Prediction and Analysis of Cybersickness in VR Games Using Symbolic Machine Learning

Wedrey Nunes da Silva; Thiago Porcino; Carla Denise Castanho; Ricardo Pezzuol Jacobi

doi:10.5753/jis.2026.5597

Authors

Wedrey Nunes da Silva University of Brasilia https://orcid.org/0009-0006-6288-1917
Thiago Porcino National Laboratory for Scientific Computing - LNCC https://orcid.org/0000-0002-0281-4580
Carla Denise Castanho University of Brasilia https://orcid.org/0000-0002-7328-5479
Ricardo Pezzuol Jacobi University of Brasilia https://orcid.org/0000-0002-4520-7641

DOI:

https://doi.org/10.5753/jis.2026.5597

Keywords:

Virtual Reality, Cybersickness, Biosignals, HMD Devices, Symbolic Machine Learning, Decision Tree, Random Forest

Abstract

Cybersickness (CS) is one of the main challenges for the adoption of Virtual Reality (VR), manifesting through symptoms such as nausea, dizziness, and eye strain, particularly in Head-Mounted Display (HMD) devices. Although subjective measures, such as questionnaires, are widely used to assess CS, they do not allow for real-time user feedback. This study investigates the role of biosignals in identifying the causes and indicators of CS in VR games, employing Symbolic Machine Learning (SML) to classify the most relevant factors. Our approach combines Electrocardiogram (ECG), Electrodermal Activity (EDA), and Accelerometer (ACC) data with game metrics and user profile attributes. Data were collected from two VR games: a car game and a flying game. Decision Trees and Random Forests were used to build interpretable models, and the results showed that integrating biosignals and game data significantly improves CS prediction, with Random Forest achieving an AUC of 0.95. The findings highlight that exposure time, motion intensity, and electrodermal activity are among the key predictors of CS, reinforcing the importance of physiological monitoring in VR research. Furthermore, the study demonstrates the potential of SML in creating explainable models, contributing to more effective strategies for mitigating CS.

Downloads

Download data is not yet available.

References

Alberdi, A., Aztiria, A., and Basarab, A. (2016). Towards an automatic early stress recognition system for office environments based on multimodal measurements: A review. Journal of biomedical informatics, 59:49–75. DOI: https://doi.org/10.1016/j.jbi.2015.11.007.

Ali, J., Khan, R., Ahmad, N., and Maqsood, I. (2012). Random forests and decision trees. International Journal of Computer Science Issues (IJCSI), 9(5):272.

Andrejašic, M. (2008). Mems accelerometers. In University of Ljubljana. Faculty for mathematics and physics, Department of physics, Seminar, volume 49.

Anguita, D., Ghelardoni, L., Ghio, A., Oneto, L., Ridella, S., et al. (2012). The’k’in k-fold cross validation. In ESANN, pages 441–446.

Awal, M. A., Mostafa, S. S., Ahmad, M., and Rashid, M. A. (2014). An adaptive level dependent wavelet thresholding for ecg denoising. Biocybernetics and biomedical engineering, 34(4):238–249. DOI: https://doi.org/10.1016/j.bbe.2014.03.002.

Bassett, D. R. and John, D. (2010). Use of pedometers and accelerometers in clinical populations: validity and reliability issues. Physical therapy reviews, 15(3):135–142. DOI: https://doi.org/10.1179/1743288X10Y.0000000004.

Bernardini, F. C. (2006). Combinação de classificadores simbólicos utilizando medidas de regras de conhecimento e algoritmos genéticos. PhD thesis, Universidade de São Paulo.

Bonato, F., Bubka, A., and Palmisano, S. (2009). Combined pitch and roll and cybersickness in a virtual environment. Aviation, space, and environmental medicine, 80(11):941–945. DOI: https://doi.org/10.3357/ASEM.2394.2009.

Bouyer, G., Chellali, A., and Lécuyer, A. (2017). Inducing self-motion sensations in driving simulators using force-feedback and haptic motion. In 2017 IEEE Virtual Reality (VR), pages 84–90. IEEE. DOI: https://doi.org/10.1109/VR.2017.7892234.

