A statistical analysis of operator behavior indicators has been performed for an operator executing a real industrial assembly task. The indicators are computed automatically from mobile eye-tracker data and computer vision algorithms – hand and target object detection. At earlier stages of this research the multimodal recording system was developed and descriptive group-level values for the same task were reported; the significance of the observed differences was not tested. Here the unit of analysis is an individual trial: 22 recordings of the assembly performed by one expert and two novice operators under organized and disorganized workplace conditions were processed. The Mann–Whitney test with the Cliff's delta effect size was applied, an indicator (the rate of switching between areas of interest) was introduced, and the dynamics of the indicators over repeated executions was examined. The expert and the novices differ significantly in task duration, gaze transition entropy, attention switching rate and the fraction of fixations outside target objects, with large effect sizes for most indicators. Under the organized condition gaze switches between target zones more often and more diversely, whereas under the disorganized condition it dwells longer on background search areas. For the novice operator the task duration decreases significantly from repetition to repetition, while the expert shows no such trend. The indicators are sensitive both to skill level and to the course of task learning and can be used for objective monitoring of operator training and for assessing workplace layout.
1. Johansson R.S., Westling G., Bäckström A., Flanagan J.R. Eye-hand coordination in object manipulation. The Journal of Neuroscience. 2001;21(17):6917–6932. https://doi.org/10.1523/JNEUROSCI.21-17-06917.2001
2. Hayhoe M., Ballard D. Eye movements in natural behavior. Trends in Cognitive Sciences. 2005;9(4):188–194. https://doi.org/10.1016/j.tics.2005.02.009
3. So W.K.Y., Wong S.W.H., Mak J.N., Chan R.H.M. An evaluation of mental workload with frontal EEG. PLoS ONE. 2017;12(4):e0174949. https://doi.org/10.1371/journal.pone.0174949
4. Kaczorowska M., Plechawska-Wójcik M., Tokovarov M., Krukow P. Automated classification of cognitive workload levels based on psychophysiological and behavioural variables of ex-Gaussian distributional features. Brain Sciences. 2022;12(5):542. https://doi.org/10.3390/brainsci12050542
5. Papoutsakis K., Bakalos N., Fragkoulis K., Zacharia A., Kapetadimitri G., Pateraki M. A vision-based framework for human behavior understanding in industrial assembly lines. In: Computer Vision – ECCV 2024 Workshops: Part XIII, 29 September – 04 October 2024, Milan, Italy. Cham: Springer; 2025. P. 324–342. https://doi.org/10.1007/978-3-031-91575-8_20
6. Gegenfurtner A., Lehtinen E., Säljö R. Expertise differences in the comprehension of visualizations: a meta-analysis of eye-tracking research in professional domains. Educational Psychology Review. 2011;23(4):523–552. https://doi.org/10.1007/s10648-011-9174-7
7. Keskin M., Ooms K., Dogru A.O., De Maeyer Ph. Exploring the cognitive load of expert and novice map users using EEG and eye tracking. ISPRS International Journal of Geo-Information. 2020;9(7):429. https://doi.org/10.3390/ijgi9070429
8. Holmqvist K., Nyström M., Andersson R., Dewhurst R., Jarodzka H., van de Weijer J. Eye Tracking: A Comprehensive Guide to Methods and Measures. Oxford: Oxford University Press; 2011. 560 p.
9. Drews M., Dierkes K. Strategies for enhancing automatic fixation detection in head-mounted eye tracking. Behavior Research Methods. 2024;56(6):6276–6298. https://doi.org/10.3758/s13428-024-02360-0
10. Krejtz K., Duchowski A., Szmidt T., et al. Gaze transition entropy. ACM Transactions on Applied Perception. 2015;13(1):4. https://doi.org/10.1145/2834121
11. Mann H.B., Whitney D.R. On a test of whether one of two random variables is stochastically larger than the other. The Annals of Mathematical Statistics. 1947;18(1):50–60. https://doi.org/10.1214/aoms/1177730491
12. Cliff N. Dominance statistics: ordinal analyses to answer ordinal questions. Psychological Bulletin. 1993;114(3):494–509. https://doi.org/10.1037/0033-2909.114.3.494
13. Sahoo P., Biondi F. On the effect of using an augmented reality laser projection operator guidance system on cognitive workload and assembly task performance. Applied Ergonomics. 2025;130:104662. https://doi.org/10.1016/j.apergo.2025.104662
14. Hart S.G., Staveland L.E. Development of NASA-TLX (Task Load Index): results of empirical and theoretical research. In: Human Mental Workload. North-Holland: Elsevier Science Publishers; 1988. P. 139–183. https://doi.org/10.1016/S0166-4115(08)62386-9
Gurbanov Kanan Aydin
ORCID |
Azerbaijan State Oil and Industry University
Baku, Azerbaijan
