Exploring Novel Methodology for Classifying Cognitive Workload

  • Seth SiriyaEmail author
  • Martin Lochner
  • Andreas Duenser
  • Ronnie Taib
Conference paper
Part of the Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering book series (LNICST, volume 273)


This paper describes our work in extracting useful cognitive load classification information from a relatively simple and non-invasive physiological measurement technique, with application in a range of Human Factors and Human-Computer Interaction contexts. We employ novel methodologies, including signal processing, machine learning and genetic algorithms, to classify Galvanic Skin Response/Electrodermal Activity (GSR/EDA) signals during performance of a customised game task (UAV Defender) in high- and low-workload conditions. Our results reveal that Support Vector Machine Linear was the most successful technique for classifying the level of cognitive load that an operator is undergoing during easy, medium, and difficult operation conditions. This methodology has the advantage of applicability in critical task situations, where other cognitive load measurement methodologies are problematic due to sampling delay (e.g. questionnaires), or difficulty of implementation (e.g. other psych-physiological measures). A proposed cognitive load classification pipeline for real-time implementation and its use in human factors contexts is discussed.


Cognitive load Galvanic Skin Response Electrodermal Activity Psycho-physiology Analytics Machine learning Decision response task 



This research was funded in part by the CSIRO Data61 Automation Trust and Workload CRP, and Australian Research Council DP160101891, CERA247.


  1. 1.
    Ayaz, H., et al.: Cognitive workload assessment of air traffic controllers using optical brain imaging sensors. In: Rice, V. (ed.) Advances in Understanding Human Performance, vol. 20105280, pp. 21–31. CRC Press, Boca Raton (2010)CrossRefGoogle Scholar
  2. 2.
    Baddeley, A.D.: Working memory. Science 255(556–559), 5044 (1992)Google Scholar
  3. 3.
    Cain, B.: A review of the mental workload literature. Technical report, DTIC (2007).
  4. 4.
    Cawley, G.C., Talbot, N.L.: On over-fitting in model selection and subsequent selection bias in performance evaluation. J. Mach. Learn. Res. 11(Jul), 2079–2107 (2010)MathSciNetzbMATHGoogle Scholar
  5. 5.
    Dünser, A., Mancero, G.: The use of depth in change detection and multiple object tracking. Ergon. Open J. 2, 142–149 (2009)CrossRefGoogle Scholar
  6. 6.
    Bureau d’Enquetes et d’Analyses France (BEA): Final Report: Accident to Airbus A330–203 Registered F-GZCP, Air France AF 447 Rio de Janeiro - Paris, 1st June 2009. Technical report, Air Accident Investigation Unit (AAIU), October 2014.
  7. 7.
    Funke, G., et al.: Evaluation of subjective and EEG-based measures of mental workload. In: Stephanidis, C. (ed.) HCI 2013. CCIS, vol. 373, pp. 412–416. Springer, Heidelberg (2013). Scholar
  8. 8.
    Healey, J., Picard, R.: SmartCar: detecting driver stress. In: Proceedings 15th International Conference on Pattern Recognition, ICPR-2000, vol. 4, pp. 218–221 (2000)Google Scholar
  9. 9.
    Hjorth, B.: EEG analysis based on time domain properties. Electroencephalogr. Clin. Neurophysiol. 29(3), 306–310 (1970)CrossRefGoogle Scholar
  10. 10.
    International Organization for Standardization: ISO 17488:2016(en), Road vehicles - transport information and control systems - detection-response task (DRT) for assessing attentional effects of cognitive load in driving. Technical Report ISO 17488:2016(en), International (2016)Google Scholar
  11. 11.
    Lim, C.L., et al.: Decomposing skin conductance into tonic and phasic components. Int. J. Psychophysiol. 25(2), 97–109 (1997)CrossRefGoogle Scholar
  12. 12.
    Lochner, M., Duenser, A., Lutzhoft, M., Brooks, B., Rozado, D.: Analysis of maritime team workload and communication dynamics in standard and emergency scenarios. J. Shipp. Trade 3(1), 2 (2018)CrossRefGoogle Scholar
  13. 13.
    Lochner, M.J., Trick, L.M.: Multiple-object tracking while driving: the multiple-vehicle tracking task. Atten. Percept. Psychophys. 76, 2326–2345 (2014)CrossRefGoogle Scholar
  14. 14.
    Nourbakhsh, N., Wang, Y., Chen, F.: GSR and blink features for cognitive load classification. In: Kotzé, P., Marsden, G., Lindgaard, G., Wesson, J., Winckler, M. (eds.) INTERACT 2013. LNCS, vol. 8117, pp. 159–166. Springer, Heidelberg (2013). Scholar
  15. 15.
    Phinyomark, A., Thongpanja, S., Hu, H., Phukpattaranont, P., Limsakul, C.: The usefulness of mean and median frequencies in electromyography analysis. In: Naik, G.R. (ed.) Computational Intelligence in Electromyography Analysis - A Perspective on Current Applications and Future Challenges. INTECH Open Access Publisher (2012).
  16. 16.
    Posada-Quintero, H.F., Chon, K.H.: Frequency-domain electrodermal activity index of sympathetic function. In: 2016 IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI), pp. 497–500, Febraury 2016Google Scholar
  17. 17.
    Pylyshyn, Z.W., Storm, R.W.: Tracking multiple independent targets: evidence for a parallel tracking mechanism. Spat. Vis. 3(3), 179–197 (1988)CrossRefGoogle Scholar
  18. 18.
    Rozado, D., Duenser, A.: Combining EEG with pupillometry to improve cognitive workload detection. IEEE Comput. 48(10), 18–25 (2015)CrossRefGoogle Scholar
  19. 19.
    Rozado, D., Lochner, M., Engelke, U., Duenser, A.: Detecting intention through motor-imagery-triggered pupil dilations. Hum.-Comput. Inter., 1–31, Febraury 2017Google Scholar
  20. 20.
    Shi, Y., Ruiz, N., Taib, R., Choi, E., Chen, F.: Galvanic skin response (GSR) as an index of cognitive load. In: CHI 2007 Extended Abstracts, pp. 2651–2656. ACM, New York, April 2007Google Scholar
  21. 21.
    Uguz, H.: A two-stage feature selection method for text categorization by using information gain, principal component analysis and genetic algorithm. Knowl.-Based Syst. 24(7), 1024–1032 (2011)CrossRefGoogle Scholar
  22. 22.
    Welch, P.: The use of fast Fourier transform for the estimation of power spectra: a method based on time averaging over short, modified periodograms. IEEE Trans. Audio Electroacoust. 15(2), 70–73 (1967)CrossRefGoogle Scholar
  23. 23.
    Wilson, G.F., Fullenkamp, P., Davis, I.: Evoked potential, cardiac, blink, and respiration measures of pilot workload in air-to-ground missions. Aviat. Space Environ. Med. 65(2), 100–105 (1994)Google Scholar
  24. 24.
    Zhou, J., Sun, J., Chen, F., Wang, Y., Taib, R., Khawaji, A., Li, Z.: Measurable decision making with GSR and pupillary analysis for intelligent user interface. ACM Trans. Comput.-Hum. Interact. 21(6), 1–23 (2015)CrossRefGoogle Scholar

Copyright information

© ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering 2019

Authors and Affiliations

  1. 1.University of MelbourneMelbourneAustralia
  2. 2.Data61, CSIROHobartAustralia
  3. 3.Data61, CSIROEveleighAustralia

Personalised recommendations