Combined Principal Component Analysis and Compression of 12-Lead Electrocardiogram signal using Singular Value Decomposition
||International Journal of Computer Trends and Technology (IJCTT)||
|© 2017 by IJCTT Journal|
|Year of Publication : 2017|
|Authors : Dr. Mridul Kumar Mathur, Gyan Prakash Bissa|
|DOI : 10.14445/22312803/IJCTT-V45P102|
Dr. Mridul Kumar Mathur, Gyan Prakash Bissa; "Combined Principal Component Analysis and Compression of 12-Lead Electrocardiogram signal using Singular Value Decomposition". International Journal of Computer Trends and Technology (IJCTT) V45(1):4-9, March 2017. ISSN:2231-2803. www.ijcttjournal.org. Published by Seventh Sense Research Group.
Electrocardiogram (ECG) is the bioelectric signals generated during the cardiac cycle. ECG shows the actual functioning of the heart and various heart diseases can be diagnosed after analyzing ECG signals. In addition to that ECG signals are required to be compressed for cost-effective storage and fast transmission over low bandwidth channels to the remote locations. Principal Component Analysis identifies the most important features of ECG signals and ECG signal can be compressed using these Principal Components. Principal Components with high variance can be retained and low variance can be discarded. Thus the ECG signal can be compressed. Multiple leads of ECG signal can depict the clear picture of the heart therefore in this paper singular value decomposition (SVD) is used to obtained combined Principal Components of twelve lead Physikalisch-Technische Bundesanstalt (PTB) Data Base ECG signal. Along with this ECG signal is also compressed and reconstructed with the help of first few Eigen Vectors and quantity of compression is measured by Compression Ratio (CR) and reconstructed signal quality is measured by Percentage Root Mean Square (PRD) difference.
 Health Care in America Trends in utilization, U.S. Department of Health and Human Services, DHHS Pub No. 2004-1031
 National Center for Health Statistics.National Ambulatory Medical Care Survey and National Hospital Ambulatory Medical Care Survey Reason for Visit Classification and Coding Manual. Hyattsville, Maryland: Ambulatory Care Statistics Branch, Division of Health Care Statistics; 2004.
 I.T, Jolliffe, Principal component analysis, New York: Springer, 2nd edition, 2002.
 H, Hotelling, Analysis of a complex of statistical variable into principal components, J.Educ. Psych., vol. 24, 417-441, 1933.
 I. A. Practical, M. Data, A. D. P. Berrar, and W. Dubitzky, “Chapter 5 Singular value decomposition and principal component analysis,” pp. 1–18, 2003.
 Workalemahu, Tsegaselassie, "Singular Value Decomposition in Image Noise Filtering and Reconstruction" (2008). Mathematics Theses.Paper 52.
 R. E. Madsen, L. K. Hansen, and O. Winther, “Singular Value Decomposition and Principal Component Analysis,” no.February, pp. 1–5, 2004.
 M. Blanco-Velasco, F. Cruz-Roldán, J. I. Godino-Llorente, J. Blanco-Velasco, C. Armiens-Aparicio, and F. López-Ferreras, On the Use of PRD and CR Parameters for ECG Compression, International Journal on Medical Engineering & Physics 27(6) (2005) 798-802, http://dx.doi.org/10.1016/j.medengphy.2005.02.007.
 J. Pan, W.J. Tompkins. A real-time QRS detection algorithm. IEEE Trans. Biomed.Eng. 1985; vol.32; pp. 230-236.
 Pradeepsingh, sulochana and A.K.wadhwani, “ECG data compression based on principal component analysis”, vol 1, June 2013.
Compression Ratio (CR), Percentage Root Mean Square Difference (PRD) difference ,Eigen Value; Eigen Vector; Principal Components analysis;