Abstract
Driver states are reported as one of the principal factors in driving safety. Distinguishing the driving driver state based on the artifact-free electroencephalogram (EEG) signal is an effective means, but redundant information and noise will inevitably reduce the signal-to-noise ratio of the EEG signal. This study proposes a method to automatically remove electrooculography (EOG) artifacts by noise fraction analysis. Specifically, multi-channel EEG recordings are collected after the driver experiences a long time driving and after a certain period of rest respectively. Noise fraction analysis is then applied to remove EOG artifacts by separating the multichannel EEG into components by optimizing the signal-to-noise quotient. The representation of data characteristics of the EEG after denoising is found in the Fisher ratio space. Additionally, a novel clustering algorithm is designed to identify denoising EEG by combining cluster ensemble and probability mixture model (CEPM). The EEG mapping plot is used to illustrate the effectiveness and efficiency of noise fraction analysis on the denoising of EEG signals. Adjusted rand index (ARI) and accuracy (ACC) are used to demonstrate clustering performance and precision. The results showed that the noise artifacts in the EEG were removed and the clustering accuracy of all participants was above 90%, resulting in a high driver fatigue recognition rate.
Funding source: National Natural Science Foundation of China
Award Identifier / Grant number: 62073282
Funding source: Central Guidance on Local Science and Technology Development Fund of Hebei Province
Award Identifier / Grant number: 206Z0301G
Funding source: Natural Science Foundation of Hebei Province
Award Identifier / Grant number: E2018203433
Acknowledgments
Thanks to all participants of the experiments.
-
Research funding: This work was supported by the National Natural Science Foundation of China [grant number 62073282]; the Central Guidance on Local Science and Technology Development Fund of Hebei Province [grant number 206Z0301G]; Natural Science Foundation of Hebei Province [grant number E2018203433];
-
Author contributions: Rongrong Fu supervised the entire experimental process. Zheyu Li conducted data analysis and wrote the first draft. Dong Xu verified the data analysis. Xiaodong Huang made suggestions on the theoretical aspects of the study. Haifeng Liang corrected the manuscript. Final manuscript read and approved by all authors.
-
Competing interests: There is no conflict of interest with any for-profit company or institution, and manuscript is approved by all authors for publication.
-
Informed consent: The subjects were informed of the content, nature, and purpose of the experiment, after which they all voluntarily signed the experimental informed consent form.
-
Ethical approval: This study was approved by the Ethics Committee of the First Hospital of Qinhuangdao City.
References
1. Pan, Y, Tsang, IW, Lyu, Y, Singh, AK, Lin, C-T. Online mental fatigue monitoring via indirect brain dynamics evaluation. Neural Comput 2021;33:1616–55. https://doi.org/10.1162/neco_a_01382.Search in Google Scholar PubMed
2. Useche, SA, Cendales, B, Lijarcio, I, Llamazares, FJ. Validation of the F-DBQ: a short (and accurate) risky driving behavior questionnaire for long-haul professional drivers. Transport Res F Traffic Psychol Behav 2021;82:190–201. https://doi.org/10.1016/j.trf.2021.08.013.Search in Google Scholar
