Sex Recognition through ECG Signals aiming toward Smartphone Authentication
Source abstract
Abstract
Physiological signals are strongly related to a person’s state of health and carry information about the human body. For example, by ECG, it is possible to obtain information about cardiac disease, emotions, personal identification, and the sex of a person, among others. This paper proposes the study of the heartbeat from a soft-biometric perspective to be applied to smartphone unlocking services. We employ the user heartbeat to classify the individual by sex (male, female) with the use of Deep Learning, reaching an accuracy of 94.4% ± 2.0%. This result was obtained with the RGB representation of the union of the time-frequency transformation from the pseudo-orthogonal X, Y, and Z bipolar signals. Evaluating each bipolar contribution, we found that the XYZ combination provides the best category distinction using GoogLeNet. The 24-h Holter database of the study contains 202 subjects with a female size of 49.5%. We propose an architecture for managing this signal that allows the use of a few samples to train the network. Due to the hidden nature of ECG, it does not present vulnerabilities like public trait exposition, light/noise sensibility, or learnability compared to fingerprint, facial, voice, or password verification methods. ECG may complement those gaps en route to a cooperative authentication ecosystem.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: ECG Monitoring and Analysis · EEG and Brain-Computer Interfaces · Emotion and Mood Recognition
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Telecommunications, Faculty of Engineering, Fundación Universitaria Compensar, Bogota 111311, Colombia
Department of Electronics, Faculty of Engineering, Pontificia Universidad Javeriana, Bogota 110231, Colombia
Funding
Fundacion Universitaria Compensar, the Colombian Ministry for the Information and Communications Technology · Colombian Administrative Department of Science, Technology and Innovation
References (54)
Show source-provided references
1. Automatic ECG-Based Emotion Recognition in Music Listening10.1109/TAFFC.2017.2781732 ↗
2. Age and Sex Estimation Using Artificial Intelligence From Standard 12-Lead ECGs10.1161/CIRCEP.119.007284 ↗
3. Cabra, J.L., Mendez, D., and Trujillo, L.C. (2018, January 16–18). Wide Machine Learning Algorithms Evaluation Applied to ECG Authentication and Gender Recognition. Proceedings of the 2nd International Conference on Biometric Engineering and Applications (ICBEA), Amsterdam, The Netherlands.10.1145/3230820.3230830 ↗
4. Misclassification of sex by deep neural networks reveals novel ECG characteristics that explain a higher risk of mortality in women and in men10.1093/eurheartj/ehab724.3162 ↗
5. Nguyen, D.T., Kim, K.W., Hong, H.G., Koo, J.H., Kim, M.C., and Park, K.R. (2017). Gender Recognition from Human-Body Images Using Visible-Light and Thermal Camera Videos Based on a Convolutional Neural Network for Image Feature Extraction. Sensors, 17.10.3390/s17030637 ↗
6. Ghildiyal, A., Sharma, S., Verma, I., and Marhatta, U. (2020, January 3–5). Age and Gender Predictions using Artificial Intelligence Algorithm. Proceedings of the 3rd International Conference on Intelligent Sustainable Systems (ICISS’20), Thoothukudi, India.10.1109/ICISS49785.2020.9316053 ↗
7. Gender recognition using optimal gait feature based on recursive feature elimination in normal walking10.1016/j.eswa.2021.116040 ↗
8. DGR: Gender Recognition of Human Speech Using One-Dimensional Conventional Neural Network
9. Gender identification on Twitter10.1002/asi.24541 ↗
10. Tsimperidis, I., Yucel, C., and Katos, V. (2021). Age and Gender as Cyber Attribution Features in Keystroke Dynamic-Based User Classification Processes. Electronics, 10.10.3390/electronics10070835 ↗
11. Bayer (2022, April 28). Las Enfermedades Cardiovasculares son la Primera Causa de Muerte en Colombia y el Mundo. Available online: https://www.bayer.com/es/co/las-enfermedades-cardiovasculares-son-la-primera-causa-de-muerte-en-colombia-y-el-mundo.
12. Centers for Disease Control and Prevention (2022, April 28). Heart Disease Facts, Available online: https://www.cdc.gov/heartdisease/facts.htm.
