TY - GEN
T1 - Design of an ECG signal peak recognition system using multiple HMLP network for diagnosis of heart disorder
AU - Alhady, S. S.N.
AU - Arshad, Mohd Rizal
PY - 2009
Y1 - 2009
N2 - ECG is a heart status analysis system which is cheap, effective, easy for implementation and safe to be used. Cardiologist will interpret ECG signals whilst monitoring changes of ECG signals in order to determine the status of the heart. In this research, suitable threshold for preprocessing of the signals was determined in two stages. The preprocessing stage has successfully eliminated 92.71% of the noisy peaks from the ECG signals. MHMLP network has been proposed in this research, to increase the performance in identifying peaks (P, Q, R, S and T) of the ECG signals. Comparisons with other available neural networks for peak recognition have also been conducted. By utilising the features selection approach, the optimum peaks identification performance of the neural networks system has been determined. During implementation, the MSE (dB) of MHMLP network to identify peaks of ECG signals has been recorded at -27.92dB. As a whole, MHMLP network has achieved recognition performance of 83.78% and 89% during testing and training phase respectively.
AB - ECG is a heart status analysis system which is cheap, effective, easy for implementation and safe to be used. Cardiologist will interpret ECG signals whilst monitoring changes of ECG signals in order to determine the status of the heart. In this research, suitable threshold for preprocessing of the signals was determined in two stages. The preprocessing stage has successfully eliminated 92.71% of the noisy peaks from the ECG signals. MHMLP network has been proposed in this research, to increase the performance in identifying peaks (P, Q, R, S and T) of the ECG signals. Comparisons with other available neural networks for peak recognition have also been conducted. By utilising the features selection approach, the optimum peaks identification performance of the neural networks system has been determined. During implementation, the MSE (dB) of MHMLP network to identify peaks of ECG signals has been recorded at -27.92dB. As a whole, MHMLP network has achieved recognition performance of 83.78% and 89% during testing and training phase respectively.
KW - ECG
KW - Neural network
KW - Noisy peak
UR - http://www.scopus.com/inward/record.url?scp=78149379947&partnerID=8YFLogxK
M3 - Conference Proceeding
AN - SCOPUS:78149379947
SN - 9789604741144
T3 - Proceedings of the 9th WSEAS International Conference on Signal, Speech and Image Processing, SSIP '09, Proc. 9th WSEAS Int. Conf. Multimedia, Internet and Video Technologies, MIV '09
SP - 74
EP - 79
BT - Proceedings of the 9th WSEAS International Conference on Signal, Speech and Image Processing, SSIP '09, Proc. 9th WSEAS Int. Conf. Multimedia, Internet and Video Technologies, MIV '09
T2 - 9th WSEAS International Conference on Signal, Speech and Image Processing, SSIP '09, 9th WSEAS International Conference on Multimedia, Internet and Video Technologies, MIV '09
Y2 - 3 September 2009 through 5 September 2009
ER -