Key result
Error back propagation neural networks compress ECG data and improve signal quality by eliminating high-frequency noise.
An EBP-NN algorithm effectively compresses ECG data for applications like Holter monitoring and telemedicine while maintaining diagnostic signal integrity.
Answers are grounded in this paper and cite their sources.
May support ECG compression for Holter and telemedicine; leaves open prospective clinical validation before adoption.
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.
No takes yet. Share an insight, caveat, or question.
Saxena et al. (2003) studied ECG data compression. Error back propagation neural networks (EBP-NN) vs. Original ECG signals was evaluated on Data compression and quality of retrieved signal (vital reference points and extracted features). ECG data compression using error back propagation neural networks efficiently compressed data and improved the quality of the retrieved signal by eliminating high-frequency noise.
Synapse has enriched 10 related papers. Consider them for comparative context: