36 results about "Electroencephalogram feature" patented technology

This invention relates to the field of music signal recognition technology, and more particularly to a method for recognizing the degree of music enjoyment based on music-EEG feature fusion. The method includes: extracting the Mel-frequency cepstral coefficients of the music signal; preprocessing and performing Fast Fourier Transform on the Mel-frequency cepstral coefficients to obtain the spectral feature values ​​of the music signal; and sequentially filtering, reducing dimensionality, and decorrelating the spectral feature values ​​of the music signal; extracting the Mel-frequency cepstral coefficients of the EEG signal; optimizing and updating the order of the Mel-frequency cepstral coefficients of the EEG signal so that the comprehensive error value between the EEG feature reconstruction signal and the original EEG signal meets a preset condition; aligning the music feature coefficients and the EEG feature reconstruction signal in the feature dimension and time axis using the FastDTW algorithm; and recognizing the degree of music enjoyment of the subject based on the alignment result. This invention effectively improves the robustness and accuracy of music recognition.

The application provides a driving intention recognition method based on functional connectivity and a graph neural network, comprising the following steps: S1, collecting electroencephalogram signals of a driver during driving, and preprocessing original electroencephalogram data; S2, calculating power spectral densities of each frequency band of the preprocessed electroencephalogram signals as electroencephalogram signal frequency domain features; S3, constructing an adjacency matrix as an initial graph structure based on electrode spatial proximity and functional connectivity; and S4, inputting the frequency domain features in S2 and the adjacency matrix obtained in S3 into a graph attention network for feature aggregation, inputting the extracted feature expression into a classifier to classify driving intentions and outputting results. The method can solve the problems of single electroencephalogram feature extraction and poor expression ability of the classification model in the existing driving intention prediction method, improve the accuracy of driving intention classification, improve the interpretability of the classification results, and better apply the method to driving state perception and auxiliary decision-making of a human-machine co-driving system.

The application provides a four-dimensional attention recognition method based on electroencephalogram feature fusion selection, and belongs to the technical field of electroencephalogram signal processing. Attention specifically includes four specific qualities of distribution, breadth, stability and transfer. The application combines electroencephalogram signals and attention qualities, extracts multi-domain electroencephalogram features to construct a fusion vector for four-dimensional attention recognition, and proposes a ReliefF-SBE-L1 three-layer hybrid feature selection model to improve recognition accuracy and calculation efficiency. The application can significantly reduce the calculation complexity while realizing efficient four-dimensional attention state recognition.

This invention discloses a lie detection device combining eye-tracking and electroencephalogram (EEG) signals, belonging to the field of lie detection devices. It includes a monitoring and mounting mechanism, with a lie detection mechanism disposed on the left side of the upper surface of the monitoring and mounting mechanism; the monitoring and mounting mechanism includes a table, with a display device disposed at the rear of the upper surface of the table and a control panel disposed at the front of the upper surface of the table; the lie detection mechanism includes a mounting plate, which is threadedly mounted to the left side of the upper surface of the table by bolts; a cylinder is mounted on the upper surface of the mounting plate via a pivot. This device integrates eye-tracking features captured by a binocular camera and EEG signals collected by electrode pads for joint analysis, solving the problems in existing technologies where eye-tracking features are easily affected by environmental interference and EEG signals are easily affected by irrelevant physiological activities when used alone. This reduces the limitations of single-signal detection and significantly improves the reliability of lie detection.

The application discloses a kind of based on convolutional neural network's electroencephalogram automatic feature extraction method, comprising the following steps: obtaining original electroencephalogram data, based on channel spectrum curvature rate of change carries out adaptive artifact suppression and channel amplitude dynamic re-labeling;Frequency band morphing reconstruction is executed, according to spectrum curvature rate of change sequence determines frequency band boundary, constructs frequency morphing mapping function and generates multiple frequency band component tensor;The frequency band component tensor is input into improved ConvNeXt model, extracts multidimensional electroencephalogram feature tensor;Cross-frequency domain attention fusion is executed, and fusion electroencephalogram feature vector is constructed;Task reasoning is carried out, and electroencephalogram task response result is output;According to frequency morphing consistency index and predicted offset degree, feature feedback reconstruction is executed, and morphing convolution kernel parameter is updated jointly.The application improves the precision and stability of electroencephalogram feature extraction, and is suitable for cognitive state recognition, medical auxiliary analysis and other multiple electroencephalogram intelligent processing scenarios.

