of tomato plant diseases using the Random Forest algorithm, Random Decision Forest is a synthetic training method for regression, classification, etc. The random forest consists of a number of decision trees. The random forest summarizes the results of the entire decision tree at the time of training and class generation in the case of classification problems and average prediction in the case of regression model. Random decision trees overcome the problem of overfitting to their training set, which is the main problem of decision tree algorithms. In this work, they were divided into two phases. In the first stage, feature extraction is performed on all images and stored in the feature table.
       
In Fig 3, random forest decision tree algorithm are used to diagnose rice leaf diseases and includes several procedures like first obtaining an image of rice leaves; preprocess the images, extract capabilities from these images and classify the images by disease name and the main dataset is divided into many units. Two thirds of the records in the dataset, i.e., a total of 352 images (276 captcha and the latest image added from) are available for training in the above concepts the authors (Sristy et al., 2012).
 

Fig 3: Random forest decision tree architecture.


 
Classification algorithms
 
Class algorithms come under supervised device getting to know approach that is used to perceive the category of latest observations primarily based on the training dataset. In class set of rules an application learns the given dataset or observations after which classifies new remark into a number of groups.
 
K-nearest neighbor (KNN)
 
K-nearest Neighbor (k-NN) is a sample reputation set of rules that utilizes the education dataset to find k closest relatives in coming cases. Whereas k-NN is utilized in the layer, you work out to place the records in its closest neighbor kind. If OK = 1, then he could be placed in the lesson closest to 1. K is categorized by one vote as said by the number of his acquaintances.
       
In the Table 1, we have summarize the various KNN algorithms for finding and comparing the result of the different papers and in (Eftekhar et al., 2019) have explained the Color and Texture Based Approach for the Detection and Classification of Plant Leaf Disease Using KNN Classifier, Modern organic farming is gaining popularity in the agriculture of many developing countries. This work proposed a way to detect and classify leaf diseases using nearest neighbor classifier (KNN).
 

Table 1: Work summary of KNN technique.


 
Naive bayes
 
Naive Bayes calculates the probability that a record point belongs to a particular category. Text analysis can be used to classify words and terms that belong to predefined tags (categories). The probability that X occurs if Y is true is equal to the probability that Y occurs if X is true multiplied by the probability that X is true divided by the probability that Y is true. Apply the formula for the probability of an event.
 
 
The authors have explained papaya plant disease (Wahyuni et_al2020). Detection Using Fuzzy Naive Bayes Classifier Algorithm Papaya is one of the common fruits grown in Indonesia. With weather conditions infested with pests and diseases, a professional papaya disease detection system was developed. Expertise is reflected in the system, allowing farmers to determine status without an expert.
 
Support vector machine (SVM)
 
SVM uses algorithms that shape and classify data into levels of polarization to go beyond X/Y prediction to some extent. For simple image rationalization, we use tags: red and blue, the same two actual functions: X and Y and train a classifier to output X/Y coordinates to pink or blue. Rajleen and Kaur (2015) in Enhancement of SVM classification to improve plant disease detection, have proposed work in leaf imaging or even leaf imaging.
 
SVM errors = Margin error + classification error.
 
Here the higher the margin, the lower could-be margin errors and vice versa.
       
In this post, we run an SVM with records. One is school grades and train grades. First the original image is captured and then miles are used for processing. The image’s black and legacy pixels are then segmented and the color and saturation portions of the image are also separated. Third, detect disease and sickness from photos and segment healthy parts from them. This study will tell you the percentage of the area where the disease occurs and may even give you the name of the disease. In Vagisha et al., (2020), the authors discussed leaf comparisons of different plants using SVM.
       
In the Table 2, have summarize the various SVM algorithm for finding and comparing the result, accuracy of the different author’s paper. Machine learning techniques have been used by (Majji et al., 2021) to find plant diseases and traditionally, crop diseases are common causes of low yields and reduced yields. Accurate identification of plant diseases can help find cures as soon as possible to control losses. These authors attempted to develop a new method using ML techniques to predict plant diseases and compare different classification techniques; a comparison is given  in Table 3.
 

Table 2: Summary of work done using SVM technique.


 

Table 3: Comparison of classification techniques with strengths and weaknesses.


       
The authors (Ramesh et al., 2020) have explained machine learning methods for the detection and classification of foliar diseases, a detailed review of the benchmarks of various advanced ML algorithms for identification. Identification and classification of foliar diseases.
 
Comparison of machine learning techniques
 
Strengths and weaknesses of various machine learning techniques are discussed in Table 3 and 4.
 

Table 4: Machine learning algorithms comparison.

