34 results about "Stimulus frequency" patented technology

The invention provides a transcranial stimulation magnetic therapy closed-loop control method and system, and the method comprises the steps: determining a multi-modal physiological signal of a user, the multi-modal physiological signal at least comprising an electroencephalogram signal, an autonomic nerve physiological signal and a subjective feedback signal; constructing an individual dynamic baseline spectrum based on user multi-state data collected before treatment; the method comprises the following steps: preprocessing a multi-modal physiological signal collected in a treatment process, and extracting a real-time feature vector; calculating a comprehensive deviation index of the real-time feature vector and the individual dynamic baseline spectrum, and determining a deviation type based on the comprehensive deviation index; the adjustment amount of transcranial magnetic stimulation parameters is dynamically calculated according to the deviation type, the individual response characteristics and the historical treatment data, stimulation operation is conducted according to the adjustment amount of the transcranial magnetic stimulation parameters, and the transcranial magnetic stimulation parameters at least comprise the stimulation frequency, the intensity, the pulse width and the stimulation duration. Parameters of transcranial magnetic stimulation are adaptively changed according to changes of neuron oscillation of a patient in the treatment process.

The invention relates to the technical field of crossing of medical instruments and artificial intelligence, and provides a hearing threshold detection method based on multi-mode hearing electrophysiological signal fusion. Comprising stimulation frequency otoacoustic emission and auditory brainstem response induced by sweep frequency stimulation sound, distortion product otoacoustic emission induced by dual-tone stimulation and middle ear sound immittance / reflection signals, and a multi-task deep learning model is constructed to perform fusion analysis on the signals. According to the method, accurate quantitative regression prediction of hearing thresholds with any frequency resolution and automatic classification and discrimination of hearing loss properties are synchronously realized, the problems of single evaluation dimension and insufficient complex hearing loss analysis ability in the prior art are effectively solved, the comprehensiveness, accuracy and clinical operation efficiency of objective hearing evaluation are remarkably improved, and the method is suitable for popularization and application. And an innovative system solution is provided for fine diagnosis of the auditory function.

The application provides a SSVEP-based brain-computer interface stimulation modulation method, system, device and medium, comprising the following steps: acquiring a preset code sequence set, a stimulation frequency set and a stimulation paradigm; the code sequence set comprises a plurality of code sequences; the code sequence comprises a plurality of code elements, and the code element corresponds to a brightness amplitude depth coefficient; the stimulation frequency set comprises a plurality of stimulation frequencies; the stimulation paradigm is used for modulating the brightness amplitude depth and the flicker frequency of visual stimulation based on the code sequence and the stimulation frequency; based on the code sequence and the stimulation frequency, a code stimulation combination of the code sequence and the stimulation frequency is generated; and based on the code stimulation combination, the visual stimulation corresponding to each stimulation block is modulated by using the stimulation paradigm. The SSVEP-based brain-computer interface stimulation modulation method, system, device and medium provided by the application not only expand the number of stimulation targets, but also improve the comfort of users when gazing at the visual stimulation.

The invention discloses a double-domain double-scale cross-subject SSVEP (Steady-State Visual Evoked Potential) decoding method and device based on transfer learning, and belongs to the technical field of brain-computer interfaces. The method comprises the following steps: acquiring SSVEP electroencephalogram data of a source domain and SSVEP electroencephalogram data to be decoded of a target domain; sub-band filtering and sine and cosine reference matrix template generation; aiming at source domain data of each sub-band in the source domain multi-sub-band data, constructing a source domain dual-scale template pair of each sub-band for each candidate stimulation frequency, and extracting a single-cycle cross-tested spatial filter; applying time local constraint to target domain data of each sub-band, and extracting an adaptive spatial filter; and calculating multi-path evidence scores, carrying out weighted fusion based on the sub-band weights, and judging and outputting a decoding result. Target subject training data is not needed, high-precision and strong-robustness cross-subject decoding is achieved through double-domain double-scale feature fusion and self-adaptive adaptation, the calculation amount is low, real-time operation is supported, and the practicability and generalization ability of a brain-computer interface are remarkably improved.

