Online BCI System for Motor Imagery Based on Sliding Weight Method Under Environmental Noise Interference.
Saved in:
| Title: | Online BCI System for Motor Imagery Based on Sliding Weight Method Under Environmental Noise Interference. |
|---|---|
| Authors: | Yang, Cheng (AUTHOR), Zhang, Ying (AUTHOR), Wang, Shiyu (AUTHOR), Lu, Shan (AUTHOR), Wu, Jianfeng (AUTHOR), Chen, Zhekun (AUTHOR) |
| Source: | International Journal of Human-Computer Interaction. Oct2025, Vol. 41 Issue 20, p12584-12601. 18p. |
| Subjects: | Brain-computer interfaces, Electroencephalography, Feature extraction, Signal processing, Noise pollution, Wheelchairs, Classification, Motor imagery (Cognition) |
| Abstract: | In real-world environments, interferences such as noise, lighting, and vibrations impact users' psychological and motor imagery (MI) EEG signals. Numerous studies focus on the performance of brain-computer interface (BCI) systems in interference-free laboratory environments, leading to significantly reduced accuracy in real-world applications. This study aims to address challenges for motor-disabled individuals using BCI systems in real-world environments, particularly the issues of insufficient system robustness to interference and differences in individual EEG features. This study designed a quantitative EEG experiment with environmental noise, analyzed its impact on EEG features, and constructed an EEG feature extraction and classification model that can adaptively adjust weight coefficients according to the external sound environment. This model was applied to a brain-controlled wheelchair system, achieving over 10% higher average classification accuracy in high-noise environments compared to two classical methods, with a classification speed within 1500 ms, significantly improving the system's noise resistance and generalization ability. [ABSTRACT FROM AUTHOR] |
| Copyright of International Journal of Human-Computer Interaction is the property of Taylor & Francis Ltd and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Psychology and Behavioral Sciences Collection |
|
Full text is not displayed to guests.
Login for full access.
|
|
Be the first to leave a comment!