 
       
In the Table 5, we have explained the comparison between the different machine learning algorithms ML approaches and what they have designed the model, highlight of that model and gap in the research. Agriculture provides food for everyone, even in times of rapid population growth. Unfortunately, however, the disease occurs in the main stages of crops (Sunil S. Harakannanavar et al., 2022). The notion behind this document is to enlighten farmers on state-of-the-art to decrease leaf diseases in crops.
 

Table 5: Summary of different machine learning algorithms.

In this paper, with a broad instruction that covers detail concepts about the plant disease and summary of the plant disease classification and type of the plant disease, to suggest enhancement in current classification methods for plant disease detection using machine learning and that is verified by classifier procedure and an extra goal was to examine on distinct leaf diseases that are not yet been studied. This can motivate researchers to find new things and explore the use of numerous environmental factors which result in plant diseases which end up in giant production losses. It is a time-eating and blunder-prone system and it is able to be an unreliable method of identifying and stopping unfolding of plant diseases. Adopting superior technology such as Machine Learning (ML) can help to conquer those demanding situations by enabling early identification of plant diseases. A few diseases predictive studies have been conducted investigating recent advances in the use of ML techniques to identify diseases. The following are some directions to further improve the ability to detect plant diseases and increase work efficiency. In the future, we may do this work on more datasets to improve results and increase accuracy. This section outlines some of the research factors that need to be considered in future studies, followed by detailed conclusions.
Authors acknowledge the support from REVA University for the facilities provided to write this article and thanks reviewers for their valuable suggestions. 
The authors certify that they have no affiliations with or involvement in any organization or entity with any financial interest (such as honoraria; educational grants; participation in speakers’ bureaus; membership, employment, consultancies, stock ownership, or other equity interest and expert testimony or patent-licensing arrangements), or non-financial interest (such as personal or professional relationships, affiliations, knowledge or beliefs) in the subject matter or materials discussed in this manuscript.

  1. Abdulridha, J., Ehsani, R., Abd-Elrahman, A., Ampatzidis, Y. (2019). A remote sensing technique for detecting laurel wilt disease  in avocado in presence of other biotic and abiotic stresses.  Computers and Electronics in Agriculture. 156: 549-557. https://doi.org/10.1016/j.compag.2018.12.018.

  2. Adhao A.S., Pawar, V.R. (2017). Machine learning regression technique for cotton leaf disease detection and controlling using IoT. International Conference on Electronics, Communication and Aerospace Technology. ICECA 2017, 978-1-5090-5686-6/17/$31.00 ©2017 IEEE.

  3. Ahmad, N., Singh, S. (2021). Comparative Study of Disease Detection in Plants using Machine Learning and Deep Learning. Second International Conference on Secure Cyber Computing and Communication (ICSCCC), © IEEE.

  4. Amrita, S., Raul, T.N. (2019). Plant Leaf Disease Detection using Machine Learning” 10th ICCCNT 2019, IIT - Kanpur, Kanpur, India.

  5. Aruraj, A., Alex, A., Subathra, M.S.P., Sairamya, N.J., George, S.T., Eward, S.E.V. (2019). Detection and Classification of Diseases of Banana Plant Using Local Binary Pattern and Support Vector Machine, 2019 International Conference on Signal Processing and Communication (ICSPC -2019), March. 29-30, 2019, Coimbatore, India. 978-1-7281- 1849-9 ©2019 IEEE.

  6. Asta, L., Gomathi, M.V. (2021). Automatic Prediction of Plant Leaf Diseases Using Deep Learning Models: A Review. 5th International Conference on Electrical, Electronics, Communication, Computer Technologies and Optimization  Techniques (ICEECCOT).

  7. Bhimte, N.R. and Thool, V.R. (2018). Diseases Detection of Cotton Leaf Spot Using Image Processing and SVM Classifier. Second International Conference on Intelligent Computing and Control Systems (ICICCS), Madurai, India, pp. 340- 344. DOI: 10.1109/ICCONS.2018.8662906.

  8. Chandraprabha, M.T., Singh, A.S. (2021). Prediction of Crop Diseases to Improve Crop Yield Using Ensemble Methods. 2021 3rd International Conference on Advances in Computing, Communication Control and Networking (ICAC3N) | 978- 1- 6654- 3811- 7/ 21/$ 31.00 2021 IEEE | DOI: 10.1109/ ICAC3N53548.2021.9725472.

  9. Davoud, A., Aghighi, H., Matkan, A.A., Mobasheri, M.R. and Rad, A.M. (2016). An investigation into machine learning regression techniques for the leaf rust disease detection using hyperspectral measurement. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing. 9(9): 4344-4351, 2016 1939-1404 IEEE. 

  10. Eftekhar, H., Hossain, M.F. and Mohammad and Rahaman, A. (2019). A Color and Texture Based Approach for the Detection and Classification of Plant Leaf Disease using KNN Classifier. International Conference on Electrical, Computer and Communication Engineering (ECCE), 7-9 February 2019. 978-1-5386-9111-3/19/$31.00 ©2019 IEEE.