The application relates to the technical field of neuromodulation devices, and provides a bone conduction neuromodulation device and a control method. The bone conduction neuromodulation device comprises an electroencephalogram acquisition device, a bone conduction vibration device and a control device. The control device is configured to extract electroencephalogram features in an electroencephalogram signal, determine vibration control parameters according to the electroencephalogram features, control the bone conduction vibration device to generate vibration according to the vibration control parameters, and adaptively adjust the vibration control parameters based on changes in the extracted electroencephalogram features during the process of generating vibration by the bone conduction vibration device, so as to form a closed-loop control. The closed-loop control mechanism based on real-time electroencephalogram feedback makes the vibration stimulation always adapt to the instant neural state of a target user, helps to reduce the influence of individual differences on the treatment effect, improves the stability and repeatability of the treatment effect, and further enhances the overall reliability of the bone conduction neuromodulation in clinical application.

The application provides a personalized brain-controlled mechanical arm rehabilitation system based on individual characteristics, comprising the following steps: S1, evaluating the performance of each MI-BCI training cycle of an individual; S2, researching the correlation between the individual's electroencephalogram features and functional indicators; S3, predicting the motor imagery ability according to the cycle rating and electroencephalogram feature quantitative data of the individual, and then establishing a mapping from the motor imagery ability to the mechanical arm movement rate; S4, constructing a personalized feedback regulation loop and establishing a complete closed-loop MI-BCI mechanical arm system. The application has the beneficial effects that: the personalized brain-controlled mechanical arm system based on individual characteristics predicts the motor imagery ability according to the performance of the training cycle and the electroencephalogram features, thereby predicting the mechanical arm rate, and the MI-BCI ability of the individual is displayed in real time by the mechanical arm rate. The individual's initiative is increased, the degree of assistance of the MI-BCI to the individual is reduced, and the rehabilitation effect is improved.

The present disclosure relates to a mobile state electrode screening method, device, equipment and computer readable storage medium. Relates to the field of computer technology, including through the band-pass filter to the target electroencephalogram signal is accurate division get multiple preset frequency band, and combined with the relative power calculation realizes feature normalization, overcomes the defect that the traditional method is not enough to protect the subtle electroencephalogram feature. Secondly, based on the relative power data statistics index of normal user and abnormal user is calculated, and the variation coefficient double verification mechanism is introduced, when the statistical index is less than the first threshold value and the variation coefficient is less than the second threshold value, the target electrode is confirmed, this kind of comprehensive screening standard based on statistical significance and feature stability ensures that the electrode has both discriminant ability and robustness. Through this targeted screening mechanism, the electrode redundancy is significantly reduced, which can focus on the electrodes that are really effective for brain injury classification, so as to realize high-precision classification in mobile environment and optimize the calculation efficiency.

The application relates to a single-channel seizure detection device, comprising: a data acquisition unit configured to acquire single-channel electroencephalogram data to be detected and to pre-process the single-channel electroencephalogram data to be detected; an electroencephalogram feature extraction unit configured to extract time-frequency features of the pre-processed single-channel electroencephalogram data and to perform standardization processing on the extracted time-frequency features; and a seizure detection unit configured to sequentially pass the standardization-processed time-frequency features through an input layer, an Embedding layer, a feature generalization module, a global pooling layer, a 1x1 convolution layer and a Linear output layer to obtain a detection result; the application combines the light convolution calculation advantages of the partial convolution idea and the advantages of the Style-domain generalization algorithm, and further divides and processes frequency domain information to reduce the increase of calculation amount, so that the detection model enhances the cross-patient detection effect of single-channel seizure electroencephalogram and makes the network lighter, and the generalization and real-time performance of the detection model are greatly improved.

This application relates to the field of computer technology and discloses a method for constructing a pain model based on multi-dimensional EEG feature fusion. The method includes: acquiring segmented EEG data; extracting four-layer heterogeneous features from the segmented EEG data to construct a high-dimensional feature matrix. The four-layer heterogeneous features include spectral features, temporal dynamic features, brain functional connectivity features based on regions of interest, and cross-frequency coupling features. The temporal dynamic features include permutation entropy, and the cross-frequency coupling features include phase-amplitude coupling. An algorithmic consensus screening framework is constructed. Using the algorithmic consensus screening framework, a consensus score for the four-layer heterogeneous features corresponding to the high-dimensional feature matrix is ​​determined. Based on the consensus score and the four-layer heterogeneous features, multiple target feature sets and their corresponding scores are determined. Based on the multiple target feature sets and their corresponding scores, a subset of features with the highest scores is determined from the multiple target feature sets. A pain model is constructed based on the feature subset.

