http://iet.metastore.ingenta.com
1887

Importance of subject-dependent classification and imbalanced distributions in driver sleepiness detection in realistic conditions

Importance of subject-dependent classification and imbalanced distributions in driver sleepiness detection in realistic conditions

For access to this article, please select a purchase option:

Buy eFirst article PDF
£12.50
(plus tax if applicable)
Buy Knowledge Pack
10 articles for £75.00
(plus taxes if applicable)

IET members benefit from discounts to all IET publications and free access to E&T Magazine. If you are an IET member, log in to your account and the discounts will automatically be applied.

Learn more about IET membership 

Recommend Title Publication to library

You must fill out fields marked with: *

Librarian details
Name:*
Email:*
Your details
Name:*
Email:*
Department:*
Why are you recommending this title?
Select reason:
 
 
 
 
 
IET Intelligent Transport Systems — Recommend this title to your library

Thank you

Your recommendation has been sent to your librarian.

The first in-depth study on the use of electrocardiogram and electrooculogram for subject-dependent classification in driver sleepiness/fatigue under realistic driving conditions is presented in this work. Since acquisitions in simulated environments may be misleading for sleepiness assessment, performing studies on road are required. For that purpose, the authors present a database resulting from a field driving study performed in the SleepEye project. Based on previous research, supervised machine learning methods are implemented and applied to 16 heart- and 25 eye-based extracted features, mostly related to heart rate variability and blink events, respectively, in order to study the influence of subject dependency in sleepiness classification, using different classifiers and dealing with imbalanced class distributions. Results showed a significantly worse performance in subject-independent classification: a decrease of ∼40 and 20% in the detection rate of the ‘sleepy’ class for two and three classes, respectively. Since physiological signals are the ones that present the most individual characteristics, a subject-independent classification can be even harder to perform. Transfer learning techniques and methods for imbalanced distributions are promising approaches and need further investigation.

