Comparative analysis of bag-of-words models for ECG-based biometrics

• Published in: IET biometrics Vol. 6; no. 6; pp. 495 - 502
• Main Author: Ciocoiu, Iulian B
• Format: Journal Article
• Language: English
• Published: Stevenage The Institution of Engineering and Technology 01.11.2017; John Wiley & Sons, Inc
• Subjects: Approximation; bag‐of‐words models; Biometric identification; Biometrics; Case Study; Classification; classification strategies; Clustering; Comparative analysis; Design parameters; Dictionaries; ECG‐based biometrics; EKG; Electrocardiography; electrocardiography signals; encoding procedures; Fingers; medical signal processing; Morphology; Parameter identification; Physiology; pooling methods; real ECG recordings; Signal classification; Signal processing; signal representation; sparse representations; Time series; Waveforms; Wavelet transforms; pooling methods; medical signal processing; electrocardiography signals; encoding procedures; sparse representations; ECG-based biometrics; classification strategies; signal representation; real ECG recordings; electrocardiography; signal classification; bag-of-words models
• ISSN: 2047-4938; 2047-4946; 2047-4946
• DOI: 10.1049/iet-bmt.2016.0177

The performances of the bag-of-words approach in biometric applications using electrocardiography (ECG) signals have been analysed according to the influence of specific design parameters. Optimal setup scenarios have been identified combining five encoding procedures, two pooling methods, and three classification strategies. The method does not require waveform segmentation nor fiducial points detection. Comparative results based on extensive experiments conducted on real ECG recordings collected on chest, finger, and hand palm are presented. Sparse representations yield best results, exceeding 99% correct classification rate for a number of 100 subjects, while additionally exhibiting robustness against modifications of the experimental setup.