Method for removing noise signals in brain-computer interface through force-electric decoupling method
Through the force electrostatic decoupling method and machine learning method, the noise problem caused by the electric motor effect is solved, and the signal quality and decoding accuracy are improved.
Patent Information
- Application Number
- CN202510576580.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-05-06
- Publication Date
- 2025-09-05
AI Technical Summary
The existing denoising methods are difficult to effectively distinguish and remove noise signals caused by electric kinetic effects, especially in dynamic mechanical environments, which affects the quality and decoding accuracy of brain-computer interface signals.
The force electrostatic decoupling method is used to decouple the signals in the brain-computer interface through the force-electroconstitutive relationship of liquid-containing porous materials, and the mechanical load changes in brain tissue are monitored by force collectors, and interfering electrical signals are separated in combination with machine learning methods to retain the electrical signals conducted by nerve fibers.
It effectively removes the noise signal generated by the electric kinetic effect, accurately obtains the electrical signal conducted by the nerve fibers, and improves the signal quality and decoding accuracy.
Smart Images
Figure CN120596790A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of brain-computer interface signal processing, and specifically to a method for removing noise signals in a brain-computer interface by using a force-electric decoupling method. Background Art
[0002] With the rapid development of brain-computer interface (BCI) technology, its applications in medical rehabilitation, human-computer interaction, neuroscience research, and other fields are becoming increasingly widespread. However, in practical applications, the neural electrical signals collected by BCIs are often subject to various types of noise interference, particularly noise caused by the electrokinetic effect. The electrokinetic effect is caused by the movement of ions in a porous material containing a liquid under the action of mechanical forces, resulting in electrical signal interference. For example, small mechanical loads (periodic, impact, or continuous) in brain tissue or implantable devices can induce this type of noise. This noise signal can overlap with the actual electrical signals conducted by nerve fibers, severely affecting signal quality and subsequent decoding accuracy. The brain, as a typical porous material containing a liquid, begins to deform under the influence of force signals, either due to physical or spontaneous movements, affecting fluid flow. At this time, the large number of ions in the cerebrospinal fluid can generate electrokinetic phenomena with brain tissue, affecting signal acquisition.
[0003] Existing denoising methods typically rely on filter design, signal separation algorithms, or hardware shielding. However, these methods struggle to effectively distinguish between noise signals caused by the electrokinetic effect and true neural electrical signals, particularly in dynamic mechanical environments. Therefore, a new method that can effectively remove electrokinetic noise signals is urgently needed. Summary of the Invention
[0004] In order to solve the problems of the prior art, the present invention provides a method for removing noise signals in the brain-computer interface through the electrokinetic decoupling method, which can effectively remove the noise signals generated by the electrokinetic effect in the brain-computer interface and accurately obtain the electrical signals conducted by nerve fibers.
[0005] The present invention provides a method for removing noise signals in a brain-computer interface through a force-electric decoupling method. The method collects signals generated in the brain-computer interface, including electrical signals conducted by nerve fibers and interfering electrical signals. The interfering electrical signals are decoupled and removed through the force-electric constitutive relationship of liquid-containing porous materials, and what remains is the electrical signals conducted by the nerve fibers.
[0006] As a further improvement, the signals generated in the brain-computer interface are collected through a brain-computer interface chip, and a force collector is integrated on the brain-computer interface chip. The force collector is used to monitor the changes in mechanical load of brain tissue or implanted area in real time.
[0007] As a further improvement, the interfering electrical signal is an electrical signal caused by force signals generated by various loads in the brain.
[0008] According to a further improvement, the various loads in the brain include periodic loads, impact loads, and continuous loads.
[0009] As a further improvement, the various loads in the brain are caused by action potentials, which are specifically signals generated by heartbeats, eyelid blinking, limb movements, and blood flow.
[0010] As a further improvement, the process of decoupling the electrical signals caused by the force signals of various loads in the brain is as follows: first, the force signals are decomposed into different types and converted into corresponding electrokinetic signals, and then the electrokinetic signals are separated from the original collected electrical signals to retain the real electrical signals conducted by nerve fibers. The separation formula is as follows: ; in, It is the electrical signal conducted by nerve fibers. It is an interfering electrical signal. It is the electrical signal collected by the electrical sensor; interference electrical signal It is mainly related to the magnitude of the force and the loading speed, namely: ; in, is the force signal collected by the force sensor, is the force loading rate, and the f function represents different types of mechanical-electrical constitutive relations.
[0011] As a further improvement, the different types of mechanical-electrical constitutive relations f functions are obtained by a machine learning method; the machine learning method first constructs a data set and then selects a model for training:
[0012] Among them, m and n are the weight coefficients of the influence of force and force loading speed on the electrical signal, For different force types:
[0013] Among them, i represents different force types, for example, a cyclically loaded force signal (heart beating), a suddenly loaded force signal (eyelid blinking), and a loaded and maintained force signal (body position change). The beneficial effect of the present invention is that it can effectively remove the noise signal generated by the electrokinetic effect in the brain-computer interface and accurately obtain the electrical signals conducted by nerve fibers.
[0014] The beneficial effects of the present invention are that it can effectively remove noise signals generated by the electrokinetic effect in the brain-computer interface and accurately obtain the electrical signals conducted by nerve fibers. BRIEF DESCRIPTION OF THE DRAWINGS
[0015] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.