References

    1. 1)
      • 1. World Health Organization: ‘Global status report on road safety’ (WHO, Geneva, Switzerland, 2015).
    2. 2)
      • 2. The Royal Society for the Prevention of Accidents: ‘Road accidents: a literature review and position paper’ (RoSPA, Birmingham, UK, 2001).
    3. 3)
      • 3. National Highway Traffic Safety Administration: ‘Traffic safety facts: a compilation of motor vehicle crash data from the fatality analysis reporting system and the general estimates system’ (National Highway Traffic Safety Administration, Washington, DC, USA, 2014).
    4. 4)
      • 4. National Highway Traffic Safety Administration: ‘Traffic safety facts: a brief statistical summary. Drowsy driving’ (National Highway Traffic Safety Administration, Washington, DC, USA, 2011).
    5. 5)
      • 5. Sahayadhas, A., Sundaraj, K., Murugappan, M.: ‘Detecting driver drowsiness based on sensors: a review’, Sensors, 2012, 12, (12), pp. 1693716953.
    6. 6)
      • 6. Yu, X.: ‘Real-time nonintrusive detection of driver drowsiness’ (University of Minnesota Center for Transportation Studies, Minneapolis, MN, USA, 2009).
    7. 7)
      • 7. Brown, I.: ‘Driver fatigue’, Hum. Factors, J. Hum. Factors Ergon. Soc., 1994, 36, (2), pp. 298314.
    8. 8)
      • 8. Wang, M., Jeong, N., Kim, K., et al: ‘Drowsy behavior detection based on driving information’, Int. J. Autom. Technol., 2016, 17, (1), pp. 165173.
    9. 9)
      • 9. Wu, Q., Zhao, Y., Bi, X.: ‘Driving fatigue classified analysis based on ECG signal’. Fifth Int. Symp. on Computational Intelligence and Design, Hangzhou, China, 2012, vol. 2, pp. 544547.
    10. 10)
      • 10. Vicente, J., Laguna, P., Bartra, A., et al: ‘Drowsiness detection using heart rate variability’, Med. Biol. Eng. Comput., 2016, 54, (6), pp. 111.
    11. 11)
      • 11. Rodríguez-Ibáñez, N., García-González, M. A., Fernández-Chimeno, M., et al: ‘Drowsiness detection by thoracic effort signal analysis with professional drivers in real environments’. Annual Int. Conf. of the IEEE Engineering in Medicine and Biology Society, EMBC, Boston, MA, USA, August 2011, pp. 125.
    12. 12)
      • 12. Yu, X.B.: ‘Non-contact driver drowsiness detection system’, Safety IDEA Project 17, 2012.
    13. 13)
      • 13. Lenné, M.G., Jacobs, E.E.: ‘Predicting drowsiness-related driving events: a review of recent research methods and future opportunities’, Theor. Issues Ergon. Sci., 2016, 17, (5–6), pp. 533553.
    14. 14)
      • 14. Hallvig, D., Anund, A., Fors, C., et al: ‘Sleepy driving on the real road and in the simulator – a comparison’, Accident Anal. Prev., 2013, 50, pp. 4450.
    15. 15)
      • 15. Vicente, J., Laguna, P., Bartra, A., et al: ‘Detection of driver's drowsiness by means of HRV analysis’. IEEE Computing in Cardiology, Hangzhou, China, 2011, pp. 8992.
    16. 16)
      • 16. Wang, J.S., Chung, P.C., Wang, W.H., et al: ‘Driving conditions recognition using heart rate variability indexes’. IEEE Sixth Int. Conf. on Intelligent Information Hiding and Multimedia Signal Processing, Darmstadt, Germany, 2010, pp. 389392.
    17. 17)
      • 17. Gupta, N.: ‘ECG and wearable computing for drowsiness detection’. PhD thesis, California State University, Northridge, 2014.
    18. 18)
      • 18. Rigas, G., Goletsis, Y., Bougia, P., et al: ‘Towards driver's state recognition on real driving conditions’, Int. J. Veh. Technol., 2011, 2011, pp. 114.
    19. 19)
      • 19. Mårtensson, H., Keelan, O., Ahlström, C.: ‘Driver sleepiness classification based on physiological data and driving performance from real road driving’, IEEE Trans. Intell. Transp. Syst., 2018, pp. 110, DOI: 10.1109/TITS.2018.2814207.
    20. 20)
      • 20. Healey, J.A., Picard, R.W.: ‘Detecting stress during real-world driving tasks using physiological sensors’, IEEE Trans. Intell. Transp. Syst., 2005, 6, (2), pp. 156166.
    21. 21)
      • 21. Miyaji, M.: ‘Method of drowsy state detection for driver monitoring function’, Int. J. Inf. Electron. Eng., 2014, 4, (4), pp. 264268.
    22. 22)
      • 22. Begum, S., Ahmed, M.U., Funk, P., et al: ‘Mental state monitoring system for the professional drivers based on heart rate variability analysis and case-based reasoning’. Computer Science and Information Systems, Wroclaw, Poland, 2012, pp. 3542.
    23. 23)
      • 23. Jung, S.J., Shin, H.S., Chung, W.Y.: ‘Driver fatigue and drowsiness monitoring system with embedded electrocardiogram sensor on steering wheel’, IET Intell. Transp. Syst., 2014, 8, (1), pp. 4350.
    24. 24)
      • 24. Patel, M., Lal, S., Kavanagh, D., et al: ‘Applying neural network analysis on heart rate variability data to assess driver fatigue’, Expert Syst. Appl., 2011, 38, (6), pp. 72357242.
    25. 25)
      • 25. Murata, A.M., Hiramatsu, Y.: ‘Evaluation of drowsiness by HRV measures – basic study for drowsy driver detection’. Fourth Int. Workshop on Computational Intelligence & Applications, Hiroshima, Japan, 2008.
    26. 26)
      • 26. Roy, R., Venkatasubramanian, K.: ‘EKG/ECG based driver alert system for long haul drive’, Indian J. Sci. Technol., 2015, 8, (19).
    27. 27)
      • 27. Camm, A.J., Malik, M., Bigger, J., et al: ‘Heart rate variability: standards of measurement, physiological interpretation and clinical use. Task force of the European society of cardiology and the north American society of pacing and electrophysiology’, Circulation, 1996, 93, (5), pp. 10431065.
    28. 28)
      • 28. Khushaba, R.N., Kodagoda, S., Lal, S., et al: ‘Driver drowsiness classification using fuzzy wavelet-packet-based feature-extraction algorithm’, IEEE Trans. Biomed. Eng., 2011, 58, (1), pp. 121131.