  11. Farhana, T.,    Khatun, P.N.,  Islam, S.M.M. (2021). Visual features based paddy leaf disease recognition, its severity detection and remedy prediction using k-means clustering and adaboost. Journal of Image Processing and Pattern Recognition Progress. 7(3): 41-52. 

  12. Gawande, A.R., Sherekar, S.S. (2021). A brief study on the prediction of crop disease using machine learning approaches. 978- 1-6654-2040-2/21/$31.00 © IEEE.

  13. Hareem, K., Abdullah, I., Nasrullah, A. (2021). Plant Disease Identification and Classification using Convolutional Neural Network and SVM. 2021 International Conference on Frontiers of Information Technology (FIT) | 978-1-6654-0830-1/21/ $31.00 ©IEEE |.

  14. Hernández, S., López, J.L. (2020). Uncertainty quantification for plant disease detection using Bayesian deep learning. Elsevier Science Publishers B.V. Netherlands available on https://doi.org/10.1016/j.asoc.2020.1065971568- 4946/© 2020 Elsevier.

  15. Hossain, E., Hossain, M.F. and Rahaman, M.A. (2019). A Color and Texture Based Approach for the Detection and Classification of Plant Leaf Disease Using KNN Classifier. 2019 International Conference on Electrical, Computer and Communication Engineering (ECCE), Cox’sBazar, Bangladesh, 2019, pp. 1-6. DOI: 10.1109/ECACE.2019. 8679247.

  16. Hossain, S., Mou, R.M., Hasan, M.M., Chakraborty, S. and Razzak, M.A. (2018). Recognition and detection of tea leaf’s diseases using support vector machine. 2018 IEEE 14th International Colloquium on Signal Processing and its Applications (CSPA), Batu Feringghi, 2018, pp. 150-154. DOI: 10.1109/CSPA.2018.8368703.

  17. Kumar V., Jat, H.S., Sharma, P.C., Singh, B., Gathala, M.K., Malik, R.K. et al. (2018). Can productivity and profitability be enhanced in intensively managed cereal systems while reducing the environmental footprint of production? Assessing sustainable intensification options in the breadbasket of India. Agriculture, Ecosystems and Environment. 252 (2018): 132-147.

  18. Lakshmanarao, A., Supriya, N., Arulmurugan, A. (2022). Plant Disease Prediction using Transfer Learning Techniques. 2022 Second International Conference on Advances in Electrical, Computing, Communication and Sustainable Technologies (ICAECT) | 978-1-6654-1120-2/22/$31.00 ©2022 IEEE | DOI: 10.1109/ICAECT54875.2022.9807956.

  19. Leo Breiman Statistics Department, (2001). Random forests are a combination of tree predictors such that each tree depends, University of California, Berkeley, CA 94720, Machine Learning, 45, 5-32, 2001 c 2001 Kluwer Academic Publishers. 

  20. Majji, V., Kumaravelan, A.G. (2021). A Review of Machine Learning Approaches in Plant Leaf Disease Detection and Classification. Third International Conference on Intelligent Communication Technologies and Virtual Mobile Networks (ICICV 2021). IEEE Xplore Part Number: CFP21ONG-ART; 978-0-7381- 1183-4.

  21. Meghana, G. and Veena, M. (2019). Diagnosis of Tomato Plant Diseases using Random Forest. 2019 Global Conference for Advancement in Technology (GCAT) Bangalore, India. Oct 18-20, 2019, 978-1-7281-3694-3/19/$31.00 ©2019 IEEE.

  22. Nalin, K.Y., Maddali, K., Jayapandian, N. (2023). Machine Learning based Plant Disease Identification by using Hybrid Naïve Bayes with Decision Tree Algorithm. 5th International Conference on Smart Systems and Inventive Technology (ICSSIT 2023) 978-1-6654-7467-2/23/$31.00 ©2023 IEEE.

  23. Padol, P.B.  and Yadav, A.A. (2016). SVM classifier based grape leaf disease detection. Conference on Advances in Signal Processing (CASP). pp. 175-179. DOI: 10.1109/CASP. 2016.7746160.

  24. Parikh, A., Raval, M.S., Parmar, C. and Chaudhary, S. (2016). Disease Detection and Severity Estimation in Cotton Plant from Unconstrained Images. 2016 IEEE International Conference on Data Science and Advanced Analytics (DSAA), Montreal, QC, 2016, pp. 594-601. DOI: 10.1109/ DSAA.2016.81.

  25. Pawara, S., Nawale, D., Patil, K., Mahajan, R. (2018). Early Detection of Pomegranate Disease Using Machine Learning and Internet of Things. 3rd International Conference for Convergence in Technology (I2CT), India.

