一种脑电信号处理方法、装置及终端设备
By establishing a unified latent space structure representation basis and local parameter adaptation mechanism, the problem of unstable model representation in cross-user EEG decoding was solved, achieving high-precision and stable cross-user EEG signal processing, and improving the recognition accuracy and adaptation efficiency of in-vehicle mind control.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- JILIN UNIVERSITY
- Filing Date
- 2026-04-14
- Publication Date
- 2026-07-17
AI Technical Summary
Existing cross-user EEG decoding technologies lack a unified group expression base. When adapting to new users, parameters need to be updated extensively. The model representation structure is easily destroyed, and the cross-user expression form is unstable, resulting in decreased recognition accuracy and drift in the model expression space.
By acquiring EEG signal information from multiple historical users, feature extraction and mapping are performed to generate EEG signal feature information of historical users. A unified latent space structure expression basis is established using a pre-set dictionary of EEG feature representations for user groups. Combined with a local parameter adaptation mechanism, a target EEG signal processing model is generated.
It effectively avoids the problems of decreased recognition accuracy and unstable representation structure caused by individual user differences in traditional EEG decoding models, ensuring that the generation of current user EEG signal processing information is both accurate and stable, and greatly improving the generalization ability and ease of use of cross-user EEG decoding in in-vehicle mind control scenarios.
Smart Images
Figure CN122020613B_ABST
Abstract
Citation Information
Patent Citations
Mechanical arm control method and device based on brain-computer interface and edge computing terminal
CN119937786A