Budhiraja, P., Miller, M. R., Modi, A. K., and Forsyth, D. (2017). Rotation blurring: use of artificial blurring to reduce cybersickness in virtual reality first person shooters. arXiv preprint arXiv:1710.02599. DOI: https://doi.org/10.48550/arXiv.1710.02599.

Caserman, P., Garcia-Agundez, A., Gámez Zerban, A., and Göbel, S. (2021). Cybersickness in current-generation virtual reality head-mounted displays: systematic review and outlook. Virtual Reality, 25(4):1153–1170. DOI: https://doi.org/10.1007/s10055-021-00513-6.

Daniya, T., Geetha, M., and Kumar, K. S. (2020). Classification and regression trees with gini index. Advances in Mathematics: Scientific Journal, 9(10):8237–8247. DOI: https://doi.org/10.37418/amsj.9.10.53.

De Miras, J. R., Ibáñez-Molina, A. J., Soriano, M. F., and Iglesias-Parro, S. (2023). Schizophrenia classification using machine learning on resting state eeg signal. Biomedical Signal Processing and Control, 79:104233. DOI: https://doi.org/10.1016/j.bspc.2022.104233.

Dunn, O. J. (1964). Multiple comparisons using rank sums. Technometrics, 6(3):241–252. DOI: https://doi.org/10.1080/00401706.1964.10490181.

Fomenko, I. and Kaewpankan, T. (2022). Thrill vs. cybersickness: A study on camera settings’ impact on immersion and cybersickness in vr racing games.

Garcia-Agundez, A., Reuter, C., Caserman, P., Konrad, R., and Göbel, S. (2019). Identifying cybersickness through heart rate variability alterations. International Journal of Virtual Reality, 19(1):1–10. DOI: https://doi.org/10.20870/IJVR.2019.19.1.2907.

Islam, R., Lee, Y., Jaloli, M., Muhammad, I., Zhu, D., Rad, P., Huang, Y., and Quarles, J. (2020). Automatic detection and prediction of cybersickness severity using deep neural networks from user’s physiological signals. In 2020 IEEE international symposium on mixed and augmented reality (ISMAR), pages 400–411. IEEE. DOI: https://doi.org/10.1109/ISMAR50242.2020.00066.

Jeong, D. and Han, K. (2024). Precyse: Predicting cybersickness using transformer for multimodal time-series sensor data. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, 8(2):1–24. DOI: https://doi.org/10.1145/3659594.

Jung, S., Li, R., McKee, R., Whitton, M. C., and Lindeman, R. W. (2021). Floor-vibration vr: mitigating cybersickness using whole-body tactile stimuli in highly realistic vehicle driving experiences. IEEE Transactions on Visualization & Computer Graphics, 27(05):2669–2680. DOI: https://doi.org/10.1109/TVCG.2021.3067773.

Kennedy, R. S., Lane, N. E., Berbaum, K. S., and Lilienthal, M. G. (1993). Simulator sickness questionnaire: An enhanced method for quantifying simulator sickness. The international journal of aviation psychology, 3(3):203–220. DOI: https://doi.org/10.1207/s15327108ijap0303_3.

Kennedy, R. S. and Lilienthal, M. G. (1995). Implications of balance disturbances following exposure to virtual reality systems. In Proceedings Virtual Reality Annual International Symposium’95, pages 35–39. IEEE. DOI: https://doi.org/10.1109/VRAIS.1995.512477.

Keshavarz, B., Peck, K., Rezaei, S., and Taati, B. (2022). Detecting and predicting visually induced motion sickness with physiological measures in combination with machine learning techniques. International Journal of Psychophysiology, 176:14–26. DOI: https://doi.org/10.1016/j.ijpsycho.2022.03.006.

Kolasinski, E. M. (1995). Simulator sickness in virtual environments.

Kotlowski, W., Dembczynski, K. J., and Huellermeier, E. (2011). Bipartite ranking through minimization of univariate loss. In Proceedings of the 28th International Conference on Machine Learning (ICML-11), pages 1113–1120.

