Classification of healthy and diabetic mellitus individuals by extracted textural features from left plantar thermograms and classifying using svm and nb classifiers

The aim of the study is to classify the healthy and diabetic mellitus individuals by extracting textural features from left plantar thermograms and classifying using support vector machine (SVM) and Naive Bayes (NB) classifiers. Materials and Methods: Images are collected from IEEE dataport, machine learning repository for healthy (n=21) and abnormal (n=21) to our study with alpha value as 0.05, 95% as CI, power as 80% and enrollment ratio as 1. The classification of diseased and healthy subjects was performed using WEKA, a data mining tool. The statistical analysis was performed using IBM SPSS software. Results: The performance of the classifiers were compared and found that the NB classifier has achieved 90.47% as classification accuracy rate than the SVM classifier. The independent Tsample test reveals that there is a significant difference between the groups (p