    29. 29)
      • 29. Shinar, Z., Akselrod, S., Dagan, Y., et al: ‘Autonomic changes during wake-sleep transition: a heart rate variability based approach’, Auton. Neurosci., 2006, 130, (1), pp. 1727.
    30. 30)
      • 30. Awais, M., Badruddin, N., Drieberg, M.: ‘A non-invasive approach to detect drowsiness in a monotonous driving environment’. TENCON 2014 IEEE Region 10 Conf., Bangkok, Thailand, 2014, pp. 14.
    31. 31)
      • 31. Jammes, B., Sharabty, H., Esteve, D.: ‘Automatic EOG analysis: a first step toward automatic drowsiness scoring during wake-sleep transitions’, Somnologie-Schlafforschung Schlafmedizin, 2008, 12, (3), pp. 227232.
    32. 32)
      • 32. Yue, C.: ‘EOG signals in drowsiness research’. PhD thesis, Linköping University, 2011.
    33. 33)
      • 33. Ebrahim, P.: ‘Driver drowsiness monitoring using eye movement features derived from electrooculography’. PhD thesis, University of Stuttgart, 2016.
    34. 34)
      • 34. Rodríguez-Ibáñez, N., Meca-Calderón, P., García-González, M. A., et al: ‘Drowsiness detection by electrooculogram signal analysis in driving simulator conditions for gold standard signal generation’. Proc. of the Int. Conf. on Biomedical Electronics and Devices, Vilamoura, Portugal, 2013, vol. 1, pp. 5763.
    35. 35)
      • 35. Pettersson, K., Jagadeesan, S., Lukander, K., et al: ‘Algorithm for automatic analysis of electro-oculographic data’, Biomed. Eng., 2013, 12, (1), p. 110.
    36. 36)
      • 36. Gao, X.Y., Zhang, Y.F., Zheng, W.L., et al: ‘Evaluating driving fatigue detection algorithms using eye tracking glasses’. 7th Int. IEEE/EMBS Conf. on Neural Engineering, Montpellier, France, 2015, pp. 767770.
    37. 37)
      • 37. Hu, S., Zheng, G.: ‘Driver drowsiness detection with eyelid related parameters by support vector machine’, Expert Syst. Appl., 2009, 36, (4), pp. 76517658.
    38. 38)
      • 38. Lal, S., Craig, A.: ‘A critical review of the psychophysiology of driver fatigue’, Biol. Psychol., 2001, 55, (3), pp. 173194.
    39. 39)
      • 39. Lee, M.L., Howard, M.E., Horrey, W., et al: ‘High risk of near-crash driving events following night-shift work’, Proc. Natl. Acad. Sci., 2016, 113, (1), pp. 176181.
    40. 40)
      • 40. Ftouni, S., Sletten, T.L., Howard, M., et al: ‘Objective and subjective measures of sleepiness, and their associations with on-road driving events in shift workers’, J. Sleep Res., 2013, 22, (1), pp. 5869.
    41. 41)
      • 41. Li, G., Chung, W.Y.: ‘A context-aware EEG headset system for early detection of driver drowsiness’, Sensors, 2015, 15, (8), pp. 2087320893.
    42. 42)
      • 42. Picot, A., Charbonnier, S., Caplier, A.: ‘On-line detection of drowsiness using brain and visual information’, Trans. Syst. Man Cybern. A, Syst. Humans, 2012, 42, (3), pp. 764775.
    43. 43)
      • 43. Jirina, M., Bouchner, P., Novotny, S.: ‘Identification of driver's drowsiness using driving information and EEG’, Neural Netw. World, 2010, 20, (6), pp. 773791.
    44. 44)
      • 44. Li, G., Lee, B.L., Chung, W.Y.: ‘Smartwatch-based wearable EEG system for driver drowsiness detection’, IEEE Sens. J., 2015, 15, (12), pp. 71697180.
    45. 45)
      • 45. Ahlstrom, C., Fors, C., Anund, A., et al: ‘Video-based observer rated sleepiness versus self-reported subjective sleepiness in real road driving’, Eur. Transp. Res. Rev., 2015, 7, (4), p. 38.
    46. 46)
      • 46. Doran, S.M., Van Dongen, H.P.A., Dinges, D.F.: ‘Sustained attention performance during sleep deprivation: evidence of state instability’, Arch. Ital. Biol., 2001, 139, (3), pp. 253267.
    47. 47)
      • 47. Ǻkerstedt, T., Gillberg, M.: ‘Subjective and objective sleepiness in the active individual’, Int. J. Neurosci., 1990, 52, (1–2), pp. 2937.
    48. 48)
      • 48. Fors, C., Ahlström, C., Sörner, P., et al: ‘Camera-based sleepiness detection: final report of the project SleepEYE’ (The Swedish National Road and Transport Research Institute, Linköping, Sweden, 2011).
    49. 49)
      • 49. Chawla, N.V., Bowyer, K.W., Hall, L.O., et al: ‘SMOTE: synthetic minority over-sampling technique’, J. Artif. Intell. Res., 2002, 16, pp. 321357.
    50. 50)
      • 50. Cruz, R., Fernandes, K., Cardoso, J.S., et al: ‘Tackling class imbalance with ranking’. 2016 Int. Joint Conf. Neural Networks (IJCNN), Vancouver, Canada, July 2016, pp. 21822187.
    51. 51)
      • 51. Ingre, M., Åkerstedt, T., Peters, B., et al: ‘Subjective sleepiness, simulated driving performance and blink duration: examining individual differences’, J. Sleep Res., 2006, 15, (1), pp. 4753.
    52. 52)
      • 52. Chua, E.C.P., Yeo, S.C., Lee, I.T.G., et al: ‘Individual differences in physiologic measures are stable across repeated exposures to total sleep deprivation’, Physiol. Rep., 2014, 2, (9).
    53. 53)
      • 53. Sparrow, A.R., LaJambe, C.M., Van Dongen, H.P.A.: ‘Drowsiness measures for commercial motor vehicle operations’, Accident Anal. Prev., 2018, doi.org/10.1016/j.aap.2018.04.020.
    54. 54)
      • 54. Åkerstedt, T., Anund, A., Axelsson, J., et al: ‘Subjective sleepiness is a sensitive indicator of insufficient sleep and impaired waking function’, J. Sleep Res., 2014, 23, (3), pp. 240252.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-its.2018.5284
Loading

Related content

content/journals/10.1049/iet-its.2018.5284
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading
This is a required field
Please enter a valid email address