AI Chat Paper
Note: Please note that the following content is generated by AMiner AI. SciOpen does not take any responsibility related to this content.
{{lang === 'zh_CN' ? '文章概述' : 'Summary'}}
{{lang === 'en_US' ? '中' : 'Eng'}}
Chat more with AI
Powered by AMiner. Clicking this button will take you away from SciOpen.
Home Journal of Computer Science and Technology Article
Article Link
Cite
EndNote(RIS) BibTeX
Collect
Submit Manuscript
Show Outline
Outline
Show full outline
Hide outline
Outline
Show full outline
Hide outline
Regular Paper

Multi-Scale Deep Cascade Bi-Forest for Electrocardiogram Biometric Recognition

School of Software, Shandong University, Jinan 250101, China
School of Computer, Heze University, Heze 274015, China
Department of Computer Engineering, Changji University, Changji 831100, China
Show Author Information

Abstract

Electrocardiogram (ECG) biometric recognition has emerged as a hot research topic in the past decade. Although some promising results have been reported, especially using sparse representation learning (SRL) and deep neural network, robust identification for small-scale data is still a challenge. To address this issue, we integrate SRL into a deep cascade model, and propose a multi-scale deep cascade bi-forest (MDCBF) model for ECG biometric recognition. We design the bi-forest based feature generator by fusing L1-norm sparsity and L2-norm collaborative representation to efficiently deal with noise. Then we propose a deep cascade framework, which includes multi-scale signal coding and deep cascade coding. In the former, we design an adaptive weighted pooling operation, which can fully explore the discriminative information of segments with low noise. In deep cascade coding, we propose level-wise class coding without backpropagation to mine more discriminative features. Extensive experiments are conducted on four small-scale ECG databases, and the results demonstrate that the proposed method performs competitively with state-of-the-art methods.

Keywords

electrocardiogram (ECG) biometric recognitionsmall-scale datadeep cascade bi-forestmulti-scale divisionsparse representation learning

Electronic Supplementary Material

Download File(s)
jcst-36-3-617-Highlights.pdf (170.2 KB)

References

[1]

Odinaka I, Lai P H, Kaplan A D, Osullivan J A, Sire-vaag E J, Rohrbaugh J W. ECG biometric recognition: A comparative analysis. IEEE Trans. Information Forensics and Security, 2012, 7(6): 1812-1824. DOI: 10.1109/TIFS.2012.2215324.
Crossref Google Scholar
[2]

Kim M, Pan S B. Deep learning based on 1-D ensemble networks using ECG for real time user recognition. IEEE Trans. Industrial Informatics, 2019, 15(10): 5656-5663. DOI: 10.1109/TII.2019.2909730.
Crossref Google Scholar
[3]

Wang J, She M, Nahavandi S, Kouzani A Z. Human identification from ECG signals via sparse representation of local segments. IEEE Signal Processing Letters, 2013, 20(10): 937-940. DOI: 10.1109/LSP.2013.2267593.
Crossref Google Scholar
[4]

Jaafar H, Ramli N, Nasir A S A. Implementation of kernel sparse representation classifier for ECG biometric system. Journal of Telecommunication, Electronic and Computer Engineering, 2018, 10(1-13): 89-94
Google Scholar
[5]

Li R, Yang G, Wang K, Huang Y, Yuan F, Yin Y. Robust ECG biometrics using GNMF and sparse representation. Pattern Recognition Letters, 2019, 129: 70-76. DOI: 10.1016/j.patrec.2019.11.005.
Crossref Google Scholar
[6]

Goshvarpour A, Goshvarpour A. Human identification using a new matching pursuit-based feature set of ECG. Computer Methods and Programs in Biomedicine, 2019, 172: 87-94. DOI: 10.1016/j.cmpb.2019.02.009.
Crossref Google Scholar
[7]

Zhang L, Liu J, Zhang B, Zhang D, Zhu C. Deep cascade model-based face recognition: When deep-layered learning meets small data. IEEE Trans. Image Process, 2019, 29: 1016-1029. DOI: 10.1109/TIP.2019.2938307.
Crossref Google Scholar
[8]

Abdeldayem S S, Bourlai T. A novel approach for ECG-based human identification using spectral correlation and deep learning. IEEE Trans. Biometrics, Behavior, and Identity Science, 2020, 2(1): 1-14. DOI: 10.1109/TBIOM.2019.2947434.
Crossref Google Scholar
[9]