The invention discloses a safety helmet intelligent control method and system based on electroencephalogram characteristics, and the method comprises the steps: decomposing a real-time electroencephalogram signal frequency spectrum to generate cognitive load frequency domain characteristics, and building an electroencephalogram control space; an electroencephalogram control space is scanned to identify a frequency band coupling unbalance point, a cooperative intervention opportunity is reversely derived, and a multi-channel adjustment mode is formed; mapping the stimulation frequency range to generate a frequency matching domain, and performing resonance analysis to determine a resonance intervention window; monitoring a frequency band in a resonance window to obtain an energy migration track, constructing a risk propagation chain to identify a cascade failure node and forming a key blocking anchor point; analyzing risk acceleration of the key blocking anchor points to form a state deterioration rate, fusing frequency domain features to generate dynamic delay tolerance, and generating variable speed control parameters in a fast-slow grading manner; the variable speed control parameter is compared with a threshold value to generate a control deviation signal, reverse phase modulation is carried out to generate a hedging stimulation waveform, a phase compensation execution instruction is formed, and accurate monitoring and safe intervention of the cognitive state are achieved.

The invention belongs to the field of auxiliary medical treatment, and provides a personalized electrical stimulation treatment scheme generation system and method, and the method comprises the steps: obtaining a voice signal of a patient, and extracting voice dynamic change information; acquiring neuromyoelectric signals, heart rate signals and motion information of the patient, and extracting physiological change information; performing association modeling on the voice change information and the physiological change information to generate fusion features for representing a multi-part tremor mode of the patient; performing dynamic generation of personalized electrical stimulation parameters based on the fused features; constraining the dynamic change of the current amplitude, the stimulation frequency and the pulse width within an individually set safety threshold range, and performing protective adjustment in combination with real-time feedback of a patient; and the electrical stimulation module is used for implementing electrical stimulation on a target nerve part in the radial nerve, the median nerve or the ulnar nerve according to the parameters issued by the decision module.

This invention discloses a device for monitoring nerve conduction function, comprising: a mounting plate, a fastening assembly, and a monitoring assembly, both of which are fixed to the surface of the mounting plate; the fastening assembly includes a connecting strap and a connecting block fixed to the side of the mounting plate, with a matching locking block fixed to one end of the connecting strap; the monitoring assembly includes an ultrasonic detection module, a detection electrode, a stimulation electrode, and a processing module, with a plurality of detection electrodes and stimulation electrodes of equal quantity. This device and method for monitoring nerve conduction function, by classifying the monitored nerves into different degrees of damage, allows the stimulation electrodes to provide precise stimulation treatment, avoiding further nerve damage due to stimulation time, intensity, and frequency exceeding tolerance limits. Simultaneously, the electrical stimulation emitted by the stimulation electrodes can promote nerve cell regeneration and growth, accelerating the repair speed of damaged nerves.

The invention discloses a space-frequency fusion visual stimulation method and system. The method comprises the following steps: S1, selecting a central stimulation target and four adjacent stimulation targets around the central stimulation target; s2, setting an arrangement mode of the stimulation blocks; s3, the two arrangement modes are stimulated in sequence, and the stimulation frequencies of the five stimulation blocks and the corresponding electroencephalogram signal amplitudes are obtained; s4, selecting an arrangement mode in which the number of the stimulation frequencies of the central stimulation target including the stimulation frequencies of the surrounding four adjacent stimulation targets is maximum and the amplitude of the electroencephalogram signals induced by the stimulation frequencies is maximum as an optimal arrangement mode; compared with the prior art, the characteristic of partition backlight space crosstalk is converted into the multi-frequency characteristic advantage, a traditional single signal loudness analysis mode is abandoned, surrounding target interference is converted into the multi-frequency and space characteristics of the center target, and the target recognition accuracy in the multi-target scene is greatly improved.

