A hybrid model of Maximum Margin Clustering method and support vector regression for solving the inverse ECG problem

Compared to body surface potentials (BSPs) recordings, myocardial transmembrane potentials (TMPs) can provide more detailed and complicated electrophysiological information. Noninvasively reconstructing the TMPs from BSPs constitutes one form of the inverse problem of ECG. In this study, the inverse ECG problem is treated as a regression problem with multi-inputs (BSPs) and multi-outputs (TMPs), which will be solved by the support vector regression (SVR) method. In this paper, the Maximum Margin Clustering (MMC) approach is adopted to cluster the training samples (different time instant BSPs), and the individual SVR model for each cluster is then constructed. For each testing sample, find the cluster to which it belongs, and then use the corresponding SVR model to reconstruct the TMPs. When reconstructing the TMPs over the testing samples, the experiment results show that SVR method combined with maximum margin clustering method can perform better than the single SVR method in solving the inverse ECG problem, leading to a more accurate reconstruction of the TMPs.