Abstract
Most of the studies on decision confidence are from the fields of neuroscience and cognitive science, and existing studies based on deep neural networks do not exploit the topology of multi-channel EEG signals. In this paper, we propose an attentive simple graph convolutional network (ASGC) for EEG-based human decision confidence measurement. ASGC captures both coarse-grained and fine-grained inter-channel relationship by learning a shared adjacency matrix and utilizing self-attention mechanism, respectively. In addition, we propose a confidence distribution learning (CDL) loss based on a natural intuition to alleviate two problems: lack of training samples and label ambiguity. We conduct experiments on a dataset built for the confidence measurement in a visual perception task. The experimental results demonstrate advanced performance of our model, achieving an accuracy of 68.83% and F1-score of 66.9%. Finally, we investigate the critical channels for decision confidence measurement with the attention matrix of EEG channels.
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
Similar content being viewed by others
References
Bang, D., Fleming, S.M.: Distinct encoding of decision confidence in human medial prefrontal cortex. Proc. Natl. Acad. Sci. 115(23), 6082–6087 (2018)
Boldt, A., Schiffer, A.M., Waszak, F., Yeung, N.: Confidence predictions affect performance confidence and neural preparation in perceptual decision making. Sci. Rep. 9(1), 1–17 (2019)
Gao, B.B., Xing, C., Xie, C.W., Wu, J., Geng, X.: Deep label distribution learning with label ambiguity. IEEE Trans. Image Process. 26(6), 2825–2838 (2017)
Gherman, S., Philiastides, M.G.: Neural representations of confidence emerge from the process of decision formation during perceptual choices. Neuroimage 106, 134–143 (2015)
Hebart, M.N., Schriever, Y., Donner, T.H., Haynes, J.D.: The relationship between perceptual decision variables and confidence in the human brain. Cereb. Cortex 26(1), 118–130 (2016)
Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016)
Li, R., Liu, L.D., Lu, B.L.: Measuring human decision confidence from EEG signals in an object detection task. In: 2021 10th International IEEE/EMBS Conference on Neural Engineering (NER), pp. 942–945. IEEE (2021)
Li, R., Liu, L.D., Lu, B.L.: Discrimination of decision confidence levels from EEG signals. In: 2021 10th International IEEE/EMBS Conference on Neural Engineering (NER), pp. 946–949. IEEE (2021)
Li, R., Wang, S., Zhu, F., Huang, J.: Adaptive graph convolutional neural networks. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32 (2018)
Molenberghs, P., Trautwein, F.M., Böckler, A., Singer, T., Kanske, P.: Neural correlates of metacognitive ability and of feeling confident: a large-scale fMRI study. Soc. Cogn. Affect. Neurosci. 11(12), 1942–1951 (2016)
Pouget, A., Drugowitsch, J., Kepecs, A.: Confidence and certainty: distinct probabilistic quantities for different goals. Nat. Neurosci. 19(3), 366 (2016)
Song, T., Zheng, W., Song, P., Cui, Z.: EEG emotion recognition using dynamical graph convolutional neural networks. IEEE Trans. Affect. Comput. 11(3), 532–541 (2018)
Wu, F., Souza, A., Zhang, T., Fifty, C., Yu, T., Weinberger, K.: Simplifying graph convolutional networks. In: International Conference on Machine Learning, pp. 6861–6871. PMLR (2019)
Zhang, G., Yu, M., Liu, Y.J., Zhao, G., Zhang, D., Zheng, W.: SparseDGCNN: recognizing emotion from multichannel EEG signals. IEEE Trans. Affect. Comput. (2021)
Zhong, P., Wang, D., Miao, C.: EEG-based emotion recognition using regularized graph neural networks. IEEE Trans. Affect. Comput. (2020)
Acknowledgments
This work was supported in part by grants from the National Natural Science Foundation of China (Grant No. 61976135), SJTU Trans-Med Awards Research (WF540162605), the Fundamental Research Funds for the Central Universities, the 111 Project, and the China Southern Power Grid (Grant No. GDKJXM20185761).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Liu, LD., Li, R., Liu, YZ., Li, HL., Lu, BL. (2021). EEG-Based Human Decision Confidence Measurement Using Graph Neural Networks. In: Mantoro, T., Lee, M., Ayu, M.A., Wong, K.W., Hidayanto, A.N. (eds) Neural Information Processing. ICONIP 2021. Communications in Computer and Information Science, vol 1517. Springer, Cham. https://doi.org/10.1007/978-3-030-92310-5_34
Download citation
DOI: https://doi.org/10.1007/978-3-030-92310-5_34
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-92309-9
Online ISBN: 978-3-030-92310-5
eBook Packages: Computer ScienceComputer Science (R0)