Data stream mining for health care application

ECG is an electric signal which is generated from human heart. It is used for investigate some of abnormal heart function.Data stream mining plays a key role to analyze the continuous data. The effective and efficient analysis of this data in different forms becomes a challenging task. Developments in sensors device, miniaturization of low power micro- electronics device, and wireless networks devices are becoming a significant opportunity for good quality of health care services. Signals like ECG, EEG, and BP etc. can be monitor through wireless sensor networks and analyzed with the help of data mining techniques. These real-time signals are continuous in nature and abruptly changing hence there is a need to apply an efficient data stream mining techniques for taking intelligent health care decisions. The high speed and large amount of data set in data stream, the traditional classifier and classification technologies are no more time applicable. The important criteria are to solve the ‘concept drift’ in data streams mining. Data Stream Mining (DSM) process performs data analysis and may uncover important data patterns, knowledge bases data, and scientific and medical research data. To extract the shape of ECG, the discrete wavelet transform is used after filter was applied to remove noise from ECG signal. After that detect the PQRST wave and used the ensemble classification technique to classify the ECG signal.