Mandavi, Prasannjit, Nilotpal Mrinal, Kalyan Chatterjee and S. Dasgupta, Bengal College of Engineering & Technology, India

Heart is one of the vital parts of human body, which maintains life line. In this paper, an efficient composite method has been developed for data compression of ECG signals. ECG waveforms reflect most of the heart parameters closely related to the mechanical pumping of the heart and can therefore, be used to infer cardiac health. After carrying out detailed studies of different data compression algorithms, we used back propagation algorithm to analyse the artificial neural networks. Twelve significant features are extracted from an echocardiogram (ECG). The features of samples are used as input to the neural network. Finally the samples which are used in the database are trained and tested using the Back Propagation Algorithm. The efficiency is observed to be 99.5%. Dual three-layer neural networks with only a few units in the hidden layer are used. It is further observed that input signals are same as supervised signals used in the networks. Back-propagation is used for the learning process.

Back propagation, Bipolar coding, Data compression, Echocardiograph Data Set, Neural networks, Linear scaling.