The application provides a neural internal medicine rehabilitation training system and regulation method based on artificial intelligence, extracts the rhythm power of a stimulation pulse of a rehabilitation training device to a patient and the blood oxygen concentration of a target nerve point of the patient, classifies the efficiency of the remodeling level of the neural function in the rehabilitation training through the blood oxygen concentration and the rhythm power, and obtains a graded remodeling index of the neural function regulation in the rehabilitation training; determines the cortex excitability index of the patient in the neural internal medicine rehabilitation training through the motor evoked potential of the target patient muscle cortex, the stimulation frequency and the stimulation intensity of the stimulation pulse in the rehabilitation training device; multi-modal synergistically integrates the cortex excitability index and the graded remodeling index of the neural function regulation, obtains the neural regulation target parameter of the remodeling index in the rehabilitation training device, and then dynamically regulates the stimulation parameter in the rehabilitation training device based on the neural regulation target parameter. Based on the above scheme, multi-modal coupling regulation of the stimulation parameter in the rehabilitation training process can be realized.

The application discloses a bilateral transaural vagus nerve regulation device, an electronic device and a storage medium. The nerve regulation device comprises an auditory stimulation module configured to apply multiple novel stimuli to a target object within an auditory stimulation period; a processing module configured to obtain an electroencephalogram signal corresponding to each electroencephalogram channel when each novel stimulus is applied to the target object; determine a target frequency when fitting the electroencephalogram signal with a target lag order based on the electroencephalogram signal corresponding to each electroencephalogram channel; determine a first proportion based on the information exchange intensity between different brain regions of the target object at each time point and the target frequency; determine a second stimulation frequency within a next electrical stimulation period adjacent to the auditory stimulation period based on the first proportion, the first stimulation frequency and the target frequency; and an electrical stimulation module configured to electrically stimulate the auricular vagus nerve of the binaural of the target object at the second stimulation frequency within the next electrical stimulation period.

To determine the presence or absence of induction of brain waves with relatively high accuracy when a determination result of the presence or absence of induction of brain waves by stimulation is used for selection of a selection target.SOLUTION: A frequency determination apparatus includes induction determination means for determining whether or not a brain wave is induced by a stimulus in a brain wave measured in a state in which the stimulus of a designated frequency is output, frequency range search means for searching for a maximum value and a minimum value of a frequency at which the induction occurs, and frequency determination means for determining a plurality of frequencies as frequencies of the stimulus within a range between the maximum value and the minimum value.SELECTED DRAWING: Figure 1

The application discloses a deep learning-based electroencephalogram slow wave real-time feedback transcranial electrical stimulation method and system, relates to the cross technical field of neural regulation and deep learning, and comprises the following steps: collecting electroencephalogram signals of a target object and pre-processing the electroencephalogram signals to obtain pre-processed electroencephalogram signals; inputting the pre-processed electroencephalogram signals into a pre-constructed deep learning model for analysis to obtain a latent representation representing the dynamic state of electroencephalogram slow waves; wherein the deep learning model is obtained through the collaborative training of three types of self-supervised targets, namely self-predictive representation, unsupervised target conditional reinforcement learning and inverse dynamics modeling; transcranial electrical stimulation parameters are decided based on the latent representation, wherein the stimulation parameters at least include a stimulation type, a stimulation intensity and a stimulation frequency; and corresponding transcranial direct current stimulation or transcranial alternating current stimulation is output to specific brain regions of the target object according to the transcranial electrical stimulation parameters.