Kourtesis, P., Collina, S., Doumas, L. A., and MacPherson, S. E. (2019). Technological competence is a pre-condition for effective implementation of virtual reality head mounted displays in human neuroscience: a technological review and meta-analysis. Frontiers in Human Neuroscience, 13:342. DOI: https://doi.org/10.3389/fnhum.2019.00342.

Krokos, E. and Varshney, A. (2022). Quantifying vr cybersickness using eeg. Virtual Reality, 26(1):77–89. DOI: https://doi.org/10.1007/s10055-021-00517-2.

Kruskal, W. H. and Wallis, W. A. (1952). Use of ranks in one-criterion variance analysis. Journal of the American statistical Association, 47(260):583–621. DOI: https://doi.org/10.1080/01621459.1952.10483441.

LaViola Jr, J. J. (2000). A discussion of cybersickness in virtual environments. ACM Sigchi Bulletin, 32(1):47–56. DOI: https://doi.org/10.1145/333329.333344.

Monard, M. C. and Baranauskas, J. A. (2003). Indução de regras e árvores de decisão. In Rezende, S. O., editor, Sistemas Inteligentes: Fundamentos e Aplicações, pages 115–139. Editora Manole, Barueri, SP, Brasil.

Mourant, R. R. and Thattacherry, T. R. (2000). Simulator sickness in a virtual environments driving simulator. In Proceedings of the human factors and ergonomics society annual meeting, volume 44, pages 534–537. SAGE Publications Sage CA: Los Angeles, CA. DOI: https://doi.org/10.1177/154193120004400513.

Nguyen, N. D., Tan, W., Du, L., Buntine, W., Beare, R., and Chen, C. (2023). Auc maximization for low-resource named entity recognition. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 37, pages 13389–13399. DOI: https://doi.org/10.1609/aaai.v37i11.26571.

Nunes da Silva, W., Porcino, T. M., Castanho, C. D., and Jacobi, R. P. (2024). Analysis of cybersickness through biosignals: an approach with symbolic machine learning. In Proceedings of the 26th Symposium on Virtual and Augmented Reality (SVR ’24), pages 11–20, New York, NY, USA. Association for Computing Machinery. DOI: https://doi.org/10.1145/3691573.3691582.

Oh, H. and Son, W. (2022). Cybersickness and its severity arising from virtual reality content: A comprehensive study. Sensors, 22(4):1314. DOI: https://doi.org/10.3390/s22041314.

Pashaei, E. and Pashaei, E. (2019). Gene selection using intelligent dynamic genetic algorithm and random forest. In 2019 11th international conference on electrical and electronics engineering (ELECO), pages 470–474. IEEE. DOI: https://doi.org/10.23919/ELECO47770.2019.8990557.

PLUX Biosignals (2023a). Electrocardiography (ecg) sensor data sheet. [link], Accessed: 24 October 2025.

PLUX Biosignals (2023b). Getting started: Bitalino electrodermal activity (eda) sensor. [link], Accessed: 24 October 2025.

PLUX Biosignals (2024). Bitalino (r)evolution lab guide. [link], Accessed: 24 October 2025.

Porcino, T., Rodrigues, E. O., Bernardini, F., Trevisan, D., and Clua, E. (2022). Identifying cybersickness causes in virtual reality games using symbolic machine learning algorithms. Entertainment Computing, 41:100473. DOI: https://doi.org/10.1016/j.entcom.2021.100473.

Porcino, T. M. (2021). Cybersickness Analysis Using Symbolic Machine Learning Algorithms. PhD thesis, Universidade Federal Fluminense - UFF, Niterói-RJ, Brasil.

Qu, C., Che, X., Ma, S., and Zhu, S. (2022). Biophysiological-signals-based vr cybersickness detection. CCF Transactions on Pervasive Computing and Interaction, 4(3):268–284. DOI: https://doi.org/10.1007/s42486-022-00103-8.

Reason, J. T. and Brand, J. J. (1975). Motion sickness. Academic press.

