ECG Compression by Efficient Coding

The continuous demand for high performance and low cost electrocardiogram (ECG) processing systems have required the elaboration of more and more efficient and reliable ECG compression techniques. Such techniques face a tradeoff between compression ratio and retrieved quality, where the decrease of the last can compromise the subsequent use of the signal for clinical purposes [1]. The objective of this work is to evaluate the validity and performance of an independent component analysis (ICA) based scheme used to efficiently compress ECG signals while introducing tests for a different type of record of the electrical activity of the heart, such as fetal magnetocardiogram (fMCG). As a result, the reconstructed signals underwent negligible visual deterioration, while achieving promising compression ratios. PROBLEM More efficient compression methods are required for ECG. Many efforts have been made whether to optimize its storage or to make its on-line transmission possible. ECG compression aims to reduce data volume while preserving the morphological features of the signal after reconstruction. Then, signal redundancy must be minimized without loss of the information contained. METHODS •Learning: Independent Component Analysis (ICA) •Projection: We project an ECG window ei onto an ICA learned subspace Φ = [φ1, φ2, . . . , φn] T so that êi = w1φ1 + w2φ2 + . . . + wnφn, (1) where the projection vector wi = [w1, w2, . . . , wn] T is given by wi = E[ΦΦ ]E[eiΦ]. (2)