Personal and Ubiquitous Computing

, Volume 22, Issue 2, pp 275–287 | Cite as

SVM-based classification method to identify alcohol consumption using ECG and PPG monitoring

  • Wen-Fong Wang
  • Ching-Yu Yang
  • Yan-Fu Wu
Original Article


Driving under the influence (DUI) of alcohol (“drunk driving”) is dangerous and may cause serious harm to people and damage to property. To address this problem, this study developed a system for identifying excess alcohol consumption. Electrocardiogram (ECG) and photoplethysmography (PPG) sensors and intoxilyzers were used to acquire signals regarding the ECG, PPG, and alcohol consumption levels of participants before and after drinking. The signals were preprocessed, segmented, and subjected to feature extraction using specific algorithms to produce ECG and PPG training and test data. Based on the ECG, PPG, and alcohol consumption data we developed a fast and accurate identification scheme using the support vector machine (SVM) algorithm for identifying alcohol consumption. Optimized SVM classifiers were trained using the training data, and the test data were applied to verify the identification performance of the trained SVMs. The identification performance of the proposed classifiers achieved 95% on average. In this study, different feature combinations were tested to select the optimum technological configuration. Because the PPG and ECG features produce identical classification performance and the PPG features are more convenient to acquire, the technological configuration based on PPG is definitely preferable for developing smart and wearable devices for the identification of DUI.


Alcohol Wearable SVM ECG PPG 



The authors thank the National Science Council, Taiwan, for supporting this study under the contract NSC 100-2218-E-224-008-MY3, and the participants who assisted in the experiment.