The application discloses a brain-computer interface signal processing method and system based on time sequence alignment and feature decoupling. In view of the problems of time asynchronization of electroencephalogram and near-infrared signal and feature entanglement caused by neurovascular coupling in the existing hybrid brain-computer interface, the application firstly extracts multi-scale features from the electroencephalogram signal and extracts multi-delay candidate feature sequences from the near-infrared signal; secondly, uses the electroencephalogram features as a query to guide a time delay attention mechanism to adaptively align the hemodynamic response features; then, projects the aligned features into shared and private subspaces through a multiple-constrained neural feature subspace decoupling module to separate the cross-modal neural intention and private physiological noise; finally, outputs a classification result through adaptive gating and multi-head decision network fusion. The application effectively overcomes the individual differences of neurovascular delay, strips the modality-specific noise, and improves the decoding accuracy and robustness.

The application relates to the fields of brain-computer interface, rehabilitation engineering and intelligent control technology, and provides a brain-computer interface exoskeleton multidimensional feedback adaptive control method and system. The method comprises the following steps: collecting multidimensional state information containing electroencephalogram features, exoskeleton physical states and current decoding intentions, and constructing a multidimensional state space; detecting an error-related potential automatically triggered by the brain due to the fact that the exoskeleton action is inconsistent with the user intention, and taking the error-related potential as an internal reward signal for correcting the multidimensional state information; inputting physical indexes including joint angles of the exoskeleton into the reinforcement learning intelligent agent, combining electroencephalogram signals and physical end feedback, and reversely optimizing decoding parameters of the electroencephalogram decoder; and optimizing decoding parameters corresponding to the multidimensional state information according to real-time performances of each user, generating a dynamically evolved control logic, and realizing adaptive and personalized control.

The application discloses a brain-computer interface interaction system and method for cerebral infarction rehabilitation training, relates to the technical field of electroencephalogram feature processing, and comprises the following steps: feature extraction is performed on electroencephalogram signal data, comprehensive electroencephalogram feature fusion coefficients are obtained through feature weighting fusion calculation based on the electroencephalogram feature data, feedback signal comprehensive calculation is performed based on patient feedback data, comprehensive signal feedback coefficients are obtained, comprehensive rehabilitation evaluation processing is performed according to the comprehensive signal feedback coefficients and the comprehensive electroencephalogram feature fusion coefficients, comprehensive rehabilitation evaluation coefficients are obtained, and the most suitable rehabilitation processing plan for the patient is finally determined based on the comprehensive rehabilitation evaluation coefficients, so that the rehabilitation process is more suitable for the actual situation of the patient itself, and the rehabilitation effect is improved.

The application is suitable for the field of intelligent networked vehicles and physiological signal processing technology, and provides a method for decoding and continuous evaluation of motion sickness electroencephalogram features for automatic driving, which comprises: acquiring multi-channel electroencephalogram data and performing event-locked segmentation; using a parameterized Sinc filter bank, combining physiological priors to mine specific band features; capturing dynamic timing features under different time windows through a multi-time scale time domain encoder, and strengthening key brain region spatial interaction features through a graph-enhanced brain region attention module; finally, performing spatio-temporal-frequency feature fusion and multi-task decoding, and synchronously outputting discrete motion sickness grades and continuous motion sickness severity scores. Through the construction of an end-to-end spatio-temporal-frequency joint modeling and multi-task learning framework, the application realizes continuous evaluation of motion sickness with high precision, high robustness and high interpretability, and the output can be directly used as a comfort cost for automatic driving closed-loop control.

The application discloses a kind of epilepsy closed loop intelligent processing method based on micro machine learning.The method comprises: the pre-processing of input electroencephalogram signal;Lightweight one-dimensional convolutional neural network model is used to analyze and judge the electroencephalogram feature after processing, and when the seizure state is identified, the treatment control module is triggered to output pulse signal, guides nerve stimulation device to intervene epilepsy, and realizes closed loop treatment.The present application is based on embedded platform, with the advantages of fast response, efficient calculation, wearable, etc., suitable for real-time epilepsy monitoring and intervention in family and mobile scene, effectively improve the intelligent and personalized level of epilepsy management.

