Your browser does not support JavaScript!
http://iet.metastore.ingenta.com
1887

access icon free Exploration and evaluation of individual difference to driving fatigue for high-speed railway: a parametric SVM model based on multidimensional visual cue

© The Institution of Engineering and Technology
Received 22/09/2017, Accepted 04/02/2018, Revised 05/12/2017, Published 06/02/2018

High-speed rails have a significantly higher driving safety requirement than other public transport because of more passengers and faster speed. However, the particularity of train driving often leads to railway drivers more susceptible to drowsiness and fatigue, and this fatigue has a distinct personality. Here, the authors analyse the mechanism of individual fatigue generation of different drivers, and use eye movement data collected by non-contact means as an objective measurement, and combine subjective sleepiness assessment to reveal the existence of individual differences in fatigue in high-speed railway driving. Furthermore, a novel driver-specific feature weighted support vector machine (FWSVM) algorithm is proposed to handle the individual differences. In the FWSVM, features are assigned with different weights by the information gain to reflect classification importance and individual effects. The average accuracy of FWSVM is 90.98%, the average sensitivity is 92.01%, and the average specificity is 89.88%, which is better than the classical SVM. Such improvements are attributed to the quantitative evaluation of individual effects by the weighted features. These results can be used as a preliminary study to design a high-speed rail vehicle interface to prevent driver fatigue.

Inspec keywords: railway safety; railways; driver information systems; support vector machines; pattern classification; human factors

Other keywords: driving fatigue; objective measurement; eye movement data collection; FWSVM algorithm; high-speed railway; high-speed rail vehicle interface design; subjective sleepiness assessment; multidimensional visual cue; parametric SVM model; individual fatigue generation mechanism; individual difference evaluation; individual difference exploration; railway drivers; information gain; driving safety requirement; public transport; driver-specific feature weighted support vector machine algorithm

Subjects: Traffic engineering computing; Data handling techniques; Knowledge engineering techniques