The application discloses a kind of nuclear magnetic compatible tactile stimulation devices, comprising: drive control system and multichannel tactile stimulation system, the drive control system with the multichannel tactile stimulation system electrically connected;The drive control system is used to control the reciprocating tactile stimulation module of corresponding position on the multichannel tactile stimulation system generates tactile stimulation output, adjusts the frequency of output, output displacement and output force size, control stimulation time length;The multichannel tactile stimulation system is used to apply contact mechanics tactile stimulation to the hand of subject, tactile stimulation area covers whole hand, stimulates position, stimulation output displacement, force and regulates and controls stimulation duration.The present application tactile stimulation has high time and space resolution, output displacement, stimulation frequency is stable and adjustable, tactile coverage area is wide, and it is beneficial to tactile brain topological function diagram research.

This invention provides a method for enhancing attention and executive function based on the synergy of transcranial alternating current stimulation (TCD) and white noise. The method includes: acquiring clinical and functional phenotypic vectors, behavioral vectors of attention and executive function, and neural oscillation and brain network vectors to obtain a comprehensive representation; defining target cognitive function, target brain region, target stimulation frequency, and stimulation parameters to obtain an individualized target brain network and oscillation frequency band scheme; designing a TCD stimulation scheme, a cognitive task training scheme, a white noise scheme, and an overall timetable to obtain a synergistic intervention scheme; recording behavioral process data, neural process data, and subjective experience data of the research subjects to obtain multimodal feedback data; and analyzing the multimodal feedback data to obtain an evaluation result of the intervention effect. This invention achieves synergistic intervention of individualized brain networks, frequency bands, tasks, noise, and time, which can not only address the symptoms and self-care abilities of individual patients but also promote the development of medicine and neuroscience.

The application discloses an individualized cognitive function adjusting device based on cross-frequency coupling, which comprises a peak frequency automatic extraction module, a spectrum analysis and automatic frequency extraction are used to obtain the peak frequency of the frontal lobe theta oscillation and the parietal lobe gamma oscillation of an individual baseline as the stimulation frequency of transcranial alternating current stimulation; a target site determination module is used to automatically output the stimulation site of tACS by determining the positive and negative power values corresponding to the peak frequency between the left and right brain regions, and the stimulation equipment outputs current to the corresponding brain region according to the output stimulation site; a signal-to-noise ratio calculation module is used to adaptively output the stimulation current intensity of tACS according to the signal-to-noise ratio value at the peak frequency; and a multi-mode regulation model is used to set the peak nesting and valley nesting modes according to the cross-frequency tACS, so that the targeted regulation of cognitive function disorders such as memory, attention and emotion processing is realized.

This invention relates to the field of cognitive data processing technology, and more particularly to a method and system for physical stimulation-driven lymphatic circulation and cognitive enhancement. The system includes a physical stimulation frequency impact assessment module, a stimulation mechanical vibration analysis module, a lymphatic circulation vibration calibration module, and a stimulation frequency drive adjustment module. It utilizes pressure and temperature sensors to monitor the corresponding physical stimulation pressure and the surface temperature of the stimulated skin in real time, performing stimulation frequency impact assessment and stimulation mechanical vibration analysis to generate a physical stimulation mechanical vibration effect. It also acquires lymphatic fluid flow velocity and EEG neural activity signals, performing neurocognitive level analysis and vibration response calibration. Simultaneously, it performs lymphatic circulation cognitive regression analysis and stimulation frequency drive adjustment to generate a physical stimulation frequency drive adjustment scheme corresponding to lymphatic circulation cognitive enhancement. This invention can accurately analyze the correlation between physical stimulation and lymphatic circulation and cognitive enhancement.

The application belongs to the technical field of nerve regulation and control engineering, and proposes an Alzheimer's disease electric stimulation system based on cerebrospinal fluid rhythm. First, the first frequency range data and the second frequency range data in the brain wave signal are coupled to obtain cerebrospinal fluid rhythm data. Then, the phase difference between the first frequency range data and the cerebrospinal fluid rhythm data is calculated. Finally, the stimulation frequency is dynamically controlled according to the phase difference, and the stimulation current is dynamically controlled according to the brain tissue water volume fraction. The problem that single frequency stimulation cannot match the specific metabolic needs of non-rapid eye movement sleep and rapid eye movement sleep cycles is solved. The dynamic changes of post-traumatic brain edema, as well as the demand and influence of cerebrospinal fluid rhythm on current control, are considered, the real-time adaptive ability to the dynamic changes of post-traumatic brain edema is improved, and the treatment effect of Alzheimer's disease is guaranteed.

