A Hybrid Feature Extraction and Feature Selection Mechanism to Predict Disease in Plant Leaves

Abstract

The health of the plants is vital to meet the demands of the food cycle. As the symptoms of disease or infection are most commonly seen in plant leaves, selecting features from plant leaves that are highly impacting plant health is crucial. Plant health is a global imperative for food security and ecological balance and must be treated as the top priority. Feature Extraction (FE) and Feature Selection (FS) are significant in Deep Learning (DL) and Machine Learning (ML) models, which are used for classification and prediction. Xception-based feature extraction and random forest classification yield accurate predictions, offering interpretability and adaptability across diverse plant diseases and datasets, benefiting agriculture. In this article, FE is performed using an Xception pre-trained model and the extracted features are sent for FS. Further, six FS methods such as ANOVA, chi-square, Sequential Forward Selection (SFS), Sequential Backward Selection (SBS), Lasso and Ridge, have been deployed and compared with machine learning algorithms such as Logistic Regression (LR), K Nearest Neighbours (KNN), Decision-Trees (DT), Random Forest (RF), Support Vector Machine (SVM), Naive-Bayes (NB) for classification. The article also proposes an Ensemble Feature Selection (EFS)-RF method, which combines feature sets from six feature selection algorithms and classifies based on majority voting. The methodology section details criteria for selecting FE and FS methods, utilizing an ensemble to maximize their respective benefits. The paper contributes to agriculture by employing a hybrid approach, integrating DL (Xception-based FE) and ML (RF-based Classification), utilizing an ensemble of FS methods to identify and assign higher weightage to features prevalent across subsets. The proposed method has outperformed other algorithms for both datasets with 98 % accuracy and 0.02 Mean Squared Error (MSE) for dataset I and 98.125 % accuracy and 0.01875 MSE for dataset II.