  1. 1.
    Borkenstein R, Zylman R, Ziel W, Shumate R, Crowther R (1974) The role of the drinking driver in traffic accidents (the grand rapids study), 2nd edn. Indiana Univ., Center for Studies in Law in Action, Department of Forensic Studies.
  2. 2.
  3. 3.
    Sweedler B M, Biecheler M -B, Laurell H, Kroj G, Lerner M, Mathijssen M, Mayhew D, Tunbridge R (2004) Worldwide trends in alcohol and drug impaired driving. Traffic Inj Prev 5(3):175–184CrossRefGoogle Scholar
  4. 4.
    WHO et al (2007) Drinking and driving: a road safety manual for decision-makers and practitioners. Global Road Safety Partnership c/o International Federation of Red Cross and Red Crescent SocietiesGoogle Scholar
  5. 5.
    Malpas S C, Whiteside E A, Maling T J B (1991) Heart rate variability and cardiac autonomic function in men with chronic alcohol dependence. British Heart J 65(2):84–88CrossRefGoogle Scholar
  6. 6.
    Koskinen P, Virolainen J, Kupari M (1994) Acute alcohol intake decreases short-term heart rate variability in healthy subjects. Clin Sci 87(2):225–230CrossRefGoogle Scholar
  7. 7.
    Ryan J, Howes L (2002) Relations between alcohol consumption, heart rate, and heart rate variability in men. Heart 88(6):641–642CrossRefGoogle Scholar
  8. 8.
    Bau P F, Moraes R S, Bau C H, Ferlin E L, Rosito G A, Fuchs F D (2011) Acute ingestion of alcohol and cardiac autonomic modulation in healthy volunteers. Alcohol 45(2):123–129CrossRefGoogle Scholar
  9. 9.
    Carpeggiani C, Emdin M, Macerata A, Raciti M, Zanchi M, Bianchini S, Kraft G, Abbate A (2000) Heart rate variability modified by altitude exposure. In: Computers in cardiology 2000. IEEE, pp 817–820Google Scholar
  10. 10.
    Carpeggiani C, Erndin M, Macerata A, Raciti M, Zanchi M, Bianchini S, Abbate A (2001) Altitude distress influence on cardiac function. In: Computers in cardiology 2001. IEEE, pp 325–328Google Scholar
  11. 11.
    Alsafwah S (2001) Electrocardiographic changes in hypothermia. Heart & Lung: J Acute Crit Care 30(2):161–163CrossRefGoogle Scholar
  12. 12.
    Graham C A, McNaughton G W, Wyatt J P (2001) The electrocardiogram in hypothermia. Wilderness Environ Med 12(4):232–235CrossRefGoogle Scholar
  13. 13.
    Simoons M, Hugenholtz P (1975) Gradual changes of ecg waveform during and after exercise in normal subjects. Circulation 52(4):570–577CrossRefGoogle Scholar
  14. 14.
    Cai J, Liu G, Hao M (2009) The research on emotion recognition from ecg signal. In: International conference on information technology and computer science, 2009 (ITCS 2009), vol 1. IEEE, pp 497–500Google Scholar
  15. 15.
    Xianhai G (2011) Study of emotion recognition based on electrocardiogram and rbf neural network. Procedia Eng 15:2408–2412CrossRefGoogle Scholar
  16. 16.
    Karlen W, Mattiussi C, Floreano D (2009) Sleep and wake classification with ecg and respiratory effort signals. IEEE Trans Biomed Circ Syst 3(2):71–78CrossRefGoogle Scholar
  17. 17.
    Allen J (2007) Photoplethysmography and its application in clinical physiological measurement. Physiol Measur 28(3):R1. CrossRefGoogle Scholar
  18. 18.
    Wu C K, Tsang KF, Chi H R, Hung F H (2016) A precise drunk driving detection using weighted kernel based on electrocardiogram. Sensors 16(5):659. CrossRefGoogle Scholar
  19. 19.
    Intoximeters Alco-Sensor IV IntoximetersGoogle Scholar
  20. 20.
    ADInstruments, Gp amp owner’s guide (2008).
  21. 21.
    ADInstruments, Bio amp owner’s guide (2009).
  22. 22.
    ADInstruments, Powerlab /30 series owner’s guide (2009).
  23. 23.
    Page R (2005) Twelve-lead ECG for acute and critical care providers, EKG Series. Pearson Prentice Hall.
  24. 24.
    Friesen G M, Jannett T C, Jadallah M A, Yates S L, Quint S R, Nagle H T (1990) A comparison of the noise sensitivity of nine qrs detection algorithms. IEEE Trans Biomed Eng 37(1):85–98CrossRefGoogle Scholar
  25. 25.
    Electronics Hub (2015) Butterworth filter Available at
  26. 26.
    Lee H, Lee J, Jung W, Lee G -K (2007) The periodic moving average filter for removing motion artifacts from ppg signals. Int J Control Autom Syst 5(6):701–706Google Scholar
  27. 27.
    Warner A (1998) Drug abuse handbook. Clin Chem 44(7):1586– 1586. Google Scholar
  28. 28.
    Stöckl D, Dewitte K, Thienpont L M (1998) Validity of linear regression in method comparison studies: is it limited by the statistical model or the quality of the analytical input data? Clin Chem 44 (11):2340–2346. Google Scholar
  29. 29.
    Jones A W The relationship between blood alcohol concentration (BAC) and breath alcohol concentration (BrAC): a review of the evidence, Road Safety Web Publication 15Google Scholar
  30. 30.
    Searle J (2015) Alcohol calculations and their uncertainty. Med Sci Law 55(1):58–64. pMID: 24644224. doi: 10.1177/0025802414524385
  31. 31.
    Allen J, Columbus M (1997) Assessing alcohol problems: a guide for clinicians and researchers, NIAAA treatment handbook series 4, Diane Pub.
  32. 32.
    Sereny G (1971) Effects of alcohol on the electrocardiogram. Circulation 44:558–564. doi: 10.1161/01.CIR.44.4.558 CrossRefGoogle Scholar
  33. 33.
    He X, Goubran R A, Liu X P (2013) Evaluation of the correlation between blood pressure and pulse transit time. In: IEEE International symposium on medical measurements and applications proceedings (MeMeA 2013). IEEE, pp 17–20Google Scholar
  34. 34.
    Li C, Zheng C, Tai C (1995) Detection of ecg characteristic points using wavelet transforms. IEEE Trans Biomed Eng 45:21–28Google Scholar
  35. 35.
    Legarreta I R, Addison P S, Reed M J, Grubb N, Clegg G R, Robertson C E, Watson J N (2005) Continuous wavelet transform modulus maxima analysis of the electrocardiogram: beat characterisation and beat-to-beat measurement. Int J Wavelets, Multiresolution Inf Process 03(01):19–42. doi: 10.1142/S0219691305000774 CrossRefzbMATHGoogle Scholar
  36. 36.
    Chavan M S, Agarwala R, Uplane M (2006) Use of kaiser window for ecg processing. In: Proceedings of the 5th WSEAS international conference on signal processing, robotics and automation. World Scientific and Engineering Academy and Society (WSEAS), pp 285–289Google Scholar
  37. 37.
    Cubbon R M, Ruff N, Groves D, Eleuteri A, Denby C, Kearney L, Ali N, Walker A M N, Jamil H, Gierula J, Gale C P, Batin P D, Nolan J, Shah A M, Fox K A A, Sapsford R J, Witte K K, Kearney M T (2016) Ambulatory heart rate range predicts mode-specific mortality and hospitalisation in chronic heart failure. Heart 102(3): 223–229CrossRefGoogle Scholar
  38. 38.
    Cortes C, Vapnik V (1995) Support-vector networks. Mach Learn 20(3):273–297zbMATHGoogle Scholar
  39. 39.
    Chang C-C, Lin C-J (2011) Libsvm: a library for support vector machines. ACM Trans Intell Syst Technol (TIST) 2(3):27:1–27:27Google Scholar

Copyright information

© Springer-Verlag London Ltd. 2017

Authors and Affiliations

  1. 1.Department of CSIENational Yunlin University of Science & TechnologyDouliuTaiwan
  2. 2.Department of CSIENational Penghu University of Science & TechnologyMakungTaiwan

Personalised recommendations