[0016] Figure 1 Schematic diagram of the signal removal process. DETAILED DESCRIPTION
[0017] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.
[0018] The present invention provides a method for removing noise signals in a brain-computer interface through a force-electric decoupling method. The method collects signals generated in the brain-computer interface, including electrical signals conducted by nerve fibers and interfering electrical signals. The interfering electrical signals are decoupled and removed through the force-electric constitutive relationship of liquid-containing porous materials, and what remains is the electrical signals conducted by the nerve fibers.
[0019] As a further improvement, the signals generated in the brain-computer interface are collected through a brain-computer interface chip, and a force collector is integrated on the brain-computer interface chip. The force collector is used to monitor the changes in mechanical load of brain tissue or implanted area in real time.
[0020] As a further improvement, the interfering electrical signal is an electrical signal caused by force signals generated by various loads in the brain.
[0021] According to a further improvement, the various loads in the brain include periodic loads, impact loads, and continuous loads.
[0022] As a further improvement, the various loads in the brain are caused by action potentials, which are specifically signals generated by heartbeats, eyelid blinking, limb movements, and blood flow.
[0023] As a further improvement, the process of decoupling the electrical signals caused by the force signals of various loads in the brain is as follows: first, the force signals are decomposed into different types and converted into corresponding electrokinetic signals, and then the electrokinetic signals are separated from the original collected electrical signals to retain the real electrical signals conducted by nerve fibers. The separation formula is as follows: ; in, It is the electrical signal conducted by nerve fibers. It is an interfering electrical signal. It is the electrical signal collected by the electrical sensor; interference electrical signal It is mainly related to the magnitude of the force and the loading speed, namely: ; in, is the force signal collected by the force sensor, is the force loading rate, and the f function represents different types of mechanical-electrical constitutive relations.
[0024] As a further improvement, the different types of mechanical-electrical constitutive relations f functions are obtained by a machine learning method; the machine learning method first constructs a data set and then selects a model for training:
[0025] Among them, m and n are the weight coefficients of the influence of force and force loading speed on the electrical signal, For different force types:
[0026] Among them, i represents different force types, for example, a cyclically loaded force signal (heart beating), a suddenly loaded force signal (eyelid blinking), and a loaded and maintained force signal (body position change). The beneficial effect of the present invention is that it can effectively remove the noise signal generated by the electrokinetic effect in the brain-computer interface and accurately obtain the electrical signals conducted by nerve fibers.
[0027] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device embodiment, the above is only a preferred embodiment of the present invention. Since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment. The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited to this. Any technical personnel familiar with this technical field is within the technical scope disclosed by the present invention. For ordinary technical personnel in this technical field, changes or replacements that can be easily thought of should be covered within the protection scope of the present invention without departing from the principle of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.
Claims
1. A method for removing noise signals in a brain-computer interface by using a force-electric decoupling method, characterized in that: The signals generated in the brain-computer interface are collected, including the electrical signals transmitted by nerve fibers and the interference electrical signals. The interference electrical signals are decoupled and removed through the force-electric constitutive relationship of the liquid-containing porous material, and what remains are the electrical signals transmitted by the nerve fibers.
2. The method for removing noise signals in a brain-computer interface by using a force-electric decoupling method according to claim 1, characterized in that: The signals generated in the brain-computer interface are collected through a brain-computer interface chip, and a force collector is integrated on the brain-computer interface chip. The force collector is used to monitor the changes in mechanical load of brain tissue or implanted area in real time.
3. The method for removing noise signals in a brain-computer interface by electromechanical decoupling according to claim 1 or 2, characterized in that: The interfering electrical signals are electrical signals caused by force signals generated by various loads in the brain.
4. The method for removing noise signals in a brain-computer interface by using a force-electric decoupling method according to claim 3, characterized in that: The various loads in the brain include periodic loads, impact loads, and continuous loads.
5. The method for removing noise signals in a brain-computer interface by using a force-electric decoupling method according to claim 3, characterized in that: The various loads in the brain are caused by action potentials, which are specifically signals generated by heartbeats, eyelid blinking, limb movements, and blood flow.
6. The method for removing noise signals in a brain-computer interface by using a force-electric decoupling method according to claim 1, characterized in that: The process of decoupling the electrical signals caused by the force signals of various loads in the brain is as follows: first, the force signals are decomposed into different types and converted into corresponding electrokinetic signals. Then, the electrokinetic signals are separated from the original collected electrical signals, retaining the true electrical signals conducted by nerve fibers. The separation formula is as follows: ； in, It is the electrical signal conducted by nerve fibers. It is an interfering electrical signal. It is the electrical signal collected by the electrical sensor; interference electrical signal It is mainly related to the magnitude of the force and the loading speed, namely: ； in, is the force signal collected by the force sensor, is the force loading rate, and the f function represents different types of mechanical-electrical constitutive relations.
7. The method for removing noise signals in a brain-computer interface by using a force-electric decoupling method according to claim 1, characterized in that: The different types of mechanical-electrical constitutive relations f functions are obtained by a machine learning method; the machine learning method first constructs a data set and then selects a model for training: ； Among them, m and n are the weight coefficients of the influence of force and force loading speed on the electrical signal, i represents different force types, To understand how forces change over time, decompose them into different force types.