This invention discloses a method for decoding EEG features for steady-state visual evoked potentials, including: the subject's fixation frequency being f n The original steady-state visual evoked potentials collected during visual stimulation are X. n Using N fb A filter bank for X n Preprocessing is performed to obtain N fb After preprocessing, the steady-state visual evoked potential pairs are filtered to obtain useful signal components and noise signal components, and then a spatial filter is obtained to obtain the steady-state visual evoked potential template signal. This is used to acquire the unknown steady-state visual evoked potential K and obtain N. fb K is a preprocessed unknown steady-state visual evoked potential. (m) By improving and K (m) The signal-to-noise ratio, calculate N fb The filtered sum K (m) The correlation coefficient of N fb The weighted summation yields ρ n ; We obtained K and steady-state visual evoked potentials [X1,…X i ,…,X n ,...,X Nf The correlation coefficient between ], ρ i If the maximum value is reached, then the visual stimulus frequency of K is f. i The technical solution in this embodiment achieves the effect of improving the accuracy of recognizing unknown visual stimuli using a small amount of training data.

Computing systems and computer-implemented methods for removing brain stimulation artifacts in neural signals are disclosed. The method makes use of a matching pursuit algorithm to accurately extract the stimulation artifact. The disclosed method removes the stimulation artifact associated with individual stimulation pulses without needing additional information from previous stimulation pulses or other electrodes. The disclosed method is compatible for use with various stimulation frequencies, does not need any filtering, and can recover neural signals almost immediately after stimulation. The disclosed method is compatible for use in has great potential in closed-loop systems used in various neurological diagnostic and therapeutic procedures.

Methods and systems for spinal cord stimulation (SCS) are disclosed. The methods and systems involve using electrode leads implanted within the patient's spinal column to record neural responses evoked by the stimulation. The disclosed neural responses are different in several respects from electrical responses that have previously been measured in the context of SCS, such as stimulation artifacts and evoked compound action potentials (ECAPs). The disclosed neural responses typically occur later in time following the evoking stimulation pulse. Another distinguishing feature is that disclosed neural responses are generally most prominently observed with consistent, relatively unchanging amplitudes when the evoking stimulation frequency is ultra-low, for example, about 10 Hz or less. The disclosed methods and systems may use these neural responses as indications of pain, therapy, and / or another clinically relevant dimension, to direct / confirm stimulation placement, and for feedback control of stimulation parameters.

The invention discloses an SSVEP (Steady-State Visual Evoked Potential) brain-computer interface stimulation method based on dynamic dot matrix-spatial reference joint modulation, and solves the technical problems of low user comfort, few stimulation frequency resources, large harmonic interference and the like in an SSVEP brain-computer interface system. The method comprises the steps of initializing a display environment, constructing a multi-position visual stimulation space layout, generating a flicker stimulation dynamic dot matrix texture sequence, integrating a visual focusing guide structure, performing frame-level synchronization and accurate frequency control, jointly modulating a stimulation process and terminating a program. According to the invention, a multi-position spatial layout with auxiliary points around a main stimulation area as a center is adopted, the main stimulation area is lightened through sine function modulation, a visual focusing guide structure is integrated, and frame-level synchronization and accurate frequency control are realized. According to the SSVEP brain-computer interface system, the visual fatigue is obviously reduced, the fixation stability is improved, meanwhile, the high recognition performance is ensured, the problem of frequency interference existing in the multi-frequency stimulation system is solved, and the comfort, practicability and expandability of the SSVEP brain-computer interface system are enhanced.

