ECG biometric identification: A compression based approach

Using the electrocardiogram signal (ECG) to identify and/or authenticate persons are problems still lacking satisfactory solutions. Yet, ECG possesses characteristics that are unique or difficult to get from other signals used in biometrics: (1) it requires contact and liveliness for acquisition (2) it changes under stress, rendering it potentially useless if acquired under threatening. Our main objective is to present an innovative and robust solution to the above-mentioned problem. To successfully conduct this goal, we rely on information-theoretic data models for data compression and on similarity metrics related to the approximation of the Kolmogorov complexity. The proposed measure allows the comparison of two (or more) ECG segments, without having to follow traditional approaches that require heartbeat segmentation (described as highly influenced by external or internal interferences). As a first approach, the method was able to cluster the data in three groups: identical record, same participant, different participant, by the stratification of the proposed measure with values near 0 for the same participant and closer to 1 for different participants. A leave-one-out strategy was implemented in order to identify the participant in the database based on his/her ECG. A 1NN classifier was implemented, using as distance measure the method proposed in this work. The classifier was able to identify correctly almost all participants, with an accuracy of 99% in the database used.

[1]  Armando J. Pinho,et al.  A Genomic Distance for Assembly Comparison Based on Compressed Maximal Exact Matches , 2013, IEEE/ACM Transactions on Computational Biology and Bioinformatics.

[2]  Manal M. Tantawi,et al.  Fiducial feature reduction analysis for electrocardiogram (ECG) based biometric recognition , 2012, Journal of Intelligent Information Systems.

[3]  Dimitrios Hatzinakos,et al.  ECG biometric analysis in cardiac irregularity conditions , 2009, Signal Image Video Process..

[4]  Ming Li,et al.  An Introduction to Kolmogorov Complexity and Its Applications , 2019, Texts in Computer Science.

[5]  Jessica Lin,et al.  Finding Motifs in Time Series , 2002, KDD 2002.

[6]  Joseph A. O'Sullivan,et al.  ECG Biometric Recognition: A Comparative Analysis , 2012, IEEE Transactions on Information Forensics and Security.

[7]  Péter Gács,et al.  Information Distance , 1998, IEEE Trans. Inf. Theory.

[8]  Armando J. Pinho,et al.  Computation of the Normalized Compression Distance of DNA Sequences using a Mixture of Finite-context Models , 2012, BIOINFORMATICS.

[9]  Hsiao-Lung Chan,et al.  Human identification by quantifying similarity and dissimilarity in electrocardiogram phase space , 2009, Pattern Recognit..

[10]  Brenda K. Wiederhold,et al.  ECG to identify individuals , 2005, Pattern Recognit..

[11]  L. Biel,et al.  ECG analysis: a new approach in human identification , 1999, IMTC/99. Proceedings of the 16th IEEE Instrumentation and Measurement Technology Conference (Cat. No.99CH36309).

[12]  Armando J. Pinho,et al.  Image similarity using the normalized compression distance based on finite context models , 2011, 2011 18th IEEE International Conference on Image Processing.

[13]  Hsiao-Lung Chan,et al.  QRS detection-free electrocardiogram biometrics in the reconstructed phase space , 2013, Pattern Recognit. Lett..

[14]  Eamonn J. Keogh,et al.  A symbolic representation of time series, with implications for streaming algorithms , 2003, DMKD '03.

[15]  Péter Gács,et al.  Information Distance , 1998, IEEE Trans. Inf. Theory.

[16]  Armando J. Pinho,et al.  A Compression Model for DNA Multiple Sequence Alignment Blocks , 2013, IEEE Transactions on Information Theory.

[17]  Eamonn J. Keogh,et al.  Towards parameter-free data mining , 2004, KDD.

[18]  Fahim Sufi,et al.  Faster person identification using compressed ECG in time critical wireless telecardiology applications , 2011, J. Netw. Comput. Appl..

[19]  Ana L. N. Fred,et al.  Novel fiducial and non-fiducial approaches to electrocardiogram-based biometric systems , 2013, IET Biom..

[20]  Armando J. Pinho,et al.  On the Representability of Complete Genomes by Multiple Competing Finite-Context (Markov) Models , 2011, PloS one.

[21]  Jeffrey M. Hausdorff,et al.  Physionet: Components of a New Research Resource for Complex Physiologic Signals". Circu-lation Vol , 2000 .

[22]  Bin Ma,et al.  The similarity metric , 2001, IEEE Transactions on Information Theory.