References

    1. 1)
      • 38. Körber, M., Cingel, A., Zimmermann, M., et al: ‘Vigilance decrement and passive fatigue caused by monotony in automated driving’, Procedia Manuf., 2015, 3, pp. 2403–2409.
    2. 2)
      • 6. Chang, H.L., Ju, L.S.: ‘Effect of consecutive driving on accident risk: a comparison between passenger and freight train driving’, Accid. Anal. Prev., 2008, 40, (6), p. 1844.
    3. 3)
      • 27. Variables, R.: ‘In-vehicle prediction of truck driver sleepiness: lane position variables, Masters Thesis’ Luleå Technical University, 2007.
    4. 4)
      • 46. Akerstedt, T., Ingre, M., Kecklund, G., et al: ‘Reaction of sleepiness indicators to partial sleep deprivation, time of day and time on task in a driving simulator – the DROWSI project’, J. Sleep Res., 2010, 19, (2), pp. 298–309.
    5. 5)
      • 19. Dorrian, J., Baulk, S.D., Dawson, D.: ‘Work hours, workload, sleep and fatigue in Australian rail industry employees’, Appl. Ergon., 2011, 42, (2), pp. 202–209.
    6. 6)
      • 41. Rowland, L.M., Thomas, M.L., Thorne, D.R., et al: ‘Oculomotor responses during partial and total sleep deprivation’, Aviat. Space Environ. Med., 2005, 76, (7 Suppl.), pp. 104–113.
    7. 7)
      • 30. Johnson, R.R., Popovic, D.P., Olmstead, R.E., et al: ‘Drowsiness/alertness algorithm development and validation using synchronized EEG and cognitive performance to individualize a generalized model’, Biol. Psychol., 2011, 87, (2), pp. 241–250.
    8. 8)
      • 23. Van Dongen, H.P., Vitellaro, K.M., Dinges, D.F.: ‘Individual differences in adult human sleep and wakefulness: leitmotif for a research agenda’, Sleep, 2005, 28, (4), pp. 479–496.
    9. 9)
      • 13. Tsao, L., Chang, J., Ma, L.: ‘Fatigue of Chinese railway employees and its influential factors: structural equation modelling’, Appl. Ergon., 2017, 62, pp. 131–141.
    10. 10)
      • 37. Schleicher, R., Galley, N., Briest, S., et al: ‘Blinks and saccades as indicators of fatigue in sleepiness warnings: looking tired?’, Ergonomics, 2008, 51, (7), pp. 982–1010.
    11. 11)
      • 20. Nosal, P.: ‘Automatic train protection and stop system patent EP2210791’. 2010.
    12. 12)
      • 55. Pedrotti, M., Lei, S., Dzaack, J., et al: ‘A data-driven algorithm for offline pupil signal preprocessing and eyeblink detection in low-speed eye-tracking protocols’, Beh. Res. Meth., 2011, 43, (2), pp. 372–383.
    13. 13)
      • 31. Sauvet, F., Bougard, C., Coroenne, M., et al: ‘In-flight automatic detection of vigilance states using a single EEG channel’, IEEE Trans. Biomed. Eng., 2014, 61, (12), pp. 2840–2847.
    14. 14)
      • 7. Furukawa, T., Nakano, H., Hirayama, K., et al: ‘Snoring, obstructive sleep apnea and their health consequences (symposium/relationship between sleep and health care)’, Jpn. J. Psychosom. Med., 2011, 51, pp. 790–798.
    15. 15)
      • 25. Borghini, G., Astolfi, L., Vecchiato, G., et al: ‘Measuring neurophysiological signals in aircraft pilots and car drivers for the assessment of mental workload, fatigue and drowsiness’, Neurosci. Biobehav. Rev., 2014, 44, pp. 58–75.
    16. 16)
      • 15. Spring, P., McIntosh, A., Caponecchia, C., et al: ‘Level of automation: effects on train driver vigilance’. 3rd Int. Conf. on Rail Human Factors, Lille, Paris, 2009.
    17. 17)
      • 28. Forsman, P.M., Vila, B.J., Short, R.A., et al: ‘Efficient driver drowsiness detection at moderate levels of drowsiness’, Accid. Anal. Prev., 2013, 50, (1), pp. 341–350.
    18. 18)
      • 51. Vapnik, V.N.: ‘The nature of statistical learning theory’, 1995, pp. 1564–1564.
    19. 19)
      • 10. Rail Safety and Standards board Ltd: ‘Fatigue and its contribution to railway incidents’, 2015.
    20. 20)
      • 35. Bergasa, L.M., Nuevo, J., Sotelo, M.A., et al: ‘Real-time system for monitoring driver vigilance’, IEEE Trans. Intell. Transp. Syst., 2006, 7, (1), pp. 63–77.
