Dimensionality reduction based on the classifier models: Performance Issues in the prediction of Lung cancer

Dimensionality reduction is an essential feature to reduce the complexity of the computations in the large data set environment. When handling large quantum of medical data set, as in the case like, Lung cancer prediction, based on symptoms and Risk factors, number of attributes/ dimensions pose a major challenge. Here in this study an attempt is made to compare the performance of the attribute selection models prior and after applying the classifier models. A total of 16 classifier models are chosen, which are based on statistical, rule based, logic based and artificial Neural network approaches. Feature set selection and ranking of attributes are done based on individual models. Confusion matrix of the models before and after dimensionality reduction is computed. Based on the confusion matrix result the models are compared and based on the performance optimal model is chosen. It is found that Multi-layer perceptron based artificial neural network model gives better performance compared to other approaches.