Autors: Georgiev S., Andonov, S. A., Tsenov, G. C., Markov A.
Title: Grouping of Multidimensional Biosignal Attributes from a Dataset of Car Driving Experiences
Keywords: biosignal measurement, driver experience, human-machine interaction, multidimensional clustering

Abstract: This study applies unsupervised clustering techniques to classify 37 vehicle models based on biometric data collected from a single driver. Physiological measurements (electroencephalograph (EEG) theta/alpha ratio, Heart Rate (HR), Galvanic Skin Response (GSR), and Blood Oxygen Level) were recorded before and after each driving session. The analysis focuses on how different vehicles influence driver physiology, aiming to uncover latent grouping structures in the data. Four clustering methods-K-Means, DBSCAN, Gaussian Mixture Models, and Agglomerative Clustering-were used to segment vehicles based on changes in physiological responses. The appropriate number of clusters was evaluated using the Elbow Method, Akaike's information criterion (AIC), and Bayesian information criterion (BIC).

References

  1. Healey, J. A., & Picard, R. W. (2005). Detecting stress during real-world driving tasks using physiological sensors. IEEE Transactions on Intelligent Transportation Systems, 6(2), 156–166.
  2. Lin, C.-T., Ko, L.-W., et al. (2006). EEG-based drowsiness estimation for safety driving using independent component analysis. IEEE Transactions on Circuits and Systems I: Regular Papers, 52(12), 2726–2738.
  3. Yeo, M. V., Li, X., et al. (2009). Can SVM be used for automatic EEG detection of drowsiness during car driving? Safety Science, 47(1), 115–124.
  4. Shi, Y., Ruiz, N., Taib, R., Choi, E., & Chen, F. (2010). Galvanic skin response (GSR) as an index of cognitive load. Proceedings of the CHI '10 Extended Abstracts on Human Factors in Computing Systems, 4473–4478.
  5. Mehler, B., Reimer, B., et al. (2012). Physiological indicators of driver workload when transitioning from a manual to an automated vehicle. Transportation Research Part F: Traffic Psychology and Behaviour, 15(5), 667–675.
  6. Takeda, K., et al. (2009). Development of in-vehicle stress monitoring system using physiological sensors. SAE Technical Paper 2009-01-2912.
  7. Siwei Ma, Xuedong Yan, Jac Billington, Natasha Merat, Gustav Markkula, Cognitive load during driving: EEG microstate metrics are sensitive to task difficulty and predict safety outcomes, Accident Analysis & Prevention, Volume 207, 2024, 107769, ISSN 0001-4575
  8. Blalock, Lisa & Sawyer, Ben & Kiken, Ariana & Gutzwiller, Robert & McGill, Calvin & Clegg, Benjamin. (2014). Cognitive load while driving impairs memory of moving but not stationary elements within the environment. Journal of Applied Research in Memory and Cognition. 3. 95-100. 10.1016/j.jarmac.2014.04.006.
  9. Siwei Ma, Xuedong Yan, Jac Billington, Natasha Merat, Gustav Markkula, Cognitive load during driving: EEG microstate metrics are sensitive to task difficulty and predict safety outcomes, Accident Analysis & Prevention, Volume 207, 2024, 107769, ISSN 0001-4575
  10. Felisberti, F.M., Fernandes, T.P. Exploring the effect of cognitive load in scenarios of daily driving. Curr Psychol 43, 26438–26448 (2024). https://doi.org/10.1007/s12144-024-06287-9
  11. Király B, Hangya B. Navigating the Statistical Minefield of Model Selection and Clustering in Neuroscience. eNeuro. 2022 Jul 14;9(4):ENEURO.0066-22.2022. doi: 10.1523/ENEURO.0066-22.2022. PMID: 35835556;

Issue

2025 34th International Scientific Conference Electronics, ET 2025 - Proceedings, 2025, Albania, https://doi.org/10.1109/ET66806.2025.11204060

Вид: публикация в международен форум, публикация в реферирано издание, индексирана в Scopus