Journal of Medical and Biological Engineering

, Volume 35, Issue 6, pp 735–748 | Cite as

Non-invasive Multi-modal Human Identification System Combining ECG, GSR, and Airflow Biosignals

  • Carmen CamaraEmail author
  • Pedro Peris-Lopez
  • Juan E. Tapiador
  • Guillermo Suarez-Tangil
Original Article


A huge amount of data can be collected through a wide variety of sensor technologies. Data mining techniques are often useful for the analysis of gathered data. This paper studies the use of three wearable sensors that monitor the electrocardiogram, airflow, and galvanic skin response of a subject with the purpose of designing an efficient multi-modal human identification system. The proposed system, based on the rotation forest ensemble algorithm, offers a high accuracy (99.6 % true acceptance rate and just 0.1 % false positive rate). For its evaluation, the proposed system was testing against the characteristics commonly demanded in a biometric system, including universality, uniqueness, permanence, and acceptance. Finally, a proof-of-concept implementation of the system is demonstrated on a smartphone and its performance is evaluated in terms of processing speed and power consumption. The identification of a sample is extremely efficient, taking around 200 ms and consuming just a few millijoules. It is thus feasible to use the proposed system on a regular smartphone for user identification.


Sensor data Bioinformatics Human identification Data mining Ensemble classification 



This work was supported by MINECO grant TIN2013- 46469-R (SPINY: Security and Privacy in the Internet of You) and CAM grant S2013/ICE-3095 (CIBERDINE: Cybersecurity, Data, and Risks).


