Prediction of Black Sigatoka Disease in Banana Plants By Data Mining Classification Techniques using Scikit for Python

Abstract

Agriculture has been evolving since humans started cultivating plants for food consumption. As the agriculture field evolves, the disease control measures too have evolved. Now in this modern era, disease in plants can be easily identified using computers. Data mining is the process of obtaining the useful information from the data. Before the electronic era, diseases in plants are identified just by seeing the symptoms of the plants. Similarly, we can identify the diseases in plants using data mining by supplying the disease symptoms data and classify them accordingly. The purpose of this paper is focusing on the prediction of the diseases from images of black sigatoka disease and uses the following methods: MultilayerPerceptrons, SVM,KNeighborsClassifier,K-NeighborsRegressor, Gaussian Process Regressor, Gaussian Process Classifier, GaussianNB, Decision Tree Classifier, Decision Tree Regressor, linear models such as Linear Regression, RidgeCV, Lasso, ElasticNet, Logistic RegressionCV, SGD Classifier, Perceptron and Passive Aggressive Classifier and ensemble models of the above classifiers. The results are compared, and multilayer perceptron model is seen to give better results for individual classifiers and ensemble of week classifiers gives better results when ensembled. In future, a new hybrid algorithm would be used from the above algorithms for attaining better accuracy. The scikit is a library used for classification, clustering, regression, dimensionality reduction,model selection and preprocessing. Our paper discusses various classifiers used in scikit-learn library for Python and their ensembling is done. This can be applied to all the classification tasks. Classification is done for classifying the black sigatoka disease in banana from healthy leaves.This disease is the most vulnerable one among banana plants.