A novel framework using sparse representation of local segments for human identification from ECG signals achieved an accuracy of 99.48% on a 100-subject dataset without requiring heartbeat segmentation.
Does a sparse representation of local segments from ECG signals accurately identify human subjects without requiring heartbeat segmentation?
A novel framework using sparse representation of local ECG segments achieves 99.48% accuracy for human identification without requiring heartbeat segmentation.
This work proposes a novel framework to extract compact and discriminative features from Electrocardiogram (ECG) signals for human identification based on sparse representation of local segments. Specifically, local segments extracted from an ECG signal are projected to a small number of basic elements in a dictionary, which is learned from training data. A final representation is extracted by performing a max pooling procedure over all the sparse coefficient vectors in the ECG signal. Unlike most of existing methods for human identification from ECG signals which require segmentation of individual heartbeats or extraction of fiducial points, the proposed method does not need to segment individual heartbeats or detect any fiducial points. The method achieves an 99.48% accuracy on a 100 subjects dataset constructed from a publicly available database, which demonstrates that both local and global structural information are well captured to characterize the ECG signals.
Wang et al. (Mon,) conducted a other in Human identification from ECG signals (n=100). Sparse representation of local segments for ECG feature extraction vs. Existing methods requiring segmentation of individual heartbeats or extraction of fiducial points was evaluated on Accuracy of human identification. A novel framework using sparse representation of local segments for human identification from ECG signals achieved an accuracy of 99.48% on a 100-subject dataset without requiring heartbeat segmentation.