Off-line and on-line vigilance estimation based on linear dynamical system and manifold learning
- PMID:21096513
- DOI: 10.1109/IEMBS.2010.5627125
Off-line and on-line vigilance estimation based on linear dynamical system and manifold learning
Abstract
For many human machine interaction systems, to ensure work safety, the techniques for continuously estimating the vigilance of operators are highly desirable. Up to now, various methods based on electroencephalogram (EEG) are proposed to solve this problem. However, most of them are static methods and are based on supervised learning strategy. The main deficiencies of the existing methods are that the label information is hard to get and the time dependency of vigilance changes are ignored. In this paper, we introduce the dynamic characteristics of vigilance changes into vigilance estimation and propose a novel model based on linear dynamical system and manifold learning techniques to implement off-line and online vigilance estimation. In this model, both spatial information of EEG and temporal information of vigilance changes are used. The label information what we need is merely to know which EEG indices are important for vigilance estimation. Experimental results show that the mean off-line and on-line correlation coefficients between estimated vigilance level and local error rate in second-scale without being averaged are 0.89 and 0.83, respectively.
Similar articles
- A multimodal approach to estimating vigilance using EEG and forehead EOG.Zheng WL, Lu BL.Zheng WL, et al.J Neural Eng. 2017 Apr;14(2):026017. doi: 10.1088/1741-2552/aa5a98. Epub 2017 Jan 19.J Neural Eng. 2017.PMID:28102833
- Dynamic clustering for vigilance analysis based on EEG.Shi LC, Lu BL.Shi LC, et al.Annu Int Conf IEEE Eng Med Biol Soc. 2008;2008:54-7. doi: 10.1109/IEMBS.2008.4649089.Annu Int Conf IEEE Eng Med Biol Soc. 2008.PMID:19162592
- A robust principal component analysis algorithm for EEG-based vigilance estimation.Shi LC, Duan RN, Lu BL.Shi LC, et al.Annu Int Conf IEEE Eng Med Biol Soc. 2013;2013:6623-6. doi: 10.1109/EMBC.2013.6611074.Annu Int Conf IEEE Eng Med Biol Soc. 2013.PMID:24111261
- Assessment of Wakefulness and Brain Arousal Regulation in Psychiatric Research.Sander C, Hensch T, Wittekind DA, Böttger D, Hegerl U.Sander C, et al.Neuropsychobiology. 2015;72(3-4):195-205. doi: 10.1159/000439384. Epub 2016 Feb 23.Neuropsychobiology. 2015.PMID:26901462Review.
- On the Nature of Vigilance.Hancock PA.Hancock PA.Hum Factors. 2017 Feb;59(1):35-43. doi: 10.1177/0018720816655240.Hum Factors. 2017.PMID:28146675Review.
Cited by
- Cross-Subject EEG Emotion Recognition With Self-Organized Graph Neural Network.Li J, Li S, Pan J, Wang F.Li J, et al.Front Neurosci. 2021 Jun 9;15:611653. doi: 10.3389/fnins.2021.611653. eCollection 2021.Front Neurosci. 2021.PMID:34177441Free PMC article.
- Multi-Scale Frequency Bands Ensemble Learning for EEG-Based Emotion Recognition.Shen F, Peng Y, Kong W, Dai G.Shen F, et al.Sensors (Basel). 2021 Feb 10;21(4):1262. doi: 10.3390/s21041262.Sensors (Basel). 2021.PMID:33578835Free PMC article.
- Discriminative possibilistic clustering promoting cross-domain emotion recognition.Dan Y, Zhou D, Wang Z.Dan Y, et al.Front Neurosci. 2024 Nov 1;18:1458815. doi: 10.3389/fnins.2024.1458815. eCollection 2024.Front Neurosci. 2024.PMID:39554850Free PMC article.
- A Novel Psychotherapy Effect Detector of Public Art Based on ResNet and EEG Imaging.Tian T, Wang L, Luo M, Zhu W.Tian T, et al.Comput Math Methods Med. 2022 Apr 7;2022:4909294. doi: 10.1155/2022/4909294. eCollection 2022.Comput Math Methods Med. 2022.PMID:35432582Free PMC article.
- EEG Signal Feature Selection Algorithm and Support Vector Machine Model in Patient's Fatigue Recognition.Chitti S, Kumar JT, Kumar VS.Chitti S, et al.Arab J Sci Eng. 2021 Oct 5:1-7. doi: 10.1007/s13369-021-06206-1. Online ahead of print.Arab J Sci Eng. 2021.PMID:34631359Free PMC article.