Reactive frequency band-based real-time motor imagery classification

2018 ◽  
Vol 17 (1/2) ◽  
pp. 136 ◽  
Author(s):  
Sumanta Bhattacharyya ◽  
Manoj Kumar Mukul
Keyword(s):  
Real Time ◽  
Motor Imagery ◽  
Frequency Band ◽  
Time Motor

scholarly journals CluSem: Accurate Clustering-based Ensemble Method to Predict Motor Imagery Tasks from Multi-channel EEG Data

2021 ◽  
Author(s):  
Md Ochiuddin Miah ◽  
Rafsanjani Muhammod ◽  
Khondaker Abdullah Al Mamun ◽  
Dewan Md. Farid ◽  
Shiu Kumar ◽  
...  
Keyword(s):  
Real Time ◽  
Motor Imagery ◽  
Classification Performance ◽  
Input Devices ◽  
Ensemble Technique ◽  
Source Codes ◽  
Eeg Data ◽  
Time Motor ◽  
Bio Engineering

Background: The classification of motor imagery electroencephalogram (MI-EEG) is a pivotal task in the biosignal classification process in brain-computer interface (BCI) applications. Currently, this bio-engineering-based technology is being employed by researchers in various fields to develop cutting-edge applications. The classification of real-time MI-EEG signals is the most challenging task in these applications. The prediction performance of the existing classification methods is still limited due to the high dimensionality and dynamic behaviors of the real-time EEG data. Proposed Method: To enhance the classification performance of real-time BCI applications, this paper presents a new clustering-based ensemble technique called CluSem to mitigate this problem. We also develop a new brain game called CluGame using this method to evaluate the classification performance of real-time motor imagery movements. In this game, real-time EEG signal classification and prediction tabulation through animated balls are controlled via threads. By playing this game, users can control the movements of the balls via the brain signals of motor imagery movements without using any traditional input devices. Results: Our results demonstrate that CluSem is able to improve the classification accuracy between 5% and 15% compared to the existing methods on our collected as well as the publicly available EEG datasets. The source codes used to implement CluSem and CluGame are publicly available at https://github.com/MdOchiuddinMiah/MI-BCI_ML.

scholarly journals Development of a Real-Time Motor-Imagery-Based EEG Brain-Machine Interface

2018 ◽  
pp. 610-622
Author(s):  
Gal Gorjup ◽  
Rok Vrabič ◽  
Stoyan Petrov Stoyanov ◽  
Morten Østergaard Andersen ◽  
Poramate Manoonpong
Keyword(s):  
Real Time ◽  
Motor Imagery ◽  
Brain Machine Interface ◽  
Machine Interface ◽  
Time Motor

Effect of real-time cortical feedback in motor imagery-based mental practice training

2014 ◽  
Vol 34 (2) ◽  
pp. 355-363 ◽  
Author(s):  
Ou Bai ◽  
Dandan Huang ◽  
Ding-Yu Fei ◽  
Richard Kunz
Keyword(s):  
Real Time ◽  
Motor Imagery ◽  
Mental Practice ◽  
Cortical Feedback

Real-time nonlinear speed control of an induction motor based on a new advanced integral backstepping approach

2019 ◽  
Vol 42 (2) ◽  
pp. 244-258 ◽  
Author(s):  
Bilel Aichi ◽  
Mohamed Bourahla ◽  
Khedidja Kendouci ◽  
Benyounes Mazari
Keyword(s):  
Real Time ◽  
Induction Motor ◽  
High Performance ◽  
Control Method ◽  
Current Control ◽  
Lyapunov Theory ◽  
External Disturbances ◽  
Low Speed ◽  
Backstepping Approach ◽  
Time Motor

This work proposes a robust control scheme of a three-phase induction motor using a new Backstepping approach based on variable gains. Because of the saturation blocks that are essential to protect the control system, the use of conventional integral Backstepping could lead to a modest performance represented by overshooting and strong vibrations in transitional regimes that cause overcurrent. To develop an efficient and simple control algorithm, the variable gains propriety is used in the speed controller to offer a quick response without overshooting with good robustness against external disturbances. The same property has been introduced in current regulation by a different mean in order to develop a new solution to solve obstacles related to very low-speed operations. The asymptotic stability of the global control is proven by Lyapunov theory. The improvement of the new version compared with the classical one was verified by a brief comparative study based on simulation results. The proposed algorithm has been implemented in a dSPACE DS 1104 card, to analyze the real-time motor performance, and to test control sensitivity against parametric variations. The obtained results show a remarkable improvement of the new control concerning rapidity and stability of transient regimes, overtaking elimination and reduction of starting current, with a low algorithm sensitivity against parametric variations. We have also been able to confirm that the new current control method can guarantee optimal regulation in order to achieve a high-performance operation at very low-speed zones, in the presence of various internal and external disturbances.

The Effects of Image Speed on the Performance of a Soccer Task

2008 ◽  
Vol 22 (1) ◽  
pp. 1-17 ◽  
Author(s):  
Jenny O ◽  
Krista J. Munroe-Chandler
Keyword(s):  
Real Time ◽  
Motor Imagery ◽  
Group Performance ◽  
Slow Motion ◽  
Control Group ◽  
Physical Practice ◽  
Error Performance ◽  
Post Intervention ◽  
Motion Imagery ◽  
And Control

The current study tested the timing element of the PETTLEP approach to motor imagery (Holmes & Collins, 2001) by examining the effects of 3 imagery conditions on the performance of a soccer dribbling task. The imagery conditions were also compared with physical-practice and control-group performance. Ninety-seven participants were randomly assigned to 1 of 5 conditions: real-time imagery, slow-motion imagery, slow motion concluded with real-time imagery, physical practice, or control. Results indicated that all 4 experimental groups significantly improved time and error performance to the same degree after the intervention. The control group significantly improved time but not error performance from pre- to post-intervention. The results of the current study provide inconclusive findings related to the timing element of the PETTLEP approach to motor imagery, however, and do suggest that slow motion might be a viable imagery characteristic. Limitations regarding the examination of slow-motion imagery, possible implications of its use, and suggestions for future image-speed research are discussed.

Sign in / Sign up

Export Citation Format

Share Document