Feature Identification of EEG Preparatory Response Signals Evoked by Motor Intention
FU Rong-rong1,2,LIANG Hai-feng1,MI Rui-fu1
1. School of Electrical Engineering, Yanshan University, Qinhuangdao, Hebei 066004, China
2. Jiangxi new energy technology institute, Xinyu, Jiangxi 338004, China
Abstract：The motor intention contained in the preparation response to electroencephalogram (EEG) signals is extracted and recognized, and the pre-movement EEG patterns is decoded. The experimental results show that using the common spatial pattern (CSP) and extreme learning machines (ELM) can efficiently distinguish the preparation potential of the left and right hands before real movement, and the average recognition accuracy rate of EEG data induced by the preparation before the execution of the brain computer interface (BCI) competition can reach 85.7%. On the decoding problem, compared with motor imagery (MI) EEG signals, the preparatory potential saves the time from consciousness generation to action execution, improves the response efficiency of operational task execution, and provides theoretical basis and technical support for efficient BCI based on motor intention.
He B, Baxter B, Edelman, B J, et al. Noninvasive brain computer interfaces based on sensorimotor rhythms ［J］. Proceedings of the IEEE, 2015, 103(6): 907-925.
Fu R R, Li P, Liu C, et al. Dynamic Motor Imagery Classification with Decision Fusion Based on Linear Discriminant Analysis ［J］. Acta Metrologica Sinica, 2022, 43(5): 688-695.
［4］
Belwafi K, Gannouni S, Aboalsamh H, et al. A dynamic and self-adaptive classification algorithm for motor imagery EEG signals ［J］. Journal of Neuroscience Methods, 2019, 327: 108346.
［6］
Baig M Z, Aslam N, Shum H P H, et al. Differential evolution algorithm as a tool for optimal feature subset selection in motor imagery EEG ［J］. Expert Syst Appl, 2017, 90: 184-195.
［8］
Cheng D, Liu Y, Zhang L. Exploring Motor Imagery EEG Patterns for Stroke Patients with Deep Neural Networks ［C］In Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, Calgary, AB, Canada, 2018, 15-20.
［10］
Jochumsen M, Niazi I K, Taylor D, et al. Detecting and classifying movement-related cortical potentials associated with hand movements in healthy subjects and stroke patients from single-electrode, single-trial EEG ［J］. Journal of Neural Engineering, 2015, 12(5): 056013.
Yu X Y, Luo Z Z. EEG signal denoising based on a wavelet nonlinear continuous function ［J］. Acta Metrologica Sinica, 2017, 38(6): 754-757.
He Q, Du S, Wang Y W, et al. The Classification of EEG Induced by Motor Imagery Based on Variational Mode Decomposition and Deep Belief Network ［J］. Acta Metrologica Sinica, 2020, 41(1): 90-99.
［9］
Pfurtscheller G, Allison B Z, Bauernfeind G, et al. The hybrid BCI ［J］. Frontiers in Neuro Science, 2010, 4: 1283.
Zhang Y, Wang Y, Jin J, et al. Sparse Bayesian learning for obtaining sparsity of EEG frequency bands based feature vectors in motor imagery classification ［J］. Neural Syst, 2017, 27(2): 1650032.
［15］
Huang G B. What are extreme learning machines? Filling the gap between Frank Rosenblatts dream and John von Neumanns puzzle ［J］. Cognitive Computation, 2015, 7(3): 263-278.
Fu R R, Bao T T, Tian Y S, et al. Comparative Study on Denoising Methods of EEG Signals Based on Subcomponent Decomposition ［J］. Acta Metrologica Sinica, 2019, 40(4): 708-713.
［7］
Oikonomou. V P, Georgiadis K, Liaros G, et al. A Comparison Study on EEG Signal Processing Techniques Using Motor Imagery EEG Data ［C］In Proceedings of the IEEE 30th International Symposium on Computer-Based Medical Systems, Thessaloniki, Greece, 2017, 22-24.
［5］
Mattar E A, Al-Junaid H. Electroencephalography Based Dexterous Robotics Hand Grasping and Manipulation: A Short Review ［J］. Robotics & Automation Engineering Journal, 2018, 2 (2): 555-583.
Jin J, Xiao R, Daly I, et al. Internal feature selection method of CSP based on L1-norm and dempster-shafer theory ［J］. IEEE Trans Neural Netw Learn Syst, 2020, 99: 1-12.
2023, Vol. 44 
