Abstract The objective of this paper is to develop an efficient P wave detection algorithm based on the morphology characteristics of arrhythmias using correlation and regression in ECG signal. Subjects for experiments included normal subjects, patients with atrial fibrillation, ventricular tachycardia, and patients with change of the artifactuale amplitude. After the step of the detection of R peak using the pan- tompkins algorithm, the correlation and regression were utilized to calculate the similarity factors between a studied P wave and the reference one. The correlation coefficient can indicate the kind of arrhythmia diseases. The algorithm was tested using MIT-BIH arrhythmia database where every P wave was classified. The results are presented in terms of correlation coefficient. Then some parameters have been extracted in order to classify the arrhythmias. The correlation coefficient results of the system are 1,0.07 and –0.92 for normal beats, atrial fibrillation and change of the artifactuale amplitude, respectively. The extracted parameters are closely similar to the expert values given by the cardiologist. The results reveal that the system is accurate and efficient to detect and classify arrhythmias resulted from atrial fibrillation or change of the artifactuale amplitude.

References

[1] Addison P., Wavelet Transforms and the ECG: A Review, Physiological Measurement , vol. 26, no. 5, pp. 155-199, 2005.

[2] Belgacem N., Chikh M., and Reguig F., D tection et Identification des Arythmies Cardiaques Par Application des R seaux de Neurones , in Conf rence Internationale sur les Syst mes de T l communications d'Electronique M dicale et d'Automatique CISTEMA , Algeria, pp. 236-239, 2003 .

[3] BenMessaoud M., Kachouri A., and Sai R., Diagnostic of Electrocardiogram ECG by Wavelet Transform Technique , in Proceedings of the IEEE Symposium on Signal Processing and Information Technology (ISSPIT) , Egypt, pp. 1 , 2001 .

[4] Chiu C., Lin T., and Liau B., Using Correlation Coefficient in ECG Waveform for Arrhythmia Detection, Biomedical Engineering Applications B asis Communications, vol. 17, no. 3, pp. 147-152. 2005.

[5] Cohen J., Cohen P., West S., and Aiken L., Applied Multiple Regression/Correlation Analysis fort the Behavioral Sciences , Lawrence Erlbaum , New York, 1983.

[6] Dubois R. , Application des Nouvelles M thodes d Apprentissage la D tection Pr coce d Anomalies en Electrocardiographie , Th se de Doctorat, Paris, 2004.

[7] PhysioNet , http://www.physionet.org/physiobank /database/ht ml /mitdbdir/intro.htm , 2007.

[8] Khelil B., Kachouri A., and Ben Messaoud M., Nouvelle Tendance Technologiques en G nie Electrique et Informatique, Springer, New York , 2006.

[9] Le Page R. and Boucher J., D tection et Analyse de l Onde P d Un Electrocardiogramme , Colloque GRETSI 01 , France, 2001.

[10] Le Page R. , D tection et Analyse de l onde P d Un Electrocardiogramme : Application au D pistage de la Fibrillation Auriculaire . Th se de Doctorat, Paris, 2003.

[11] Mahmoodabadi S., Ahmadian A., and Abolhasani M., ECG Feature Analysis and Parameter Extraction of P Wave Using Correlation Method 46 Extraction Using Daubechies Wavelets, in Proceedings of the International Association of Science and Technology for Development (IASTED) , Spain, pp. 220-225, 2005.

[12] McNames J., Optimal Rate Filters for Biomedical Point Processes, in Proceedings of the IEEE Medical & Biological Engineering 27 th Annual , China, pp 5388-5391, 2005.

[13] Narayan S., Kahn A., Brown J., Krummen D., Bhargava V., and Feld G., Determination of Intra-Atrial Fibrillatory Cycle Length from the Electrocardiogram Using Auto-Correlation Analysis, International Journal of Bioelectromagnetism Advances in Electrocardiology , vol. 7, no. 1, pp. 162-165, 2005.

[14] Pan J. and Tompkins W., A Real Time QRS Detection Algorithm, IEEE Transactionsons on Biomedical Engineering , vol. 32, no. 3, pp. 230- 236, 1985.

[15] Portet F. , Pilotage D'algorithmes Pour la Reconnaissance en Ligne D'arythmies Cardiaques, Th se de doctorat , Paris , 2005.

[16] Schreicr G., Kastner P., and Marko W., An Automatic ECG Processing Algorithm to Identify Patients Prone to Paroxysmal Atrial Fibril lation, IEEE Computers in Cardlology , vol. 28, pp. 133- 135, 2001.

[17] Tan K., Chan K., and Choi K., Detection of the QRS Complex, P Wave and T Wave in Electrocardiogram, in Proceddings of First International Conference on Advances in Medical Signal and Information, pp. 41-47, UK, 2000.

[18] Poli S., Barbaro V., Bartolini P., Calcagnini G., and Censi F., Prediction of Atrial Fibrillation from Surface ECG: Review of Methods and Algorithms, in Annual I st Super Sanit , vol. 39, no. 2, pp. 195-203, 2003. Mohamed Ben Messaoud received the engineer degree in electrical engineering from the University of Sfax, Tunisia, in 1981 and the Docteur Ingenieur Diploma in automatic control engineering from the University of Paul Sabatier of Toulouse, France, in 1983. Besma Khelil received the engineer degree in electric engineering from the National School of engineering of Sfax (ENIS), Tunisia, in 2005, and the MSc degree in electronic from University of Sfax, Tunisia, in 2007. Abdennaceur Kachouri received the engineering diploma from National School of Engineers of Sfax in 1981, a Master degree in measurement and instrumen-tation from National School of Bordeaux (ENSERB) of France in 1981, and a Doctorate in measurement and instrumentation from NSERB, in 1983.