13. Publishing, H.H. (2022, April 28). The Heart Attack Gender Gap. Available online: https://www.health.harvard.edu/heart-health/the-heart-attack-gender-gap.
14. Health, H. (2022, April 28). Throughout Life, Heart Attacks are Twice as Common in Men than Women–Harvard Health. Available online: https://www.health.harvard.edu/heart-health/throughout-life-heart-attacks-are-twice-as-common-in-men-than-women.
15. Lifelong Gender Gap in Risk of Incident Myocardial Infarction: The Tromsø Study10.1001/jamainternmed.2016.5451 ↗
16. Cho, L. (2022, April 28). Women or Men—Who Has a Higher Risk of Heart Attack?. Available online: https://health.clevelandclinic.org/women-men-higher-risk-heart-attack/.
17. Gender Related Differences in Electrocardiographic Parameters and Their Association with Cardiac Events in Patients After Myocardial Infarction10.1016/j.amjcard.2007.07.077 ↗
18. Gender differences in the dynamics of terminal T wave intervals10.1111/j.1540-8159.2004.00526.x ↗
19. Ergin, S., Uysal, A.K., Gunal, E.S., Gunal, S., and Gulmezoglu, M.B. (2014, January 18–21). ECG based biometric authentication using ensemble of features. Proceedings of the 9th Iberian Conference on Information Systems and Technologies (CISTI’14), Barcelona, Spain.10.1109/CISTI.2014.6877089 ↗
20. Evolution, Current Challenges, and Future Possibilities in ECG Biometrics10.1109/ACCESS.2018.2849870 ↗
21. Jain, A.K., Nandakumar, K., Lu, X., and Park, U. (2004, January 15). Integrating Faces, Fingerprints, and Soft Biometric Traits for User Recognition. Proceedings of the 2nd Biometric Authentication ECCV International Workshop (BioAW’04), Prague, Czech Republic.10.1007/978-3-540-25976-3_24 ↗
22. Ceci, M., Japkowicz, N., Liu, J., Papadopoulos, G.A., and Raś, Z.W. (2018, January 29–31). Foundations of Intelligent Systems. Proceedings of the 24th International Symposium, ISMIS 2018, Limassol, Cyprus.10.1007/978-3-030-01851-1 ↗
23. MasterPrint: Exploring the Vulnerability of Partial Fingerprint-Based Authentication Systems10.1109/TIFS.2017.2691658 ↗
24. Winder, D. (2022, June 15). Hackers Claim ‘Any’ Smartphone Fingerprint Lock Can be Broken in 20 Minutes. Available online: https://www.forbes.com/sites/daveywinder/2019/11/02/smartphone-security-alert-as-hackers-claim-any-fingerprint-lock-broken-in-20-minutes/?sh=2ca0734f6853.
25. Mott, N. (2022, June 15). Hacking Fingerprints Is Actually Pretty Easy—And Cheap. Available online: https://www.pcmag.com/news/hacking-fingerprints-is-actually-pretty-easy-and-cheap.
26. Winder, D. (2022, June 15). Apple’s iPhone FaceID Hacked In Less Than 120 Seconds. Available online: https://www.forbes.com/sites/daveywinder/2019/08/10/apples-iphone-faceid-hacked-in-less-than-120-seconds/?sh=349627621bc3.
27. Pato, J., and Millett, L. (2010). Biometric Recognition: Challenges and Opportunities, The National Academies Press. [1st ed.].
28. Atkielski, A. (2022, June 25). Schematic Diagram of Normal Sinus Rhythm for a Human Heart as Seen on ECG. Available online: https://commons.wikimedia.org/wiki/File:SinusRhythmLabels-es.svg.