Labati R D, Munoz E, Piuri V, Sassi R, Scotti F. Deep-ECG: Convolutional neural networks for ECG biometric recognition. Pattern Recognition Letter, 2019, 126: 78-85. DOI: 10.1016/j.patrec.2018.03.028.
Crossref Google Scholar
[10]

da Silva Luz E, Moreira G, Oliveira L S, Schwartz W R, Menotti D. Learning deep off-the-person heart biometrics representations. IEEE Trans. Information Forensics and Security, 2017, 13(5): 1258-1270. DOI: 10.1109/TIFS.2017.2784362.
Crossref Google Scholar
[11]

Hammad M, Liu Y, Wang K. Multimodal biometric authentication systems using convolution neural network based on different level fusion of ECG and fingerprint. IEEE Access, 2019, 7: 26527-26542. DOI: 10.1109/AC-CESS.2018.2886573.
Crossref Google Scholar
[12]

Zhang Y, Xiao Z, Guo Z, Wang Z. ECG-based personal recognition using a convolutional neural network. Pattern Recognition Letter, 2019, 125: 668-676. DOI: 10.1016/j.patrec.2019.07.009.
Crossref Google Scholar
[13]
Zhou Z, Feng J. Deep forest: Towards an alternative to deep neural networks. In Proc. the 26th Int. Artificial Intelligence, August 2017, pp.3553-3559. DOI: 10.24963/ij-cai.2017/497.
Crossref
[14]
Liu X B, Wang R, Cai Z, Cai Y, Yin X. Deep multi-grained cascade forest for hyperspectral image classification. IEEE Trans. Geoscience and Remote Sensing, 2019, 57(10): 8169-8183. DOI: 0.1109/TGRS.2019.2918587.
Crossref
[15]
Wen H, Zhang J, Lin Q, Yang K, Huang P. Multi-level deep cascade trees for conversion rate prediction in recommendation system. In Proc. the 23rd Int. Artificial Intelligence, May 2019, pp.338-345. DOI: 10.1609/aaai.v33i01.3301338.
Crossref
[16]

Lim C, Woo W L, Dlay S, Gao B. Heartrate-dependent heartwave biometric identification with thresholding-based GMM-HMM methodology. IEEE Trans. Industrial Informatics, 2019, 15(1): 45-53. DOI: 10.1109/TII.2018.2874462.
Crossref Google Scholar
[17]
Meltzer D, Luengo D. Fiducial ECG-based biometry: Comparison of classifiers and dimensionality reduction methods. In Proc. the 42nd Int. Telecommunications and Signal Processing, Jul. 2019, pp.552-556. DOI: 10.1109/TSP.2019.8768891.
Crossref
[18]

Diab M O, Seif A, El-Abed M, Sabbah M. Individual identification using ECG signals. Journal of Computer and Communications, 2018, 6: 74-80. DOI: 10.4236/jcc.2018.61008.
Crossref Google Scholar
[19]

Dong X, Si W, Huang W. ECG-based identity recognition via deterministic learning. Biotechnology & Biotech-nological Equipment, 2018, 32(3): 769-777. DOI: 10.1080/13102818.2018.1428500.
Crossref Google Scholar
[20]

Rahman S A E. Biometric human recognition system based on ECG. Multimedia Tools and Applications, 2019, 78(3): 17555-17572. DOI: 10.1007/s11042-019-7152-0.
Crossref Google Scholar
[21]
Srivastva R, Singh Y N. Human recognition using discrete cosine transform and discriminant analysis of ECG. In Proc. the 4th Int. Image Information Processing, Dec. 2017, pp.368-372. DOI: 10.1109/ICIIP.2017.8313742.
Crossref
[22]

Bassiouni M M, El-Dahshan E A, Khalefa W, Salem A M. Intelligent hybrid approaches for human ECG signals identification. Signal, Image and Video Processing, 2018, 12(5): 941-949. DOI: 10.1007/s11760-018-1237-5.
Crossref Google Scholar
[23]
Ur Rehman U, Kamal K, Iqbal J, Sheikh M F. Biometric identification through ECG signal using a hybridized approach. In Proc. the 5th Int. Computing and Artificial Intelligence, Apr. 2019, pp.226-230. DOI: 10.1145/3330482.3330496.
Crossref
[24]

Wu S C, Chen P T, Swindlehurst A L, Hung P L. Cancelable biometric recognition with ECGs: Subspace-based approaches. IEEE Trans. Information Forensics and Security, 2019, 14(5): 1323-1336. DOI: 10.1109/TIFS.2018.2876838.
Crossref Google Scholar
[25]

