Medical Data Clustering and Classification Using TLBO and Machine Learning Algorithms

This study aims to empirically analyze teaching-learning-based optimization (TLBO) and machine learning algorithms using k-means fuzzy c-means (FCM) for their individual performance evaluation in terms of clustering classification. In the first phase, (k-means FCM) were employed independently accuracy was evaluated different computational measures. During second non-clustered data obtained from phase preprocessed with TLBO. TLBO performed (TLBO-KM) FCM (TLBO-FCM) (TLBO-KM/FCM) algorithms. The objective function determined by considering both minimization maximization criteria. Non-clustered further utilized fed as input threshold optimization. Five benchmark datasets considered University California, Irvine (UCI) Machine Learning Repository comparative experimentation. These are breast cancer Wisconsin (BCW), Pima Indians Diabetes, Heart-Statlog, Hepatitis, Cleveland Heart Disease datasets. combined average collectively is approximately 99.4% case TLBO-KM 98.6% TLBO-FCM. approach also capable finding dominating attributes. findings indicate that TLBO-KM/FCM, measures, perform well on where FCM, if independently, fail provide significant results. Evaluating feature sets, TLBO-KM/FCM SVM(GS) clearly outperformed all other classifiers sensitivity, specificity accuracy. attained highest sensitivity (98.7%), (98.4%) (99.4%) 10-fold cross validation test data.