3. Pan, Y, Tsang, IW, Singh, AK, Lin, C-T, Sugiyama, M. Stochastic multichannel ranking with brain dynamics preferences. Neural Comput 2020;32:1499–530. https://doi.org/10.1162/neco_a_01293.Search in Google Scholar PubMed
4. Daryanavard, S, Porr, B. Closed-loop deep learning: generating forward models with backpropagation. Neural Comput 2020;32:2122–44. https://doi.org/10.1162/neco_a_01317.Search in Google Scholar PubMed
5. Tuckute, G, Hansen, ST, Kjaer, TW, Hansen, LK. Real-time decoding of attentional states using closed-loop EEG neurofeedback. Neural Comput 2021;33:967–1004. https://doi.org/10.1162/neco_a_01363.Search in Google Scholar PubMed
6. Wang, F, Wang, H, Zhou, X, Fu, R. A driving fatigue feature detection method based on multifractal theory. IEEE Sens J 2022;22:19046–59. https://doi.org/10.1109/JSEN.2022.3201015.Search in Google Scholar
7. Canale, F, Trojsi, F, Di Nardo, F, Siciliano, M, D’Alvano, G, Passaniti, C, et al.. “Mental” component of fatigue correlates with cognitive and behavioral impairment in amyotrophic lateral sclerosis. J Neurol Sci 2021;429:119379. https://doi.org/10.1016/j.jns.2021.119379.Search in Google Scholar
8. Orlando, G, Balducci, S, Boulton, AJM, Degens, H, Reeves, ND. Neuromuscular dysfunction and exercise training in people with diabetic peripheral neuropathy: a narrative review. Diabetes Res Clin Pract 2022;183:109183. https://doi.org/10.1016/j.diabres.2021.109183.Search in Google Scholar PubMed
9. Douma, B, Derbali, H, Messelmani, M, Elfekih, M, Mansour, M, Zaouali, J, et al.. Fatigue in multiple sclerosis: physical, cognitive and psychosocial impact. J Neurol Sci 2021;429:118135. https://doi.org/10.1016/j.jns.2021.118135.Search in Google Scholar
10. Abu, MA, Ishak, ID, Basarudin, H, Ramli, AF, Shapiai, MI. Fatigue and drowsiness detection system using artificial intelligence technique for car drivers. In: Ismail A, Dahalan WM, Öchsner A, editors. Design in Maritime Engineering. Advanced Structured Materials. Springer, Cham; 2022, vol 167:421–30 pp.10.1007/978-3-030-89988-2_31Search in Google Scholar
11. Husna, M, Rianawati, S, Afif, Z, Damayanti, Y. Correlation between the occurrence of seizures and EEG results. J Neurol Sci 2021;429:118551. https://doi.org/10.1016/j.jns.2021.118551.Search in Google Scholar
12. Giugno, A, Sammarra, I, Sturniolo, M, Zoleo, P, Rubino, V, Labate, A, et al.. Usefulness of 24-hour ambulatory EEG monitoring in the diagnosis of typical absences. J Neurol Sci 2021;429:117684. https://doi.org/10.1016/j.jns.2021.117684.Search in Google Scholar
13. Li, C, Wang, B, Zhang, S, Liu, Y, Song, R, Cheng, J, et al.. Emotion recognition from EEG based on multi-task learning with capsule network and attention mechanism. Comput Biol Med 2022;143:105303. https://doi.org/10.1016/j.compbiomed.2022.105303.Search in Google Scholar PubMed
14. Panchal, S, T, SI, Uniyal, S, Tantry, S. Design and implementation of low noise amplifier and variable gain amplifier for ECG systems. In: 2022 IEEE 7th Int. Conf. Converg. Technol. IEEE; 2022:1–6 pp.10.1109/I2CT54291.2022.9824947Search in Google Scholar
15. Hou, C, Cai, F, Liu, F, Cheng, S, Wang, H. A method for removing ECG interference from lumbar EMG based on signal segmentation and SSA. IEEE Sens J 2022;22:13309–17. https://doi.org/10.1109/JSEN.2022.3179434.Search in Google Scholar
