Intelligent Decision Support for Real Time Health Care Monitoring System

In the health care monitoring, data mining is mainly used for classification and predicting the diseases. Various data mining techniques are available for classification and predicting diseases. This paper analyzes and evaluates various classification techniques for decision support system and for assisting an intelligent health monitoring system. The aim of this paper is to investigate the experimental results of the performance of different classification techniques for classifying the data from different wearable sensors used for monitoring different diseases. The Base Classifiers Proposed used in this work are IBk, Attribute Selected Classifier, Bagging, PART, J48, LMT, Random Forest and the Random Tree algorithm. Experiments are conducted on wearable sensors vital signs data set, which was simulated using a hospital environment. The main focus was to reduce the dimensionality of the attributes and perform different comparative analysis and evaluation using various evaluation methods like Error Metrics, ROC curves, Confusion Matrix, Sensitivity and Specificity. Experimental results reveal that the proposed framework is very efficient and can achieve high accuracy.