Electroencephalogram-Based Subject Matching Learning (ESML): A Deep Learning Framework on Electroencephalogram-Based Biometrics and Task Identification
-
Published:2023-09-14
Issue:9
Volume:13
Page:765
-
ISSN:2076-328X
-
Container-title:Behavioral Sciences
-
language:en
-
Short-container-title:Behavioral Sciences
Author:
Xu Jin1ORCID, Zhou Erqiang1, Qin Zhen1ORCID, Bi Ting2ORCID, Qin Zhiguang1
Affiliation:
1. School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu 610097, China 2. Department of Computer Science, Maynooth University, W23 F2K8 Maynooth, Ireland
Abstract
An EEG signal (Electroencephalogram) is a bioelectric phenomenon reflecting human brain activities. In this paper, we propose a novel deep learning framework ESML (EEG-based Subject Matching Learning) using raw EEG signals to learn latent representations for EEG-based user identification and tack classification. ESML consists of two parts: one is the ESML1 model via an LSTM-based method for EEG-user linking, and one is the ESML2 model via a CNN-based method for EEG-task linking. The new model ESML is simple, but effective and efficient. It does not require any restrictions for EEG data collection on motions and thinking for users, and it does not need any EEG preprocessing operations, such as EEG denoising and feature extraction. The experiments were conducted on three public datasets and the results show that ESML performs the best and achieves significant performance improvement when compared to baseline methods (i.e., SVM, LDA, NN, DTS, Bayesian, AdaBoost and MLP). The ESML1 model provided the best precision at 96% with 109 users and the ESML2 model achieved 99% precision at 3-Class task classification. These experimental results provide direct evidence that EEG signals can be used for user identification and task classification.
Funder
National Natural Science Foundation of China Sichuan Science and Technology Innovation Platform and Talent Plan Sichuan Science and Technology Support Plan YIBIN Science and Technology Support Plan Medico-Engineering Cooperation Funds from University of Electronic Science and Technology of China
Subject
Behavioral Neuroscience,General Psychology,Genetics,Development,Ecology, Evolution, Behavior and Systematics
Reference69 articles.
1. EEG-based emotion recognition using deep learning network with principal component based covariate shift adaptation;Jirayucharoensak;Sci. World J.,2014 2. An, X., Kuang, D., Guo, X., Zhao, Y., and He, L. (2014, January 3–6). A deep learning method for classification of EEG data based on motor imagery. Proceedings of the International Conference on Intelligent Computing, Taiyuan, China. 3. Deep learning with convolutional neural networks for EEG decoding and visualization;Schirrmeister;Hum. Brain Mapp.,2017 4. Schons, T., Moreira, G.J., Silva, P.H., Coelho, V.N., and Luz, E.J. (2017, January 7–10). Convolutional network for EEG-based biometric. Proceedings of the Iberoamerican Congress on Pattern Recognition, Valparaiso, Chile. 5. Mao, Z., Yao, W.X., and Huang, Y. (2017, January 25–28). EEG-based biometric identification with deep learning. Proceedings of the 2017 8th International IEEE/EMBS Conference on Neural Engineering (NER) IEEE, Shanghai, China.
|
|