Grasshopper Optimization Algorithm based Feature Selection with Twin Support Vector Machine Classifier for Coronary Artery Heart Disease Prediction
Data mining research extends its wings in almost all domains that include healthcare applications. ML algorithms took an important role in classification task and optimization algorithms are propounding in almost all tasks in knowledge discovery in data. This part of research work aims in employing grasshopper optimization algorithm on feature selection and twin SVM classifier is used for classification. This grasshopper optimization algorithm with twin SVM classifier is tested for performance over two dataset for prediction of CAHD. Performance metrics sensitivity, specificity, accuracy and elapsed time are considered formeasuring the effectiveness of the classifier. From the results it is inferred that the GOA-TSVM outperforms other chosen machine learning classifier.