Selection of classification models from repository of model for water quality dataset

Abstract

This paper proposes a new technique, Model Selection Technique (MST) for selection andranking of models from the repository of models by combining three performance measures (Acc, TPR and TNR). This technique provides weightage to each performance measure to find the most suitable model from the repository of models. A number of classification models have been generated to classify water quality using the most significant features and classifiers such as J48, JRip and BayesNet. To validate this technique proposed, the water quality dataset of Kinta River was used in this research. The results demonstrate that the Function classifier is the optimal model with the most outstanding accuracy of 97.02%, TPR = 0.96 and TNR = 0.98. In conclusion, MST is able to find the most relevant model from the repository of models by using weights in classifying the water quality dataset.