    21. 21)
      • 50. K, K., M, T., T, A., et al: ‘Validation of the Karolinska sleepiness scale against performance and EEG variables’, Clin. Neurophysiol., 2006, 117, (7), pp. 1574–1581.
    22. 22)
      • 8. Zoer, I., Sluiter, J.K., Fringsdresen, M.H.W.: ‘Psychological work characteristics, psychological workload and associated psychological and cognitive requirements of train drivers’, Ergonomics, 2014, 57, (10), pp. 1473–1487.
    23. 23)
      • 16. Phillips, R.O.: ‘What is fatigue and how does it affect the safety performance of human transport operators?’. Tøi Report, 2014.
    24. 24)
      • 43. Mandal, B., Li, L., Wang, G.S., et al: ‘Towards detection of bus driver fatigue based on robust visual analysis of eye state’, IEEE Trans. Intell. Transp. Syst., 2017, 18, (3), pp. 545–557.
    25. 25)
      • 11. 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. 242–254.
    26. 26)
      • 9. Härmä, M., Sallinen, M., Ranta, R., et al: ‘The effect of an irregular shift system on sleepiness at work in train drivers and railway traffic controllers’, J. Sleep Res., 2010, 11, (2), pp. 141–151.
    27. 27)
      • 48. ‘Railway Locomotive Driver's Training and Test Center’. Available at http://www.rdtec.org/Index_index.action, accessed 20 May 2015.
    28. 28)
      • 57. Komogortsev, O.V., Gobert, D.V., Jayarathna, S., et al: ‘Standardization of automated analyses of oculomotor fixation and saccadic behaviors’, IEEE Trans. Biomed. Eng., 2010, 57, (11), pp. 2635–2645.
    29. 29)
      • 24. Wang, X., Xu, C.: ‘Driver drowsiness detection based on non-intrusive metrics considering individual specifics’, Accid. Anal. Prev., 2016, 95, (Pt B), pp. 350–357.
    30. 30)
      • 33. Picard, R.: ‘Smartcar: detecting driver stress’. Int. Conf. on Pattern Recognition, 2000, vol. 4, pp. 218–221.
    31. 31)
      • 1. Zhang, X., Li, J., Liu, Y., et al: ‘Design of a fatigue detection system for high-speed trains based on driver vigilance using a wireless wearable EEG’, Sensors, 2017, 17, (3), pp. 486–497.
    32. 32)
      • 42. Eskandarian, A., Mortazavi, A.: ‘Evaluation of a smart algorithm for commercial vehicle driver drowsiness detection’. Intelligent Vehicles Symp., 2007, pp. 553–559.
    33. 33)
      • 36. Daza, I.G., Bergasa, L.M., Bronte, S., et al: ‘Fusion of optimized indicators from advanced driver assistance systems (ADAS) for driver drowsiness detection’, Sensors, 2014, 14, (1), p. 1106.
    34. 34)
      • 58. Hupé, J.M., Lamirel, C., Lorenceau, J.: ‘Pupil dynamics during bistable motion perception’, J. Vision, 2009, 9, (7), p. 10.
    35. 35)
      • 34. Dinges, D.F., Grace, R.: ‘PERCLOS: a valid psychophysiological measure of alertness as assessed by psychomotor vigilance’, Tech Brief, 1998.
    36. 36)
      • 18. Darwent, D., Lamond, N., Dawson, D.: ‘The sleep and performance of train drivers during an extended freight-haul operation’, Appl. Ergon., 2008, 39, (5), pp. 614–622.
    37. 37)
      • 44. Jin, L., Niu, Q., Jiang, Y., et al: ‘Driver sleepiness detection system based on eye movements variables’, Adv. Mech. Eng., 2013, 2013, (5), pp. 1–7.
    38. 38)
      • 3. National Transport Safety Board (NTSB): ‘Collision of BNSF coal train with the rear end of standing BNSF maintenance-of-way equipment train’ (NTSB, Red Oak, IA, 2011).
    39. 39)
      • 39. Nishiyama, J., Tanida, K., Kusumi, M., et al: ‘The pupil as a possible premonitor of drowsiness’. Int. Conf. of the IEEE Engineering in Medicine and Biology Society, 2007, pp. 1586–1589.
    40. 40)
      • 53. Jin, L., Niu, Q., Hou, H., et al: ‘Driver cognitive distraction detection using driving performance measures’, Discret. Dyn. Nat. Soc., 2012, 2012, pp. 1555–1565.
    41. 41)
