一种基于特征增强与差异放大的脑电信号识别方法
By constructing a component space filter and a common space pattern algorithm to process EEG signals, the problem of identifying motion-related cortical potentials with high signal-to-noise ratio was solved, the classification accuracy of EEG signals was improved, and the effective application of brain-computer interface systems was realized.
CN117814812BActive Publication Date: 2026-07-17HEBEI UNIV OF TECH
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- HEBEI UNIV OF TECH
- Filing Date
- 2024-02-02
- Publication Date
- 2026-07-17
AI Technical Summary
Technical Problem
In existing technologies, the signal-to-noise ratio of motor-related cortical potentials is high, resulting in poor accuracy in EEG signal recognition and classification, making it difficult to effectively apply to brain-computer interface systems.
Method used
The EEG signal data is filtered by constructing a component space filter, and then horizontally spliced and amplified for differences. Features are extracted using the cospace pattern algorithm and input into a classifier for classification.
Benefits of technology
It improves the classification accuracy of EEG signals and can be effectively applied to motor-related brain-computer interface systems, especially the control of intelligent prostheses and mechanical exoskeletons.
✦ Generated by Eureka AI based on patent content.
Smart Images
Figure CN117814812B_ABST
Abstract
本发明提供了一种基于特征增强与差异放大的脑电信号识别方法，包括以下步骤：S1、根据脑电信号数据的任务类型构建相应的成分空间滤波器；S2、使用成分空间滤波器对脑电信号数据进行滤波处理；S3、将经过滤波处理的相同任务类型的脑电信号数据进行横向拼接形成增强脑电信号数据；S4、利用共空间模式算法增强脑电信号数据进行差异放大与特征提取，将特征输入至分类器进行分类。本发明有益效果：本发明所提出的方法通过脑电信号数据进行特征增强和差异放大，能够有效提取MRCPs信号的微弱特征并获得良好的分类精度，能够有效应用于运动相关的脑机接口系统中。
Need to check novelty before this filing date? Find Prior Art