The invention discloses an individualized electrical stimulation parameter AI data modeling method, and belongs to the technical field of artificial intelligence data modeling. According to the method, a multi-modal state feature set is constructed by collecting surface electromyogram signals, stimulation loop impedance, physiological cycle information and user subjective tolerance data; on the basis, an improved support vector machine model based on a physiological cycle sensitive weight is used for modeling the electrical stimulation effectiveness, and an optimal treatment window for effective muscle contraction and user comfort is determined; a fuzzy PID control algorithm fused with physiological tolerance is further combined to dynamically adjust the stimulation frequency, the pulse width and the current intensity; and through historical data iteration modeling, an individualized initial parameter library and a rehabilitation trend evaluation result are formed. According to the invention, on the premise of guaranteeing the safety, individualization, self-adaption and long-term optimization of electrical stimulation parameters can be realized, and the effectiveness, comfort and stability of electrical stimulation treatment are improved.

The invention discloses an electrical stimulation bracelet, a dehydration and dizziness and vomiting prevention control method and device and a medium. The electrical stimulation bracelet comprises a bracelet body; the at least two stimulating electrodes are arranged on the inner side of the bracelet body and are in contact with the skin on the inner side of the wrist when the bracelet is worn; the at least four detection electrodes are arranged on the inner side of the bracelet body, are used for being in contact with the skin of the wrist part when being worn and are used for acquiring human body composition parameters of a user; the electrical stimulation generator is electrically connected with the stimulation electrode; the controller is electrically connected with the detection electrode and used for determining the dehydration degree according to the obtained human body composition parameters; the controller is further electrically connected with the electrical stimulation generator and used for generating control signals with the same or different waveform parameters and stimulation frequencies according to electrical stimulation parameters actively selected by a user or individually preset by the user in combination with the dehydration degree and controlling the electrical stimulation generator according to the control signals. Therefore, each stimulation electrode can receive and apply the same or different electrical stimulation to the inner side of the wrist.

An example diagnostic system is configured to: direct an acoustic stimulus generator to apply acoustic stimuli having a plurality of stimulus frequencies to a recipient of a cochlear implant during an insertion procedure in which an electrode lead communicatively coupled to the cochlear implant is inserted into a cochlea of the recipient; direct the cochlear implant to record, using electrodes disposed on the electrode lead, a plurality of evoked response signals during the insertion procedure, each evoked response signal included in the plurality of evoked response signals corresponding to a different stimulus frequency included in the plurality of stimulus frequencies; and determine an insertion status of the electrode lead within the cochlea of the recipient based on an amplitude and a phase of each of one or more evoked response signals included in the plurality of evoked response signals.

The invention relates to the technical field of brain-computer interfaces, in particular to an augmented reality stimulation module and a brain-computer interface system for target detection, target detection and aVEP stimulation adsorption. The target detection module comprises an image acquisition unit and a target detection unit; wherein the image acquisition unit acquires image data including a controlled object and global environment information in real time; a pre-trained improved YOLOv5 network model is configured in the target detection unit, the number of C3 modules is simplified, and a non-maximum suppression algorithm is optimized; the improved YOLOv5 network model receives image data output by the image acquisition unit and then carries out target detection; and selecting frame coordinates of the optimal preselection frame to complete target detection. According to the invention, jump caused by environment change is reduced, time sequence synchronism is improved, stability of stimulation frequency output is ensured, the position of stimulation superposition on the target position of the controlled object is kept stable, and a visual lag phenomenon caused by image refresh delay or detection lag is reduced at the same time.

