Abstract
Machine learning has been used in the last decade to solve many problems in the haptics field. In particular, EEG data that is recorded during haptic interactions was used to train machine learning (ML) models to answer questions that are of interest to the neurohaptics community. However, the behavior of machine learning models in taking out their decisions is treated as black box hindering the interpretability of these decisions. In this paper, we used Shapley values, a concept from game theory, to explain the behavior of a tree-based classifier model in classifying electroencephalography data that was collected during an interaction with a surface haptic device under two conditions: with and without tactile feedback. We trained a tree-based ML model to classify data based on the presence or absence of tactile feedback. Using Shapley values, we identified the features (across and within channels) that contribute the most to the classification decision. Results showed channel AF3 and neural activity after 700 ms from the onset contributed the most in recognizing tactile feedback in the interaction. This study demonstrates the use of explainable machine learning in the field of Neurohaptics.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Alsuradi, H., Pawar, C., Park, W., Eid, M.: Detection of tactile feedback on touch-screen devices using EEG data. In: 2020 IEEE Haptics Symposium (HAPTICS). IEEE (2020)
Chen, T., Guestrin, C.: XGBoost: a scalable tree boosting system. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 785–794 (2016)
Cisotto, G., Guglielmi, A.V., Badia, L., Zanella, A.: Classification of grasping tasks based on EEG-EMG coherence. In: 2018 IEEE 20th International Conference on e-Health Networking, Applications and Services (Healthcom), pp. 1–6. IEEE (2018)
Dietterich, T.G., Kong, E.B.: Machine learning bias, statistical bias, and statistical variance of decision tree algorithms. Technical report, Department of Computer Science, Oregon State University (1995)
Egner, T., Gruzelier, J.H.: EEG biofeedback of low beta band components: frequency-specific effects on variables of attention and event-related brain potentials. Clin. Neurophysiol. 115(1), 131–139 (2004)
Glover, G.H.: Overview of functional magnetic resonance imaging. Neurosurg. Clin. 22(2), 133–139 (2011)
Greco, A., Nardelli, M., Bianchi, M., Valenza, G., Scilingo, E.P.: Recognition of affective haptic stimuli conveyed by different fabrics sing EEG-based sparse SVM. In: 2017 IEEE 3rd International Forum on Research and Technologies for Society and Industry (RTSI), pp. 1–5. IEEE (2017)
Grummett, T.S., et al.: Constitutive spectral EEG peaks in the gamma range: suppressed by sleep, reduced by mental activity and resistant to sensory stimulation. Front. Hum. Neurosci. 8, 927 (2014)
Khasnobish, A., Konar, A., Tibarewala, D.N., Bhattacharyya, S., Janarthanan, R.: Object shape recognition from EEG signals during tactile and visual exploration. In: Maji, P., Ghosh, A., Murty, M.N., Ghosh, K., Pal, S.K. (eds.) PReMI 2013. LNCS, vol. 8251, pp. 459–464. Springer, Heidelberg (2013). https://doi.org/10.1007/978-3-642-45062-4_63
Kim, S.G., Richter, W., Uǧurbil, K.: Limitations of temporal resolution in functional MRI. Magn. Reson. Med. 37(4), 631–636 (1997)
Loftus, E.F., Pickrell, J.E.: The formation of false memories. Psychiatric Ann. 25(12), 720–725 (1995)
Lundberg, S.M., et al.: From local explanations to global understanding with explainable AI for trees. Nat. Mach. Intell. 2(1), 2522–5839 (2020)
Lundberg, S.M., Lee, S.I.: A unified approach to interpreting model predictions. In: Advances in Neural Information Processing Systems, pp. 4765–4774 (2017)
Morin, C.: Neuromarketing: the new science of consumer behavior. Society 48(2), 131–135 (2011). https://doi.org/10.1007/s12115-010-9408-1
Park, W., Jamil, M.H., Eid, M.: Neural activations associated with friction stimulation on touch-screen devices. Front. Neurorobot. 13, 27 (2019)
Saha, A., Konar, A., Bhattacharya, B.S., Nagar, A.K.: EEG classification to determine the degree of pleasure levels in touch-perception of human subjects. In: 2015 International Joint Conference on Neural Networks (IJCNN), pp. 1–8. IEEE (2015)
Shapley, L.S.: A value for n-person games. In: Contributions to the Theory of Games, vol. 2, no. 28, pp. 307–317 (1953)
Acknowledgement
This research was funded by NYU Abu Dhabi PhD Fellowship Program.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Alsuradi, H., Park, W., Eid, M. (2020). Explainable Classification of EEG Data for an Active Touch Task Using Shapley Values. In: Stephanidis, C., Kurosu, M., Degen, H., Reinerman-Jones, L. (eds) HCI International 2020 - Late Breaking Papers: Multimodality and Intelligence. HCII 2020. Lecture Notes in Computer Science(), vol 12424. Springer, Cham. https://doi.org/10.1007/978-3-030-60117-1_30
Download citation
DOI: https://doi.org/10.1007/978-3-030-60117-1_30
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-60116-4
Online ISBN: 978-3-030-60117-1
eBook Packages: Computer ScienceComputer Science (R0)