Abstract
In this paper, we describe a multi-lead electrocardiogram (MECG) compression technique, which preserves pathological information in different affected leads while achieving high overall compression. For non-affected leads, the principal component decomposed expansion coefficients were optimally quantized using a feed-forward neural network. For affected leads, the wavelet decomposed coefficients were quantized using a fixed level. The proposed technique was evaluated with 130 ECG records with three major classes of myocardial infarction under Physionet. An average overall compression ratio of 21.25, with low values of percentage root mean squared difference of 2.45 for the affected lead group, was obtained.
Acknowledgements
The authors sincerely acknowledge Dr Jayanta Saha, MD (Med.), DM (Card.), Associate Professor at the Department of Cardiology, Medical College and Hospital, Kolkata, India for his suggestions, feedback and double-blind clinical evaluation of the reconstructed ECG records. Priyanka Bera acknowledges the Council for Scientific and Industrial Research (CSIR), India for the fellowship.
Additional information
Funding
Notes on contributors
![](/cms/asset/f1d24ba2-d36b-4c50-8cf7-3be888914e8b/titr_a_1831971_ilg0001.gif)
Priyanka Bera
Priyanka Bera is currently a research scholar with Electrical Engineering Section, Department of Applied Physics, University of Calcutta, India. She completed her BTech (2009) and MTech (2013) in instrumentation engineering from West Bengal University of Technology and University of Calcutta, India, respectively. She is currently pursuing PhD on biomedical instrumentation and signal processing. She has six publications in peer-reviewed international journals and conferences. Email: [email protected]
![](/cms/asset/9fca75a0-721c-47df-9d84-327d94c79f14/titr_a_1831971_ilg0002.gif)
Rajarshi Gupta
Rajarshi Gupta is currently professor with Electrical Engineering Section, Dept. of Applied Physics at the University of Calcutta, India. His research interests include biomedical signal analysis, and intelligent health monitoring. He has 60 publications in national and international peer-reviewed journals and conferences. He is involved as PI/Co-PI with five funded research projects on biomedical measurements and health monitoring applications development, with a total funding of INR 61 lakhs. Currently, he is guiding five PhD students and one scholar has been awarded PhD.