16. Islam, MK, Ghorbanzadeh, P, Rastegarnia, A. Probability mapping based artifact detection and removal from single-channel EEG signals for brain–computer interface applications. J Neurosci Methods 2021;360:109249. https://doi.org/10.1016/j.jneumeth.2021.109249.Search in Google Scholar PubMed
17. Reijntjes, RH, Potters, WV, Kerkhof, FI, van Zwet, E, van Rossum, IA, Verhamme, C, et al.. Deriving reference values for nerve conduction studies from existing data using mixture model clustering. Clin Neurophysiol 2021;132:1820–9. https://doi.org/10.1016/j.clinph.2021.04.013.Search in Google Scholar PubMed
18. Xu, L, Ding, S. Dual-granularity weighted ensemble clustering. Knowl Base Syst 2021;225:107124. https://doi.org/10.1016/j.knosys.2021.107124.Search in Google Scholar
19. Lu, C, Feng, J, Lin, Z, Mei, T, Yan, S. Subspace clustering by block diagonal representation. IEEE Trans Pattern Anal Mach Intell 2019;41:487–501. https://doi.org/10.1109/TPAMI.2018.2794348.Search in Google Scholar PubMed
20. Tarnutzer, AA, Weber, KP. Pattern analysis of peripheral-vestibular deficits with machine learning using hierarchical clustering. J Neurol Sci 2022;434:120159. https://doi.org/10.1016/j.jns.2022.120159.Search in Google Scholar PubMed
21. Tang, X-L, Ma, W-C, Kong, D-S, Li, W. Semisupervised deep stacking network with adaptive learning rate strategy for motor imagery EEG recognition. Neural Comput 2019;31:919–42. https://doi.org/10.1162/neco_a_01183.Search in Google Scholar PubMed
22. Ojeda, A, Kreutz-Delgado, K, Mishra, J. Bridging M/EEG source imaging and independent component analysis frameworks using biologically inspired sparsity priors. Neural Comput 2021;33:2408–38. https://doi.org/10.1162/neco_a_01415.Search in Google Scholar PubMed PubMed Central
23. Mumtaz, W, Rasheed, S, Irfan, A. Review of challenges associated with the EEG artifact removal methods. Biomed Signal Process Control 2021;68:102741. https://doi.org/10.1016/j.bspc.2021.102741.Search in Google Scholar
24. Takahashi, N, Ishigami, S, Kawamata, K. Basic study of electromagnetic noise waveform extraction using independent component analysis. In: 2021 IEEE Asia-Pacific Microw. Conf. IEEE; 2021:473–5 pp.10.1109/APMC52720.2021.9661884Search in Google Scholar
25. Fei, S, Chu, Y. A novel classification strategy of motor imagery EEG signals utilizing WT-PSR-SVD-based MTSVM. Expert Syst Appl 2022;199:116901. https://doi.org/10.1016/j.eswa.2022.116901.Search in Google Scholar
26. Abdi-Sargezeh, B, Foodeh, R, Shalchyan, V, Daliri, MR. EEG artifact rejection by extracting spatial and spatio-spectral common components. J Neurosci Methods 2021;358:109182. https://doi.org/10.1016/j.jneumeth.2021.109182.Search in Google Scholar PubMed
27. Marriott Haresign, I, Phillips, E, Whitehorn, M, Noreika, V, Jones, EJH, Leong, V, et al.. Automatic classification of ICA components from infant EEG using MARA. Dev Cognit Neurosci 2021;52:101024. https://doi.org/10.1016/j.dcn.2021.101024.Search in Google Scholar PubMed PubMed Central
28. Tuta, L, Rosu, G, Popovici, C, Nicolaescu, I. Real-time EEG data processing using independent component analysis (ICA). In: 2022 14th Int. Conf. Commun. IEEE; 2022:1–4 pp.10.1109/COMM54429.2022.9817209Search in Google Scholar
29. Hu, G, Zhang, Q, Waters, AB, Li, H, Zhang, C, Wu, J, et al.. Tensor clustering on outer-product of coefficient and component matrices of independent component analysis for reliable functional magnetic resonance imaging data decomposition. J Neurosci Methods 2019;325:108359. https://doi.org/10.1016/j.jneumeth.2019.108359.Search in Google Scholar PubMed