The application discloses a three-flow state space driving fatigue detection system, comprising an electroencephalogram signal acquisition and feature extraction module, an electrooculogram signal acquisition and feature extraction module, a three-flow state space modeling module, a neurophysiological interaction module and a multi-modal fusion and fatigue regression module; the detection method is that electroencephalogram and electrooculogram signals of a driver are collected and pretreated first, features are extracted and divided into at least two electroencephalogram feature flows of different brain areas and an electrooculogram feature flow, then each feature flow is input into a corresponding state space model for parallel modeling, subsequently, the neurophysiological interaction module is used to simulate the functional connection between brain areas and the electrooculogram features are used to correct the electroencephalogram features, finally, the corrected features are weighted and fused, and a continuous driving fatigue evaluation result is output. The application introduces state space modeling and neurophysiological interaction, reduces the calculation complexity, improves the accuracy and stability of fatigue detection, and enhances the physiological interpretability of the model.

The application discloses a cross-domain electroencephalogram emotion recognition method based on two-stage domain alignment and double-classifier collaborative confrontation, comprising the following steps: collecting multi-subject and multi-session electroencephalogram emotion data and completing filtering and denoising, artifact rejection, feature extraction and other preprocessing operations; constructing a feature extractor module containing a public feature extractor and a domain-specific feature extractor and a double-classifier module; then performing global domain alignment and subdomain alignment to complete two-stage domain alignment; meanwhile, a double-classifier consistency-determinacy constraint loss is proposed, the loss is calculated by calculating the joint consistency term and the local classification determinacy term of the double-classifier output probability, an antagonistic mechanism of "double-classifier module minimizing loss-feature extractor module maximizing loss" is constructed, and the model is guided to generate electroencephalogram features with domain invariance and high classification certainty; finally, the model is optimized through multi-round iterative training to realize accurate electroencephalogram emotion recognition. The cross-domain generalization ability of electroencephalogram emotion recognition is effectively improved.

The application discloses a collaborative robot grasping and placing intention recognition and control method based on eye-brain feature fusion, comprising: obtaining first electroencephalogram features and first eye movement features; obtaining second electroencephalogram features; obtaining second eye movement features; taking the second electroencephalogram features and the second eye movement features as input, and taking continuous intention time sequence as label, constructing and training a cross-attention neural network model to learn the time sequence change relationship of grasping and placing intention; inputting the third electroencephalogram features and the third eye movement features into the trained neural network model to output the continuous intention time sequence; comparing the continuous intention time sequence with a threshold interval to determine the intention result of grasping or placing; and converting the intention result into a control instruction of the collaborative robot to drive the robot to perform the grasping or placing task of the target object. The method provided by the application realizes continuous recognition of the operator's grasping and placing intention, and significantly improves the accuracy and robustness of intention recognition.

The application provides an autism emotion ability evaluation method based on electroencephalogram and visual emotion features, acquires electroencephalogram signals and facial video data of an autism subject, respectively extracts electroencephalogram emotion features and visual emotion features, the electroencephalogram features include frequency band energy calculation and brain region function connection analysis, the visual features include facial key point expression features and emotion arousal degree sequences. Through an emotion arousal degree screening mechanism, effective emotion segments are screened, and multi-modal features are input into a structured Prompt reasoning model for semantic analysis to generate an emotion ability analysis report of the subject. According to the analysis result, scores of the subject in emotion recognition ability, emotion understanding ability and emotion regulation ability and other dimensions are output, and objective and quantitative evaluation of the emotion ability of an autism individual is realized. Through the cooperative processing of electroencephalogram and visual information, the evaluation accuracy and reliability can be improved, and scientific basis and application value are provided for early screening, intervention assistance and individualized rehabilitation.

The application provides a robot control method and device, computer equipment and a storage medium, which can acquire image information collected by a robot, and show a virtual reality picture of an environment where the robot is located to a target user based on the image information, thereby improving the immersion of robot control; by acquiring electroencephalogram signals of the target user at multiple electrode channels, and extracting time domain nonlinear features and frequency domain features of the electroencephalogram signals, an electroencephalogram feature vector can be constructed in combination with signal active modes corresponding to the multiple electrode channels respectively; by the electroencephalogram feature vector and a trained intention recognition model, high-precision and continuous user intention information can be obtained, thereby effectively improving the control accuracy and reducing the control delay.