      • 22. Buckelmüller, J., Landolt, H.P., Stassen, H.H., et al: ‘Trait-like individual differences in the human sleep electroencephalogram’, Neuroscience, 2006, 138, (1), pp. 351–356.
    42. 42)
      • 17. Dunn, N., Williamson, A.: ‘Driving monotonous routes in a train simulator: the effect of task demand on driving performance and subjective experience’, Ergonomics, 2012, 55, (9), p. 997.
    43. 43)
      • 47. Johns, D.M.W., Tucker, A.: ‘Monitoring eye and eyelid movements by infrared reflectance oculography to measure drowsiness in drivers’, Somnologie – Schlafforschung und Schlafmedizin, 2007, 11, (4), pp. 234–242.
    44. 44)
      • 32. Qian, D., Wang, B., Qing, X., et al: ‘Drowsiness detection by Bayesian-copula discriminant classifier based on EEG signals during daytime short nap’, IEEE Trans. Biomed. Eng., 2017, 64, (4), pp. 743–754.
    45. 45)
      • 21. 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. 47–53.
    46. 46)
      • 29. Satzoda, R.K., Trivedi, M.M.: ‘Drive analysis using vehicle dynamics and vision-based lane semantics’, IEEE Trans. Intell. Transp. Syst., 2015, 16, (1), pp. 9–18.
    47. 47)
      • 45. Zhao, C., Zhang, X., Zhang, B., et al: ‘Driver's fatigue expressions recognition by combined features from pyramid histogram of oriented gradient and contourlet transform with random subspace ensembles’, IET Intell. Transp. Syst., 2013, 7, (1), pp. 36–45.
    48. 48)
      • 59. ‘Tobii Studio 3.3 User Guide’. Available at http://www.tobiipro.com/product-listing/tobii-pro-x2-60/, accessed 17 March 2016.
    49. 49)
      • 54. Grandchamp, R., Braboszcz, C., Delorme, A.: ‘Oculometric variations during mind wandering’, Front. Psychol., 2014, 5, (1), p. 31.
    50. 50)
      • 14. Cabon, P., Coblentz, A., Mollard, R., et al: ‘Human vigilance in railway and long-haul flight operation’, Ergonomics, 1993, 36, (9), pp. 1019–1033.
    51. 51)
      • 40. Lowenstein, O., Feinberg, R., Loewenfeld, I.E.: ‘Pupillary movements during acute and chronic fatigue a new test for the objective evaluation of tiredness’, Invest. Ophthalmol., 1963, 2, (2), pp. 138–157.
    52. 52)
      • 26. Dawson, D., Searle, A.K., Paterson, J.L.: ‘Look before you (s)leep: evaluating the use of fatigue detection technologies within a fatigue risk management system for the road transport industry’, Sleep Med. Rev., 2014, 18, (2), pp. 141–152.
    53. 53)
      • 2. Federal Railroad Administration: ‘National rail safety action plan final report 2005–2008’, 2008.
    54. 54)
      • 5. National Transport Safety Board (NTSB): ‘Chicago transit authority train collides with bumping post and escalator at o'Hare station’ (NTSB, Chicago, IL, 2014).
    55. 55)
      • 12. Leeuwen, W.M.A.V., Anund, A., Fors, C., et al: ‘Countermeasures for fatigue in transportation – a review of existing methods for drivers on road, rail, sea and in aviation’, J. Urol., 2015, 181, (4), pp. 453–453.
    56. 56)
      • 52. Chen, Y., Hao, Y.: ‘A feature weighted support vector machine and K-nearest neighbor algorithm for stock market indices prediction’, Expert Syst. Appl., 2017, 80, pp. 340–355.
    57. 57)
      • 4. National Transport Safety Board (NTSB): ‘Railroad accident brief: Washington metropolitan area transit authority rear-end collision’ (NTSB, Falls Church, VA, 2009).
    58. 58)
      • 56. Geangu, E., Hauf, P., Bhardwaj, R., et al: ‘Infant pupil diameter changes in response to others’ positive and negative emotions’, Plos One, 2011, 6, (11), p. e27132.
    59. 59)
      • 49. Åkerstedt, T., Gillberg, M.: ‘Subjective and objective sleepiness in the active individual’, Int. J. Neurosci., 1990, 52, (1–2), pp. 29–37.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-its.2017.0289
Loading

Related content

content/journals/10.1049/iet-its.2017.0289
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading
Print this page
This is a required field
Please enter a valid email address