29. İzci, E., Değirmenci, M., Özdemir, M.A., and Akan, A. (2020, January 5–7). ECG Arrhythmia Detection with Deep Learning. Proceedings of the 28th IEEE Signal Processing and Communications Applications (SIU), Gaziantep, Turkey.10.1109/SIU49456.2020.9302219 ↗
30. An Ensemble of Deep Learning-Based Multi-Model for ECG Heartbeats Arrhythmia Classification10.1109/ACCESS.2021.3098986 ↗
31. ECG Heartbeat Classification Using Multimodal Fusion10.1109/ACCESS.2021.3097614 ↗
32. Inter-Patient ECG Classification With Symbolic Representations and Multi-Perspective Convolutional Neural Networks10.1109/JBHI.2019.2942938 ↗
33. A review on deep learning methods for ECG arrhythmia classification
34. Sleep Apnea Detection From Single-Lead ECG: A Comprehensive Analysis of Machine Learning and Deep Learning Algorithms
35. End-to-End Deep Learning Architecture for Separating Maternal and Fetal ECGs Using W-Net10.1109/ACCESS.2022.3166925 ↗
36. Short-Term Nacelle Orientation Forecasting Using Bilinear Transformation and ICEEMDAN Framework10.3389/fenrg.2021.780928 ↗
37. Monitoring and Identifying Wind Turbine Generator Bearing Faults Using Deep Belief Network and EWMA Control Charts10.3389/fenrg.2021.799039 ↗
38. Gajare, A., and Dey, H. (2021, January 18–20). MATLAB-based ECG R-peak Detection and Signal Classification using Deep Learning Approach. Proceedings of the 3rd IEEE Bombay Section Signature Conference (IBSSC), Gwalior, India.10.1109/IBSSC53889.2021.9673301 ↗
39. QRS Complex Detection Using Novel Deep Learning Neural Networks10.1109/ACCESS.2020.2997473 ↗
40. Sequence to Sequence ECG Cardiac Rhythm Classification Using Convolutional Recurrent Neural Networks10.1109/JBHI.2021.3098662 ↗
41. A Novel Approach for ECG-Based Human Identification Using Spectral Correlation and Deep Learning10.1109/TBIOM.2019.2947434 ↗
42. A Comprehensive Survey on ECG Signals as New Biometric Modality for Human Authentication: Recent Advances and Future Challenges10.1109/ACCESS.2021.3095248 ↗
43. Deep Learning for ECG Analysis: Benchmarks and Insights from PTB-XL10.1109/JBHI.2020.3022989 ↗
44. Deep neural networks reveal novel sex-specific electrocardiographic features relevant for mortality risk
45. Chen, T., Kornblith, S., Norouzi, M., and Hinton, G. (2020, January 12–18). A Simple Framework for Contrastive Learning of Visual Representations. Proceedings of the 37th International Conference on Machine Learning (ICML’20), Vienna, Austria.
46. Diamant, N., Reinertsen, E., Song, S., Aguirre, A.D., Stultz, C.M., and Batra, P. (2022). Patient contrastive learning: A performant, expressive, and practical approach to electrocardiogram modeling. PLoS Comput. Biol., 18.10.1371/journal.pcbi.1009862 ↗
47. Symmetric Projection Attractor Reconstruction: Sex Differences in the ECG10.3389/fcvm.2021.709457 ↗
48. brgfx (2022, June 18). Telemetric and ECG Holter Warehouse Project. Available online: http://thew-project.org/Database/E-HOL-03-0202-003.html.
49. brgfx (2022, June 18). Vector de Cuerpo Humano Creado por Brgfx - www.freepik.es. Available online: https://www.freepik.es/vectores/cuerpo-humano.
50. Padsalgikar, A. (2017). Plastics in Medical Devices for Cardiovascular Applications. A Volume in Plastics Design Library, Elsevier. [1st ed.].10.1016/B978-0-323-35885-9.00002-3 ↗
51. ECG Authentication for Mobile Devices10.1109/TIM.2015.2503863 ↗
52. Wiggers, K. (2021, October 28). AliveCor Raises $65 Million to Detect Heart Problems with AI. Available online: https://venturebeat.com/2020/11/16/alivecor-raises-65-million-to-detect-heart-problems-with-ai/.
53. CardioID (2021, October 28). Every Heart Has a Beat, But the Way We Use it is Unique! 2016. Available online: https://www.cardio-id.com/.
54. Nymi (2021, October 28). Nymi Workplace Wearables. Available online: https://www.nymi.com/nymi-band.