He H, Tan Y. Automatic pattern recognition of ECG signals using entropy-based adaptive dimensionality reduction and clustering. Applied Soft Computing, 2017, 55: 238-252. DOI: 10.1016/j.asoc.2017.02.001.
Crossref Google Scholar
[26]
Srivastva R, Singh Y. ECG biometric analysis using Walsh-Hadamard transform. In Advances in Data and Information Sciences, Kolhe M L, Trivedi M C, Tiwari S, Singh V (eds.), Springer, 2018, pp.201-210. DOI: 10.1007/978-981-10-8360-0_19.
Crossref
[27]
Zheng G, Wang Y, Sun X, Sun Y, Ji S. Study on Matthew effect based feature extraction for ECG biometric. In Proc. the 8th Int. Conf. Intelligent Science and Big Data Engineering, Aug. 2018, pp.623-634. DOI: 10.1007/978-3-030-02698-1-54.
Crossref
[28]

Pinto J R, Cardoso J S, Lourenço A. Evolution, current challenges, and future possibilities in ECG biometrics. IEEE Access, 2018, 6: 34746-34776. DOI: 10.1109/AC-CESS.2018.2849870.
Crossref Google Scholar
[29]
Pal A, Singh Y. ECG biometric recognition. In Proc. the 4th Int. Conf. Mathematics and Computing, Jan. 2018, pp.61-73. DOI: 10.1007/978-981-13-0023-37.
Crossref
[30]

Hejazi M, Al-Haddad S A R, Singh Y P, Hashim S J, Aziz A F A. ECG biometric authentication based on non-fiducial approach using kernel methods. Digital Signal Processing, 2016, 52: 72-86. DOI: 10.1016/j.dsp.2016.02.008.
Crossref Google Scholar
[31]
Chen H, Huang C, Huang Q, Zhang Q, Wang W. ECGadv: Generating adversarial electrocardiogram to misguide arrhythmia classification system. In Proc. the 34th AAAI Conference on Artificial Intelligence, Feb. 2020, pp.3446-3453. DOI: 10.1609/aaai.v34i04.5748.
Crossref
[32]

Utkin L V, Ryabinin M A. Discriminative metric learning with deep forest. International Journal of Artificial Intelligence Tools, 2017, 28(2): 195-204. DOI: 10.1142/S0218213019500076.
Crossref Google Scholar
[33]

Su R, Liu X,Wei L, Zou Q. Deep-Resp-forest: A deep forest model to predict anti-cancer drug response. Methods, 2019, 166: 91-102. DOI: 10.1016/j.ymeth.2019.02.009.
Crossref Google Scholar
[34]
Pang M, Ting K M, Zhao P, Zhou Z. Improving deep forest by confidence screening. In Proc. the 20th Int. Data Mining, Nov. 2018, pp.1194-1199. DOI: 10.1109/ICDM.2018.00158.
Crossref
[35]

Lan X, Zhang S, Yuen P C, Chellappa R. Learning common and feature-specific patterns: A novel multiple-sparse-representation-based tracker. IEEE Trans. Image Processing, 2017, 27(4): 2022-2037. DOI: 10.1109/TIP.2017.2777183.
Crossref Google Scholar
[36]

Panagakis Y, Kotropoulos C, Arce G R. Music genre classification via joint sparse low-rank representation of audio features. IEEE/ACM Trans. Audio, Speech, and Language Processing, 2014, 22(12): 1905-1917. DOI: 10.1109/TASLP.2014.2355774.
Crossref Google Scholar
[37]

Wright J, Yang A Y, Ganesh A, Sastry S, Ma Y. Robust face recognition via sparse representation. IEEE Trans. Pattern Analysis and Machine Intelligence, 2009, 31(2): 210-227. DOI: 10.1109/TPAMI.2008.79.
Crossref Google Scholar
[38]

Moody G B, Mark R G. The impact of the MIT-BIH arrhythmia database. IEEE Engineering in Medicine and Biology Magazine, 2001, 20(3): 45-50. DOI: 10.1109/51.932724.
Crossref Google Scholar
[39]

Bousseljot R, Kreiseler D, Schnabel A. Nutzung der EKG-signaldatenbank CARDIODAT der PTB uber das internet. Biomedizinische Technik/Biomedical Engineering, 2009, 40(s1): 317-318. DOI: 10.1515/bmte.1995.40.s1.317.
Crossref Google Scholar
[40]

