Abstract
Task classification is an important step towards brain-computer interfaces (BCI). A reliable task classifier could help build better user models and help the BCI to adapt to the user task. This paper reports on a study conducted with nine human subjects on six different cognitive tasks. The study collected brain activity data from the participants using a 52 channel functional Near-Infrared Spectroscopy (fNIRS) sensor. The resulting dataset was labeled with the task type administered to the subject. After analyzing the across subject dataset using a multi-class decision tree classifier, the results show a promising F1 score of 0.94. The most predictive features for the classification are reported to guide future research into this area. The implications of this work include a generalizable task classifier based on brain activity data.
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
Hasson, U., Nusbaum, H.C., Small, S.L.: Task-dependent organization of brain regions active during rest. Proc. Natl. Acad. Sci. 106(26), 10841–10846 (2009)
Wickramaratne, S.D., Mahmud, M.S.: A deep learning based ternary task classification system using Gramian angular summation field in fNIRS neuroimaging data. In: 2020 IEEE International Conference on E-health Networking, Application & Services (HEALTHCOM), pp. 1–4. IEEE, March 2021
Chen, C., et al.: A multichannel fNIRS system for prefrontal mental task classification with dual-level excitation and deep forest algorithm. J. Sens. 2020 (2020)
Herff, C., Heger, D., Putze, F., Hennrich, J., Fortmann, O., Schultz, T.: Classification of mental tasks in the prefrontal cortex using fNIRS. In: 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), pp. 2160–2163. IEEE, July 2013
Bandara, D., Grant, T., Hirshfield, L., Velipasalar, S.: Identification of potential task shedding events using brain activity data. Augmented Hum. Res. 5(1), 1–15 (2020). https://doi.org/10.1007/s41133-020-00034-y
Hong, K.S., Naseer, N., Kim, Y.H.: Classification of prefrontal and motor cortex signals for three-class fNIRS–BCI. Neurosci. Lett. 587, 87–92 (2015)
Herold, F., Wiegel, P., Scholkmann, F., Thiers, A., Hamacher, D., Schega, L.: Functional near-infrared spectroscopy in movement science: a systematic review on cortical activity in postural and walking tasks. Neurophotonics 4(4), 041403 (2017)
Shamsi, F., Najafizadeh, L.: Multi-class classification of motor execution tasks using fNIRS. In: 2019 IEEE Signal Processing in Medicine and Biology Symposium (SPMB), pp. 1–5. IEEE, December 2019
Kocsis, L., Herman, P., Eke, A.: The modified Beer-Lambert law revisited. Phys. Med. Biol. 51(5), N91 (2006)
Song, Y.Y., Ying, L.U.: Decision tree methods: applications for classification and prediction. Shanghai Arch. Psychiatry 27(2), 130 (2015)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Bandara, D. (2022). Multi-class Task Classification Using Functional Near-Infrared Spectroscopy. In: Schmorrow, D.D., Fidopiastis, C.M. (eds) Augmented Cognition. HCII 2022. Lecture Notes in Computer Science(), vol 13310. Springer, Cham. https://doi.org/10.1007/978-3-031-05457-0_11
Download citation
DOI: https://doi.org/10.1007/978-3-031-05457-0_11
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-05456-3
Online ISBN: 978-3-031-05457-0
eBook Packages: Computer ScienceComputer Science (R0)