  1. 1.
    Banaee, H., Ahmed, M. U., & Loutfi, A. (2013). Data mining for wearable sensors in health monitoring systems: A review of recent trends and challenges. Sensors, 13, 17472–17500.CrossRefGoogle Scholar
  2. 2.
    Rostami, M., Juels, A., & Koushanfar, F. (2013). Heart-to-heart (H2H): authentication for implanted medical devices. In Proceedings of the ACM SIGSAC conference on computer & communications security (pp. 1099–1112).Google Scholar
  3. 3.
    Rasmussen, K. B., Roeschlin, M., Martinovic, I., & Tsudik, G. (2014). Authentication using pulse-response biometrics. In Proceedings of the network and distributed system security symposium (NDSS).Google Scholar
  4. 4.
    Eng, A., & Wahsheh, L. (2013). Look into my eyes: A survey of biometric security. In Proceedings of the tenth international conference on information technology: New generations (pp. 422–427).Google Scholar
  5. 5.
    Odinaka, I., Po-Hsiang, L., Kaplan, A. D., O’Sullivan, J. A., Sirevaag, E. J., & Rohrbaugh, J. W. (2012). ECG biometric recognition: A comparative analysis. IEEE Transactions on Information Forensics and Security, 7, 1812–1824.CrossRefGoogle Scholar
  6. 6.
    Khalifa, W., Salem, A., Roushdy, M., & Revett, K. (2012). A survey of EEG based user authentication schemes. In Proceedings of the 8th international conference on informatics and systems (pp. BIO-55–BIO-60).Google Scholar
  7. 7.
    Spachos, P., Gao, J., & Hatzinakos, D. (2011).Feasibility study of photoplethysmographic signals for biometric identification. In Proceedings of the 17th international conference on digital signal processing (DSP) (pp. 1–5).Google Scholar
  8. 8.
    Ichino, M., Sakano, H., & Komatsu, N. (2006). Multimodal biometrics of lip movements and voice using kernel fisher discriminant analysis. In Proceedings of the international conference on control, automation, robotics and vision (pp. 1–6).Google Scholar
  9. 9.
    Jani, R., & Agrawal, N. (2013). Proposed framework for enhancing security in fingerprint and finger-vein multimodal biometric recognition. In Proceedings of the international conference on machine intelligence and research advancement (pp. 440–444).Google Scholar
  10. 10.
    Revett, K., Deravi, F., & Sirlantzis, K. (2010). Biosignals for user authentication—Towards cognitive biometrics. In Proceedings of the international conference on emerging security technologies (EST) (pp. 71–76).Google Scholar
  11. 11.
    Riera, A., Dunne, S., Cester, I., & Ruffini, G. (2008). STARFAST: A wireless wearable EEG/ECG biometric system based on the ENOBIO Sensor. In Proceedings of the international workshop on wearable micro and nanosystems for personalised health (pp. 1–4).Google Scholar
  12. 12.
    Simon, B. P., & Eswaran, C. (1997). An ECG classifier de- signed using modified decision based neural networks. Computer and Biomedical Research, 30, 257–272.CrossRefGoogle Scholar
  13. 13.
    Doorly, D. J., Taylor, D. J., & Schroter, R. C. (2008). Mechanics of airflow in the human nasal airways. Respiratory Physiology & Neurobiology, 163, 100–110.CrossRefGoogle Scholar
  14. 14.
    Chaaban, M., & Corey, J. P. (2011). Assessing Nasal Air Flow. Proceedings of the American Thoracic Society, 8, 70–78.CrossRefGoogle Scholar
  15. 15.
    Ogorevc, J., Gersak, G., Novak, D., & Drnovsek, J. (2013). Metrological evaluation of skin conductance measurements. Measurement, 46, 2993–3001.CrossRefGoogle Scholar
  16. 16.
    Clifford, G. D., Azuaje, F., & McSharry, P. (2006). Advanced methods and tools for ECG data analysis. Norwood, MA: Artech House Inc.Google Scholar
  17. 17.
    Abellán, J., & Mantas, C. J. (2014). Improving experimental studies about ensembles of classifiers for bankruptcy prediction and credit scoring. Expert Systems with Applications, 41, 3825–3830.CrossRefGoogle Scholar
  18. 18.
    Rahman, A., & Verma, B. (2013). Effect of ensemble classifier composition on offline cursive character recognition. Information Processing and Management, 49, 852–864.CrossRefGoogle Scholar
  19. 19.
    Ozçift, A. (2011). Random forests ensemble classifier trained with data resampling strategy to improve cardiac arrhythmia diagnosis. Computers in Biology and Medicine, 41, 265–271.CrossRefGoogle Scholar
  20. 20.
    Yin, X. C., Huang, K., Hao, H. W., Iqbal, K., & Wang, Z. B. (2014). A novel classifier ensemble method with sparsity and diversity. Neurocomputing, 134, 214–221.CrossRefGoogle Scholar
  21. 21.
    Breiman, L. (1996). Bagging predictors. Machine Learning, 24, 123–140.zbMATHMathSciNetGoogle Scholar
  22. 22.
    Freund, Y., & Schapire, R. E. (1997). A decision-theoretic generalization of on-line learning and an application to boosting. Journal of Computer and System Sciences, 55, 119–139.zbMATHMathSciNetCrossRefGoogle Scholar
  23. 23.
    Cao, Y., Miao, Q. G., Liu, J. C., & Gao, L. (2013). Advance and prospects of adaboost algorithm. Acta Automatica Sinica, 39, 745–758.CrossRefGoogle Scholar
  24. 24.
    Brown, G., Wyatt, J. L., Harris, R., & Yao, X. (2005). Diversity creation methods: A survey and categorization. Information Fusion, 6, 5–20.CrossRefGoogle Scholar
  25. 25.
    Rokach, L. (2010). Pattern Classification Using Ensemble Methods. River Edge: World Scientific.zbMATHGoogle Scholar
  26. 26.
    Rodriguez, J. J., Kuncheva, L. I., & Alonso, C. J. (2006). Rotation forest: A new classifier ensemble method. IEEE Transactions on Pattern Analysis and Machine Intelligence, 28, 1619–1630.CrossRefGoogle Scholar
  27. 27.
    Pal, S., & Mitra, M. (2011). ECG based biometric authentication: a novel data modeling approach. In Proceedings of the international conference on image information processing (ICIIP) (pp. 1–4).Google Scholar
  28. 28.
    Singh, Y., & Singh, S. (2012). Evaluation of electrocardiogram for biometric authentication. Journal of Information Security, 3, 39–48.CrossRefGoogle Scholar
  29. 29.
    Shen, T. W., Tompkins, W. J., & Hu, Y. H. (2002). One-lead ECG for identity verification. In Proceedings of the 24th annual conference and the annual fall meeting of the biomedical engineering society EMBS/BMES conference (Vol. 1, pp. 62–63).Google Scholar
  30. 30.
    Anderson, C. W., & Bratman, J. A. (2008). Translating thoughts into actions by finding patterns in brainwaves. In Proceedings of the fourteenth Yale workshop on adaptive and learning systems (pp. 1–6).Google Scholar
  31. 31.
    Carmona, N., Rua-Seoane, J., Elorza, J., Saenz de Pipaon, E., Palacios, C., & Bragard, J. (2013). Aging of ECG characteristics over a five year period. In Proceedings of the conference on computing in cardiology (CinC) (pp. 1031–1034).Google Scholar
  32. 32.
  33. 33.
    Singh, Y. N., Singh, S. K., & Ray, A. K. (2012). Bioelectrical Signals as emerging biometrics: Issues and challenges. ISRN Signal Processing, 2012, 1–13.CrossRefGoogle Scholar
  34. 34.
    Tantawi, M. M., Revett, K., Tolba, M. F., & Salem, A. (2012). On the use of the electrocardiogram for biometric authentication. In Proceedings of the 8th international conference on informatics and systems (pp. BIO-48–BIO-54).Google Scholar
  35. 35.
    Suarez-Tangil, G., Tapiador, J. E., Peris-Lopez, P., & Pastrana, S. (2015). Power-aware anomaly detection in smartphones: An analysis of on-platform versus externalized operation. Pervasive and Mobile Computing, 18, 137–151.CrossRefGoogle Scholar
  36. 36.
    Yoon, C., Kim, D., Jung, W., Kang, C., & Cha, H. (2012). Appscope: Application energy metering framework for android smartphone using kernel activity monitoring. In Proceedings of the USENIX annual technical conference (p. 36).Google Scholar
  37. 37.
    Jung, W., Kang, C., Yoon, C., Kim, D., & Cha, H. (2012). DevScope: A nonintrusive and online power analysis tool for smartphone hardware components. In Proceedings of the eighth IEEE/ACM/IFIP international conference on Hardware/software codesign and system synthesis (pp. 353–362).Google Scholar

Copyright information

© Taiwanese Society of Biomedical Engineering 2015

Authors and Affiliations

  • Carmen Camara
    • 1
    Email author
  • Pedro Peris-Lopez
    • 1
  • Juan E. Tapiador
    • 1
  • Guillermo Suarez-Tangil
    • 1
  1. 1.Department of Computer ScienceCarlos III University of Madrid (UC3 M)LeganésSpain

Personalised recommendations