A diagnostic system is disclosed configured to direct an acoustic stimulus generator to apply an acoustic stimulus having a stimulus frequency to a recipient of a cochlear implant during an insertion procedure in which an electrode lead of the cochlear implant is inserted into a cochlea of the recipient, direct the cochlear implant to record, using an electrode disposed on the electrode lead, an evoked response signal during the insertion procedure, the evoked response signal representative of amplitudes of a plurality of evoked responses occurring within the recipient in response to the acoustic stimulus applied to the recipient, and incrementally step the stimulus frequency through a sequence of decreasingly lower values as the electrode lead is inserted into the cochlea, the sequence of decreasingly lower values beginning with an initial value and ending with a final value lower than the initial value.

The invention belongs to the technical field of neural regulation and control, and discloses a closed-loop deep brain stimulation ADRC control method and system based on Bayesian optimization, and the system comprises a neural signal processing module, an ADRC controller, a Bayesian optimization module, and a stimulator module. The method comprises the following steps: acquiring a target brain region neuroelectric signal and extracting beta-band oscillation power as feedback; an ADRC controller is adopted, an extended state observer of the ADRC controller is utilized to estimate and compensate total disturbance of the system on line, real-time tracking and suppression of the oscillation power are achieved, and a stimulation frequency control signal is output; a Bayesian optimization algorithm is further introduced, comprehensive performance indexes with control errors and stimulation energy as targets are constructed, automatic global optimization is carried out on key parameters of an ADRC controller through Gaussian process modeling and collection function guidance, the defects of unsmooth control, poor interference immunity and the like in an existing closed-loop stimulation strategy are overcome, and the method has the advantages of being high in robustness, high in reliability and the like. And an effective solution is provided for individualized closed-loop treatment of Parkinson's disease.

This invention provides a real-time interactive method and system for a brain-controlled rehabilitation robot based on a brain-computer interface. It synchronously acquires the user's electroencephalogram (EEG) signals and records the steady-state visual evoked potential (SSVEP) stimulation frequencies associated with different rehabilitation tasks. The system then processes the EEG signals in parallel to extract features: extracting motor imagery-related frequency band signals, obtaining tangent space feature vectors by calculating the Riemann covariance matrix, and calculating the spectral Shannon entropy; calculating response features for each SSVEP stimulation frequency; constructing a composite feature vector, inputting the vector into an intention classification model, and outputting preliminary decoding results including candidate motor intentions and confidence levels; setting a rejection threshold; if the highest confidence level is below the threshold, it is determined as an invalid instruction and feature extraction is repeated; if it is above the threshold, the corresponding candidate intention is determined as a control instruction; inputting the control instruction confidence level, SSVEP response features, and spectral Shannon entropy into a dynamic mapping model to calculate motion parameters and drive the rehabilitation robot to perform actions.

A visual brain-computer interface frequency detection method combining convolutional neural network and task-related analysis, comprising: 1) channel extraction, frequency reduction, data cutting and sub-band filtering are performed on the EEG data of each subject; 2) the sbCNN model is trained by using the training data of all subjects, the test data is classified, the classification scores of all stimulus frequencies are obtained and normalized; 3) the TRCA model is trained by using the training data of the test subject, the spatial filter and the template of each stimulus frequency are obtained, the spatial filter of all stimulus frequencies is integrated to filter the template and the test experiment, and the classification score of the test experiment is obtained by performing correlation operation on the filtered template and the test experiment and normalized; 4) the classification scores of the two models are added, the mode classification is performed according to the classification score, and the stimulus frequency of the test experiment is identified. The application can improve the classification accuracy of the brain-computer interface and promote its practical application.

The embodiment of the invention discloses a closed-loop visual stimulation system and method based on a multi-modal synchronous sensing signal, and the method comprises the steps: collecting at least two types of multi-modal data, carrying out the processing and analysis of the multi-modal data, determining a stimulation position and a stimulation parameter, and outputting a stimulation signal according to the stimulation position and the stimulation parameter, the modal combination of the multi-modal data is determined according to the stimulation target, and the stimulation parameters comprise the stimulation amplitude and the stimulation frequency, so that the stimulation position and the stimulation parameters can be adjusted according to the multi-modal data, and the stimulation accuracy is improved.