30. Nandi, S, Subba Reddy, B. Understanding Failure analysis using harmonic analysis and empirical mode decomposition techniques. Eng Fail Anal 2022;139:106442. https://doi.org/10.1016/j.engfailanal.2022.106442.Search in Google Scholar
31. Wang, J-Y, Dai, Y-H, Si, X-X. Feature layer fusion of linear features and empirical mode decomposition of human EMG signal. J Electron Sci Technol 2022;20:100169. https://doi.org/10.1016/j.jnlest.2022.100169.Search in Google Scholar
32. Li, K, Wang, Y, Chen, Z. A comparative study of battery state-of-health estimation based on empirical mode decomposition and neural network. J Energy Storage 2022;54:105333. https://doi.org/10.1016/j.est.2022.105333.Search in Google Scholar
33. Shang, X, Liu, S, Wan, W, Liu, L. Complementary ensemble empirical mode decomposition based microwave induced thermoacoustic image reconstruction method. In: 2022 IEEE MTT-S Int. Microw. Biomed. Conf. IEEE; 2022:229–31 pp.10.1109/IMBioC52515.2022.9790144Search in Google Scholar
34. Yuan, J, Xu, C, Zhao, Q, Jiang, H, Weng, Y. High-fidelity noise-reconstructed empirical mode decomposition for mechanical multiple and weak fault extractions. ISA Trans 2022;129:380–97. https://doi.org/10.1016/j.isatra.2022.02.017.Search in Google Scholar PubMed
35. Wen, Y, Zhang, Y, Wen, L, Cao, H, Ai, G, Gu, M, et al.. A 65 nm/0.448 mW EEG processor with parallel architecture SVM and lifting wavelet transform for high-performance and low-power epilepsy detection. Comput Biol Med 2022;144:105366. https://doi.org/10.1016/j.compbiomed.2022.105366.Search in Google Scholar PubMed
36. Shahbakhti, M, Beiramvand, M, Nazari, M, Broniec-Wojcik, A, Augustyniak, P, Rodrigues, AS, et al.. An efficient algorithm for detection and elimination of eye blink from short segments of single EEG channel. IEEE Trans Neural Syst Rehabil Eng 2021;29:408–17. https://doi.org/10.1109/TNSRE.2021.3054733.Search in Google Scholar PubMed
37. Shahbakhti, M, Maugeon, M, Beiramvand, M, Marozas, V. Low complexity automatic stationary wavelet transform for elimination of eye blinks from EEG. Brain Sci 2019;9:352. https://doi.org/10.3390/brainsci9120352.Search in Google Scholar PubMed PubMed Central
38. Chavez, M, Grosselin, F, Bussalb, A, De Vico Fallani, F, Navarro-Sune, X. Surrogate-based artifact removal from single-channel EEG. IEEE Trans Neural Syst Rehabil Eng 2018;26:540–50. https://doi.org/10.1109/TNSRE.2018.2794184.Search in Google Scholar PubMed
39. Noorbasha, SK, Sudha, GF. Removal of EOG artifacts from single channel EEG – an efficient model combining overlap segmented ASSA and ANC. Biomed Signal Process Control 2020;60:101987. https://doi.org/10.1016/j.bspc.2020.101987.Search in Google Scholar
40. Foodeh, R, Khorasani, A, Shalchyan, V, Daliri, MR. Minimum noise estimate filter: a novel automated artifacts removal method for field potentials. IEEE Trans Neural Syst Rehabil Eng 2017;25:1143–52. https://doi.org/10.1109/TNSRE.2016.2606416.Search in Google Scholar PubMed
41. Foodeh, R, Shalchyan, V, Daliri, MR. GMMPLS: a novel automatic state-based algorithm for continuous decoding in BMIs. IEEE Access 2021;9:148756–70. https://doi.org/10.1109/ACCESS.2021.3123098.Search in Google Scholar
