Modified Sand Cat Swarm Optimization (MSCSO) Based Feature Selection for Classification of Diseases in Tomato Leaves

Food obtained from the plants is one of the most basic requirements for the survival of humanity. However, plant diseases produce low-quality products that adversely affect the country's economy. Machine learning based detection methods for such diseases can reduce these effects. However, these methods involve plant images and usually suffer the curse of dimensionality in terms of features. Features selection improves the performance of machine learning algorithms. Feature selection method aims to find optimal number of features for a machine learning algorithm such as classification, clustering and many more. This work proposed a Modified Sand Cat Swarm Optimization (MSCSO) algorithm based feature selection to find the optimal number of features. The algorithm performs well over other standard algorithm such as GA, PSO, and GWO. The performance of different classifiers are analysed for classification of diseases in tomato leaves based on features selected by MSCSO.