  26. Priyanka, C., Gupta, S.S., Patnaik, D.M.S.P.K., Munagala, N.V.L.M.K., Sivasangari, A. and Tannad, H. (2022). Efficient plant disease prediction based on convolutional neural network using optimized proposed logistic decision regression. 2nd International Conference on Technological Advancements in Computational Sciences (ICTACS). 978-1-6654-7657- 7/22/$31.00 ©2022 IEEE.

  27. Radwan, Q., Amro, M., Zaghal, R., Sawafteh, M. (2021). Machine Learning Techniques for Tomato Plant Diseases Clustering, Prediction and Classification. International Conference on Promising Electronic Technologies (ICPET) ©IEEE.

  28. Raj, K., Shukla, N., Princee, (2022). Plant Disease Detection and Crop Recommendation Using CNN and Machine Learning. 2022 International Mobile and Embedded Technology Conference (MECON) 978-1-6654-2020-4/22/$31.00 © IEEE.

  29. Rajesh, B., Vardhan, M.V.S., Sujihelen, L. (2020). Leaf Disease Detection and Classification by Decision Tree Proceedings of the Fourth International Conference on Trends in Electronics and Informatics (ICOEI 2020) IEEE Xplore Part Number: CFP20J32-ART. ISBN: 978-1-7281-5518-0.

  30. Rajleen, K. and Kang, S.S. (2015). An Enhancement in Classifier Support Vector Machine to Improve Plant Disease Detection.  2015 IEEE 3rd International Conference on MOOCs, Innovation and Technology in Education (MITE). 978-1- 4673-6747-9/15/$31.00 c 2015 IEEE.

  31. Ramcharan, A., Baranowski, K., McCloskey, P., Ahmed, B., Legg, J., Hughes, D.P. (2017). Deep learning for image-based cassava disease detection. Frontiers in Plant Science. 8: 1852. https://doi.org/10.3389/fpls.2017.01852.

  32. Ramesh, A., Schbert, R.D., Greenfield, A.L., Wilson, M.R. (2020). A pathogenic and clonally expanded B cell transcriptome in active multiple sclerosis, Edited by Lawrence Steinman, Stanford University School of Medicine, Stanford, CA and Approved August 3, 2020.

  33. Ruthvik, K. and Kommisetti, (2021). Prediction of Maize Leaf Disease Detection to improve Crop Yield using Machine Learning based Models. 2021 4th International Conference on Recent Trends in Computer Science and Technology, (ICRTCST). DOI: 10.1109/ICRTCST54752.2022.9782023.

  34. Singh, K., Kumar, S. and Kaur, P. (2019). Support vector machine classifier-based detection of fungal rust disease in pea plant (Pisam sativam). International Journal of Information Technology. 11: 485-492 (2019).https://doi.org/10.1007/s41870-018-0134-z.

  35. Sristy, S., Ahsan, S.M.M. (2012). Rice disease detection using intensity moments and random forest. International Conference on Information and Communication Technology or Sustainable Development (ICICT4SD). 27-28 February,  Dhaka, 978-1-6654-1460-9/21/$31.00 ©IEEE.

  36. Sunil, S.H., Rudagi, J.M. (2022). Plant leaf disease detection using computer vision and machine learning algorithms. Global Transitions Proceedings, Journal Homepage. 3(11): https:// doi.org/10.1016/j.gltp.2022.03.016. 

  37. Suresha, M., Shreekanth, K.N. and Thirumalesh, B.V. (2017). Recognition of diseases in paddy leaves using knn classifier. 2017 2nd International Conference for Convergence in Technology (I2CT), Mumbai, 2017, pp. 663-666. DOI: 10.1109/I2CT.2017.8226213.

  38. Thakur, P.S., Khanna, P., Sheorey, T., Ojha, A. (2022). Trends in vision-based machine learning techniques for plant disease identification: A systematic review. https://doi.org/10.1016/j.eswa.2022.118117. Expert Systems with Applications 208 (2022) 118117Available online 11 July 2022 0957-4174/© 2022 / Elsevier. 

  39. Vagisha, S., Verma, A., Goel, N. (2020). Classification techniques for plant disease detection. Retrieval Number: F99020 38620/2020©BEIESPDOI:10.35940/ijrte.F9902.038620.

  40. Wahyuni, E.S., Kurniawati, Y.E. and Santosa, P.I. (2020). Papaya Disease Detection using Fuzzy Naïve Bayes Classifier 2020 3rd International Seminar on Research of Information Technology and Intelligent Systems (ISRITI) | 978-1- 7281-8406-7/20/$31.00 ©IEEE | DOI: 10.1109/ISRITI5 1436.2020.9315497.

Editorial Board

View all (0)