42. Foodeh, R, Ebadollahi, S, Daliri, MR. Regularized partial least square regression for continuous decoding in brain-computer interfaces. Neuroinformatics 2020;18:465–77. https://doi.org/10.1007/s12021-020-09455-x.Search in Google Scholar PubMed
43. Buzzell, GA, Niu, Y, Aviyente, S, Bernat, E. A practical introduction to EEG time-frequency principal components analysis (TF-PCA). Dev Cognit Neurosci 2022;55: 101114. https://doi.org/10.1016/j.dcn.2022.101114.Search in Google Scholar PubMed PubMed Central
44. She, K, Dai, C, Ding, Y. Application of logistic regression and principal component analysis in TCM diagnosis and treatment. In: 2021 4th Int. Conf. Adv. Electron. Mater. Comput. Softw. Eng. IEEE; 2021:726–9 pp.10.1109/AEMCSE51986.2021.00150Search in Google Scholar
45. Yu, M, Li, C, Xu, B, Li, Y. GMSK modulated DSSS signal separation based on principal component analysis. In: 2020 IEEE 20th Int. Conf. Commun. Technol. IEEE; 2020:1271–5 pp.10.1109/ICCT50939.2020.9295670Search in Google Scholar
46. Yan, T, Wang, D, Zheng, M, Xia, T, Pan, E, Xi, L. Fisher’s discriminant ratio based health indicator for locating informative frequency bands for machine performance degradation assessment. Mech Syst Signal Process 2022;162:108053. https://doi.org/10.1016/j.ymssp.2021.108053.Search in Google Scholar
47. Golalipour, K, Akbari, E, Hamidi, SS, Lee, M, Enayatifar, R. From clustering to clustering ensemble selection: a review. Eng Appl Artif Intell 2021;104:104388. https://doi.org/10.1016/j.engappai.2021.104388.Search in Google Scholar
48. Zhong, C, Hu, L, Yue, X, Luo, T, Fu, Q, Xu, H. Ensemble clustering based on evidence extracted from the co-association matrix. Pattern Recognit 2019;92:93–106. https://doi.org/10.1016/j.patcog.2019.03.020.Search in Google Scholar
49. Li, Z, Liu, K, Deng, X, Wang, G. Spatial fusion of maximum signal fraction analysis for frequency recognition in SSVEP-based BCI. Biomed Signal Process Control 2020;61:102042. https://doi.org/10.1016/j.bspc.2020.102042.Search in Google Scholar
50. Short, M, Woll, K. An expansion of the Fisher model for concentration dependent grain boundary diffusion. Acta Mater 2021;217:117056. https://doi.org/10.1016/j.actamat.2021.117056.Search in Google Scholar
51. Schöneich, S, Ochoa, GS, Monzón, CM, Synovec, RE. Minimum variance optimized Fisher ratio analysis of comprehensive two-dimensional gas chromatography/mass spectrometry data: study of the pacu fish metabolome. J Chromatogr A 2022;1667:462868. https://doi.org/10.1016/j.chroma.2022.462868.Search in Google Scholar PubMed
52. Fu, R, Bao, T, Tian, Y, Wang, L. Comparative study on EEG signal denoising methods based on subcomponent decomposition. J Metrol 2019;40:708–13. https://doi.org/10.3969/j.issn.1000-1158.2019.04.27.Search in Google Scholar
53. Cherradi, B, Terrada, O, Ouhmida, A, Hamida, S, Raihani, A, Bouattane, O. Computer-aided diagnosis system for early prediction of atherosclerosis using machine learning and K-fold cross-validation. In: 2021 Int. Congr. Adv. Technol. Eng. IEEE; 2021:1–9 pp.10.1109/ICOTEN52080.2021.9493524Search in Google Scholar
54. Shahbakhti, M, Beiramvand, M, Rejer, I, Augustyniak, P, Broniec-Wojcik, A, Wierzchon, M, et al.. Simultaneous eye blink characterization and elimination from low-channel prefrontal EEG signals enhances driver drowsiness detection. IEEE J Biomed Health Inf 2022;26:1001–12. https://doi.org/10.1109/JBHI.2021.3096984.Search in Google Scholar PubMed
© 2023 Walter de Gruyter GmbH, Berlin/Boston
