Brain-computer interface (BCI) technology enables the direct transmission of human control intentions to external devices, allowing direct control of external devices through the human brain. However, the current implementation of BCIs is limited by the low accuracy of electroencephalogram (EEG) classification. In this study, we applied Gaussian distribution model as a preprocessing tool to screen and filter EEG training data samples, aiming to improve the classification accuracy of motor imagery tasks. Firstly, the Gaussian distribution model was established through small sample pre-training. Subsequently, a probability threshold was determined based on the two types of Gaussian model distributions corresponding to the imagery of the left and right hands. This threshold was used to screen and filter subsequent training samples. Our results demonstrated that this proposed method effectively enhanced the accuracy of motor imagery task classification, and significant improvements were observed in public datasets. This study emphasizes the importance of data screening in ensuring the quality and reliability of training data, thereby presenting promising opportunities for the practical implementation of BCI technology.
Improving Motor Imagery Brain-Computer Interface Performance Through Data Screening
Lect.Notes Computer
International Conference on Intelligent Robotics and Applications ; 2023 ; Hangzhou, China July 05, 2023 - July 07, 2023
21.10.2023
11 pages
Aufsatz/Kapitel (Buch)
Elektronische Ressource
Englisch
Brain Computer Interface , Gaussian Distribution Model , EEG Data Screening , Motor Imagery Computer Science , Artificial Intelligence , Software Engineering/Programming and Operating Systems , Computer Applications , Computer Communication Networks , Special Purpose and Application-Based Systems , User Interfaces and Human Computer Interaction
Kinesthetic Motor Imagery Based Brain-Computer Interface for Power Wheelchair Manoeuvring
BASE | 2018
|Partial Directed Coherence for the Classification of Motor Imagery-Based Brain-Computer Interface
Springer Verlag | 2022
|