Analysis of complex cognitive task and pattern recognition using distributed patterns of EEG signals with cognitive func
- PDF / 1,914,220 Bytes
- 10 Pages / 595.276 x 790.866 pts Page_size
- 21 Downloads / 161 Views
(0123456789().,-volV)(0123456789(). ,- volV)
S.I. : BIO-INSPIRED COMPUTING FOR DLA
Analysis of complex cognitive task and pattern recognition using distributed patterns of EEG signals with cognitive functions Jianyu Zhao1 • Ke Li1 • Xi Xi2 • Shanshan Wang3 • Vijayalakshmi Saravanan4 • R. Dinesh Jackson Samuel5 Received: 26 June 2020 / Accepted: 10 October 2020 Springer-Verlag London Ltd., part of Springer Nature 2020
Abstract The arrangement and functional distribution of an EEG signal structure related to higher cortical functions are being analyzed by both recent and substantial hypothesis experiments. This article provides a technique for analyzing the distribution pattern of EEG signals with cognitive functions utilizing the variational pattern recognition based on brain computation. The nonparametric rules of decision reveal vital EEG patterns that distinguish between several tasks. The general truth of findings is measured by the cross-validation recognition rate. This method is employed to derive signals from a group of adults performing several complex works. These cognitive signals that distinguish between assignments are keeping with visual EEG understandings and spectral intensity analysis and enhance the results. Since tasks recognized, it is clear that EEG signals can distinguish that complex behavior or sensory-motivating and performancerelated factors that are related to the cognitive components of the work. The obtained results achieve high accuracy and sensitivity rate with less error rate. Keywords Complex cognitive task Cognitive functions Pattern recognition EEG signals
1 Background of the study & Jianyu Zhao [email protected] & Xi Xi [email protected] Ke Li [email protected] Shanshan Wang [email protected] Vijayalakshmi Saravanan [email protected] R. Dinesh Jackson Samuel [email protected] 1
School of Economics and Management, Harbin Engineering University, Harbin, P.R. China
2
Management School, Harbin University of Commerce, Harbin, P.R. China
3
College of Innovative Business and Accountancy, Dhurakij Pundit University, Bangkok, Thailand
4
Ryerson University, Toronto, Canada
5
Faculty of Technology, Design and Environment, Visual Artificial Intelligence Lab, Oxford Brookes University, Oxford, UK
Electroencephalography (EEG) is a neuroimaging technique used in brain information processing that is used for the electric potential of the brain [1], often used for the study, and the diagnosis of dynamics. Large quantities of EEG data are recorded, and EEG data cannot be visually analyzed [2, 3]. Therefore, the relevant information from EEG records must be collected for evaluation and accurate cognitive process knowledge. There is a collection of large amounts of EEG [4] data that cannot be visually analyzed. Detailed knowledge from the EEG signal must be retrieved to determine and understand desirable cognitive processes [5]. The key measures to extract proper knowledge from EEG data are preprocessing extraction and classification of features [6–8]. The main ste
Data Loading...
