11
Views
4
CrossRef citations to date
0
Altmetric
Original Articles

ECG Data Compression using EBP-NN

, FIETE, , FIETE &
Pages 583-604 | Published online: 26 Mar 2015
 

Abstract

This paper deals with an efficient algorithm, which has been developed for Electrocardiogram (ECG) data compression using error back propagation neural networks (EBP-NN). Four EBP-NN have been trained to retrieve all the 12 standard leads of the ECG signal. The combination of leads and the network topologies have been finalized after an extensive study of correlation between the ECG leads using CSE database. Each network has a topology of N-4-4-N, where N represents the number of samples in one cycle in any particular lead. It has been observed that this method compresses the data as well as improves the quality of retrieved signal due to elimination of high frequency noise. The compression ratio (CR) in EBP-NN method goes on increasing with the increase in the number of ECG cycles. This method is best suited for data compression in Holter monitoring, ambulatory care and telemedicine. The performance of the algorithm has been evaluated by comparing the vital reference points like onsets, offsets, amplitudes, durations and the extracted features of diagnostic significance like amplitudes, durations and ventricular activation time (VAT) of various wave segments of the original and the reconstructed ECG signals. The use of wavelet transform has been made for the QRS detection, which sets the reference for the extraction of reference points and the diagnostic parameters from the ECG signal. The test results at each stage are consistent and reliable. The test results and performance indices have proved beyond doubt that the EBP-NN method is very efficient for the data compression and help in the management of ECG data in both offline and real-time applications.

Additional information

Notes on contributors

S C Saxena

S C Saxena, Dean of Students Welfare and Professor of Electrical Engineering Department at mc Indian Institute of Technology Roorkee, Roorkee obtained BE (Electrical) from Allahabad University in 1970 and ME Electrical (M&I) and PhD from University of Roorkee in 1973 and 1977 respectively. He has served as an Expert at Military Technical College, Baghdad, Iraq during 1983–86 and as an Advisor in AICTE, New Delhi in the year 1994. Dr Saxena has visited France, Iraq and Kuwait. He has very wide and valuable experience of Academics and Student affairs in various important capacities in the Institute. He has published about 140 research papers al National & international levels; written 6 monographs; received 9 awards including Khosla Gold Medal & cash Award, Khosla Silver Medal and Cash Award, President of India's Prize, Jawaharlal Memorial Award; organised 23 specialised courses for industry; handled 10 research schemes; guided a large number of UG and 80 PG students for their projects, seminars and dissertations; supervised 11 and supervising 7 Ph.D. theses; organised at Chairman/Co-chairman/convener/organising secretary international/National Conferences/Seminars/Workshops, and made three educational films. Dr Saxena is a fellow of IEI, Fellow of IETE, and Life Member of BMESI, NIQR, ISTE and ISCEE. He is Vice-President of Biomedical Engg. Society of India, former Council member of the IE (I); former Chairman Roorkee local centre of the IE(I), Vice-President ISCEE, Member Management Committee of UP State Centre of the IE(I), Chairman ISTE chapter at Indian Institute of Technology Roorkee, Vice-chairman, NIQR Chapter at Roorkee, and Chairman, Consultants Committee of Roorkee School for the Deaf. He has been the Honorary Secretary of Roorkee local Centre of the IE(I)and worked on number of Expert Committees of AICTE, New Delhi and University Sector institutions. His areas of specializations are Biomedical Engineering, Measurement & Instrumentation. He has experience of over 25 years of consultancy and testing. Dr. Saxena is a trained Motivation Trainer by NIMID Bombay and NIESBUD, New Delhi.

Vinod Kumar

Vinod Kumar Professor, obtained his BSc (Elect Engineering) Hons Degree from Punjab University in 1973, ME (Measurement & Instrumentation) Hons and PhD Degree from University of Roorkee, Roorkee in 1975 and 1984 respectively. He joined the Electrical Engineering Department of University of Roorkee, Roorkee in 1975. He has published more than 90 research papers, guided 52 PG students, supervised 9 and supervising 4 PhD theses. He has undertaken large number of consultancy & sponsored projects from industries and government department. He was elected as Fellow of the Institution of Engineers (I), Institution of Electronics and Telecommunication Engineers, and is a member of many professional bodies. He has received many awards including Khosla Medal and best paper awards of the Institution of Engineers. He has organised a workshop on Biomedical Engineering Education to frame the model syllabi in the area of biomedical engineering. He has also conducted several courses, workshops for the benefit of faculty & field engineers. Presently, Dr. Kumar is also coordinator, Audio Visual Research Centre IIT, Roorkee. His areas of interest are Measurement and Instrumentation, Medical Instrumentation, Digital Signal Processing and Telemedicine.

V K Giri

V K Giri obtained his BE (Electrical) Degree from REC, Sural (Gujrat) in 1988 and ME (Measurement and Instrumentation) Hons Degree from University of Roorkee, Roorkee in 1997. He is serving as Sr Lecturer in M M M Engineering College, Gorakhpur (UP) since last 11 years. Mr. Giri has published 4 research papers. He is the life member of ISTE, member IEE and member CSI. He is now working towards the PhD degree at the Electrical Engineering Department of the Indian Institute of Technology, Roorkee. His research interests include Biomedical Instrumentation, Data Compression and Telemedicine.

Reprints and Corporate Permissions

Please note: Selecting permissions does not provide access to the full text of the article, please see our help page How do I view content?

To request a reprint or corporate permissions for this article, please click on the relevant link below:

Academic Permissions

Please note: Selecting permissions does not provide access to the full text of the article, please see our help page How do I view content?

Obtain permissions instantly via Rightslink by clicking on the button below:

If you are unable to obtain permissions via Rightslink, please complete and submit this Permissions form. For more information, please visit our Permissions help page.