Feedback system based on motor imagery brain-computer interface
A motion imagery and feedback system technology, applied in the field of feedback system, can solve the problems of reducing the universality of the system and user experience, lack of instruction feedback paths, etc., and achieve considerable social and economic benefits.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0032] The embodiment of the present invention provides a feedback system based on motor imagery brain-computer interface, the system is used to design the online experiment of user motor imagery feedback, build the EEG signal acquisition device required for the experiment, and then collect the operator's EEG signal data, store it and then perform certain preprocessing, feature extraction, classification and recognition, see figure 1 (a), the feedback system includes: a feedback module 1 , an EEG collector 2 , a wireless transmission module 3 and a terminal device 4 .
[0033] Feedback module 1, used to write feedback interface.
[0034] In actual implementation, the feedback interface can be written and designed under the Matlab platform, and parameters such as target tasks, number of imaginations, and other parameters can be set. The embodiment of the present invention does not limit the setting of the parameters, which can be set according to the needs in practical applica...
Embodiment 2
[0042] The scheme in embodiment 1 is described in detail below in conjunction with specific example, accompanying drawing, see below for details:
[0043] EEG collector 2 collects leads related to motion (14 channels in total, namely AF3, AF4, F3, F4, F7, F8, FC5, FC6, T7, T8, P7, P8, O1, O2, see figure 1 (b) EEG signal.
[0044] The terminal device 4 also includes an initial feedback module and an online feedback module, wherein the specific experimental process of the initial feedback module is as follows: figure 2 Shown:
[0045] 1) To collect real-time EEG without an initial model, the user first rests for 30s, and generates an initial judgment threshold based on the ERD energy value of the last 20s data;
[0046] 2) Enter the MI feedback interface training for 20s, and when the initial judgment threshold is reached, the target command feedback result will be output, otherwise the target command feedback will not be triggered;
[0047] That is, the operation feedback s...
Embodiment 3
[0060] Below in conjunction with specific example, calculation formula, the scheme in embodiment 1, 2 is described in detail, see the following for details:
[0061] 1. ERD energy feature calculation
[0062] For the processing of motor imagery ERD / ERS signals, power spectrum time-frequency analysis is usually used. Short-time Fourier analysis is one of the commonly used time-frequency analysis methods at present. It assumes that EEG signals have a certain degree of short-term stationarity, that is, is that the spectral distribution of the signal is invariant within a finite time window. In the case of no initial model in Example 2, the short-time Fourier transform is used to process the motor imagery EEG to obtain the real-time change of the ERD energy value, and compare it with the initial judgment threshold to determine whether to trigger the target command.
[0063] 2. Binary classification co-space model and support vector machine
[0064] When the data accumulation in ...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com