一种基于脑电时变性检测的自适应集成脑-机接口解码算法
By integrating Bayesian linear regression with Gaussian mixture models, the time-varying nature of EEG signals is detected and model parameters are adjusted, solving the problems of insufficient stability and accuracy of adaptive brain-computer interface decoding algorithms and achieving more efficient EEG signal decoding.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- HEBEI UNIV OF TECH
- Filing Date
- 2022-10-18
- Publication Date
- 2026-07-17
AI Technical Summary
Existing adaptive brain-computer interface decoding algorithms suffer from insufficient stability and accuracy in adapting to the time-varying nature of EEG signals. In particular, supervised algorithms require a large amount of label information, unsupervised algorithms have low accuracy, and ensemble algorithms have low computational efficiency, making it difficult to adapt to complex changes in EEG signal features.
An ensemble model composed of Bayesian linear regression and Gaussian mixture model was adopted to detect changes in EEG characteristics by means of sample distribution differences, and the model parameters were adjusted by weight coefficients to achieve adaptive adjustment of the time-varying nature of EEG signals.
It improves the stability and decoding accuracy of brain-computer interfaces, enhances anti-interference capabilities, and better adapts to the time-varying nature of EEG signals, thereby improving the stability and accuracy of the system.
Smart Images
Figure CN115480648B_ABST