Recenti, M., Ricciardi, C., Aubonnet, R., Picone, I., Jacob, D., Svansson, H. Á., Agnarsdóttir, S., Karlsson, G. H., Baeringsdóttir, V., Petersen, H., et al. (2021). Toward predicting motion sickness using virtual reality and a moving platform assessing brain, muscles, and heart signals. Frontiers in Bioengineering and Biotechnology, 9:635661. DOI: https://doi.org/10.3389/fbioe.2021.635661.

Riccio, G. E. and Stoffregen, T. A. (1991). An ecological theory of motion sickness and postural instability. Ecological psychology, 3(3):195–240. DOI: https://doi.org/10.1207/s15326969eco0303_2.

Rokach, L. and Maimon, O. (2005). Decision trees. Data mining and knowledge discovery handbook, pages 165–192. DOI: https://doi.org/10.1007/0-387-25465-X_9.

Saredakis, D., Szpak, A., Birckhead, B., Keage, H. A., Rizzo, A., and Loetscher, T. (2020). Factors associated with virtual reality sickness in head-mounted displays: a systematic review and meta-analysis. Frontiers in human neuroscience, 14:96. DOI: https://doi.org/10.3389/fnhum.2020.00096.

Shannon, C. E. (1948). A mathematical theory of communication. The Bell system technical journal, 27(3):379–423. DOI: https://doi.org/10.1002/j.1538-7305.1948.tb01338.x.

SHAPIRO, S. (1965). An analysis of variance test for normality (complete samples) t. Biometrika, 52(3/4):591–611. DOI: https://doi.org/10.1093/biomet/52.3-4.591.

Stanney, K. M. and Hash, P. (1998). Locus of user-initiated control in virtual environments: Influences on cybersickness. Presence, 7(5):447–459. DOI: https://doi.org/10.1162/105474698565848.

Tan, J., Liu, H., Li, M., and Wang, J. (2018). A prediction scheme of tropical cyclone frequency based on lasso and random forest. Theoretical and applied climatology, 133:973–983. DOI: https://doi.org/10.1007/s00704-017-2233-3.

Tian, N. and Boulic, R. (2024). Who says you are so sick? an investigation on individual susceptibility to cybersickness triggers using eeg, egg and ecg. IEEE Transactions on Visualization and Computer Graphics. DOI: https://doi.org/10.1109/TVCG.2024.3372066.

Valkonen, M., Kartasalo, K., Liimatainen, K., Nykter, M., Latonen, L., and Ruusuvuori, P. (2017). Metastasis detection from whole slide images using local features and random forests. Cytometry Part A, 91(6):555–565. DOI: https://doi.org/10.1002/cyto.a.23089.

Vince, J. (2004). Introduction to Virtual Reality. Springer London, London.

Wang, T., Jia, W., Li, F., Liu, X., Zhang, X., and Hu, F. (2025). Multi-dimensional feature extraction of eeg signal and its application in stroke classification. Scientific Reports, 15(1):19589. DOI: https://doi.org/10.1038/s41598-025-04756-0.

Wilcoxon, F. (1945). Individual comparisons by ranking methods. Biometrics bulletin, 1(6):80–83. DOI: https://doi.org/10.2307/3001968.

Yao, D., Zhan, X., and Kwoh, C.-K. (2019). An improved random forest-based computational model for predicting novel mirna-disease associations. BMC bioinformatics, 20:1–14. DOI: https://doi.org/10.1186/s12859-019-3290-7.

Young, S. D., Adelstein, B. D., and Ellis, S. R. (2007). Demand characteristics in assessing motion sickness in a virtual environment: Or does taking a motion sickness questionnaire make you sick? IEEE transactions on visualization and computer graphics, 13(3):422–428. DOI: https://doi.org/10.1109/TVCG.2007.1029.

Zhao, Y. and Zhang, Y. (2008). Comparison of decision tree methods for finding active objects. Advances in Space Research, 41(12):1955–1959. DOI: https://doi.org/10.1016/j.asr.2007.07.020.