Da Silva H P, Lourenço A, Fred A, Raposo N, Airesde-Sousa M. Check your biosignals here: A new dataset for off-the-person ECG biometrics. Computer Methods and Programs in Biomedicine, 2014, 113(2): 503-514. DOI: 10.1016/j.cmpb.2013.11.017.
Crossref Google Scholar
[41]
Pouryayevali S, Wahabi S, Hari S, Hatzinakos D. On establishing evaluation standards for ECG biometrics. In Proc. the 2014 Int. Conf. Acoustics, Speech and Signal Processing, May 2014, pp.3774-3778. DOI: 10.1109/ICASSP.2014.6854307.
Crossref
[42]

Pan J, Tompkins W J. A real-time QRS detection algo-rithm. IEEE Trans. Biomedical Engineering, 1985, BME-32(3): 230-236. DOI: 10.1109/TBME.1985.325532.
Crossref Google Scholar
[43]

Biel L, Pettersson O, Philipson L, Wide P. ECG analysis: A new approach in human identification. IEEE Trans. Instrumentation and Measurement, 2001, 50(3): 808-812. DOI: 10.1109/19.930458.
Crossref Google Scholar
[44]

Chan A A, Hamdy M M, Badre A, Badee V. Wavelet distance measure for person identification using electrocar-diograms. IEEE Trans. Instrumentation & Measurement, 2008, 57(2): 248-253. DOI: 10.1109/TIM.2007.909996.
Crossref Google Scholar
[45]
Yang J, Yu K, Gong Y, Huang T S. Linear spatial pyramid matching using sparse coding for image classification. In Proc. the 2009 Computer Vision and Pattern Recognition, Jun. 2009, pp.1794-1801. DOI: 10.1109/CVPR.2009.5206757.
Crossref
[46]

Wang K, Yang G, Huang Y, Yin Y. Multi-scale differential feature for ECG biometrics with collective matrix factorization. Pattern Recognition, 2020, 102: Article No. 107211. DOI: 10.1016/j.patcog.2020.107211.
Crossref Google Scholar
[47]

Chu Y, Shen H, Huang K. ECG authentication method based on parallel multi-scale one-dimensional residual net-work with center and margin loss. IEEE Access, 2019, 7: 51598-51607. DOI: 10.1109/ACCESS.2019.2912519.
Crossref Google Scholar
[48]

Komeili M, Louis W, Armanfard N, Hatzinakos D. Feature selection for nonstationary data: Application to human recognition using medical biometrics. IEEE Trans. Cybern., 2018, 48(5): 1446-1459. DOI: 10.1109/TCYB.2017.2702059.
Crossref Google Scholar
[49]

Huang Y W, Yang G P, Wang K K, Liu H Y, Yin Y L. Learning joint and specific patterns: A unified sparse representation for o_-the-person ECG biometric recognition. IEEE Trans. Information Forensics & Security, 2021, 16(1): 147-160. DOI: 10.1109/TIFS.2020.3006384.
Crossref Google Scholar
[50]

Lynn H M, Pan S B, Kim P. A deep bidirectional GRU net-work model for biometric electrocardiogram classification based on recurrent neural networks. IEEE Access, 2019, 7: 145395-145405. DOI: 10.1109/ACCESS.2019.2939947.
Crossref Google Scholar
[51]

Louis W, Komeili M, Hatzinakos D. Continuous authentication using one-dimensional multi-resolution local binary patterns (1DMRLBP) in ECG biometrics. IEEE Trans. Information Forensics & Security, 2016, 11(12): 2818-2832. DOI: 10.1109/TIFS.2016.2599270.
Crossref Google Scholar
Journal of Computer Science and Technology
Volume 36 Issue 3,
May 2021
Pages 617-632
DOI: 10.1007/s11390-021-1033-5
Cite this article:
Huang Y-W, Yang G-P, Wang K-K, et al. Multi-Scale Deep Cascade Bi-Forest for Electrocardiogram Biometric Recognition. Journal of Computer Science and Technology, 2021, 36(3): 617-632. https://doi.org/10.1007/s11390-021-1033-5

418

Views

8

Crossref

7

Web of Science

8

Scopus

0

CSCD

Altmetrics
Received: 29 September 2020
Accepted: 02 March 2021
Published: 05 May 2021
©Institute of Computing Technology, Chinese Academy of Sciences 2021
Return