The present invention discloses an early judgment system for Parkinson's disease cognitive impairment based on multi-dimensional features of transcranial magnetic stimulation - electroencephalogram, including: a transcranial magnetic stimulation - electroencephalogram combined acquisition module, a synchronous signal preprocessing module, a multi-dimensional feature extraction module, a feature intelligent fusion module, and a storage and display module; the transcranial magnetic stimulation - electroencephalogram combined acquisition module is used to encode and perturb the patient's nerve activity through single-pulse transcranial magnetic stimulation and collect the evoked electroencephalogram signals; the synchronous signal preprocessing module is used to denoise and filter the evoked electroencephalogram signals; the multi-dimensional feature extraction module uses multi-dimensional electroencephalogram feature analysis to extract features from the processed evoked electroencephalogram signals to obtain multi-parameter electroencephalogram nerve activity features; the feature intelligent fusion module is used to assign weights and fuse the multi-parameter electroencephalogram nerve activity features to obtain multi-modal nerve indexes for cognitive impairment; the storage and display module is used to store the multi-modal nerve indexes for cognitive impairment and visualize the multi-modal nerve indexes for cognitive impairment.

The application discloses a sleep state recognition system, comprising a data acquisition module, a feature extraction module and a fusion feature recognition module; the data acquisition module is used for collecting electroencephalogram data and electrocardiogram data of a user after the user prepares to start sleeping; the feature extraction module is used for extracting features of the electroencephalogram data and the electrocardiogram data collected by the data acquisition module respectively; the fusion feature recognition module is used for splicing and fusing the electroencephalogram features and the electrocardiogram features extracted by the feature extraction module to obtain probabilities of different sleep states; a current sleep state quantitative value V of the user is obtained according to a formula V = ∑s i p i The current sleep state of the user is obtained according to a range of the current sleep state quantitative value V of the user; and the application further provides a sleep intervention method based on the sleep state recognition system; and the sleep state of the current user can be accurately and quickly recognized, and the user can be accurately intervened in sleeping.

Systems, methods, and computer-readable storage media for transcranial electrical stimulation, and more particularly to systems, methods and software for personalized transcranial electrical stimulation using electroencephalographic features. A system can include an electroencephalography (EEG) system, a feature extraction module, an electrical stimulation target module, and an electrical stimulation system. The EEG system can include sensor electrodes to be attached to a subject's scalp and which provide electrical signals. The electrical signals are processed by the feature extraction module, resulting in corresponding electrical signals for a first period of time and features therefrom. The electrical stimulation target designation module can use those to determine stimulation parameters which result in electrical stimulations provided via the electrodes to the subject's scalp.

The application provides a training method and device based on electroencephalogram signal features, equipment and storage medium, and the method comprises the following steps: collecting electroencephalogram signals of a target brain area at different leads; extracting time domain features and frequency domain features of the electroencephalogram signals, and constructing an initial electroencephalogram feature topographic map; collecting real-time electroencephalogram signals of the target brain area at different leads, and constructing a real-time electroencephalogram feature topographic map based on the real-time electroencephalogram signals; inputting cognitive assessment score results, the initial electroencephalogram feature topographic map and the real-time electroencephalogram feature topographic map into a classification model, so that the classification model outputs a cognitive domain impaired target area result; and generating a personalized training task and a multi-modal stimulation scheme in cognitive training according to the cognitive domain impaired target area result. The application can improve the pertinence and effectiveness of cognitive training.

Embodiments of the present disclosure disclose a method and device for exoskeleton control based on reinforcement learning. A specific implementation of the method comprises: obtaining a physiological and motion signal set of a target user and a current virtual reality scene complexity level; preprocessing and feature extraction are performed on the physiological and motion signal set to obtain electroencephalogram features, electromyogram features and joint motion features; a state feature vector is constructed according to the current virtual reality scene complexity level, the electroencephalogram features, the electromyogram features and the joint motion features; the state feature vector is input into a preset reinforcement learning agent to obtain a control parameter set; a rendering parameter is generated according to a target virtual reality scene complexity level, and a virtual reality device is controlled to perform scene rendering; an exoskeleton joint torque instruction is generated according to an auxiliary torque gain, and the exoskeleton is controlled to perform a corresponding torque adjustment operation according to the exoskeleton joint torque instruction. The implementation can improve the safety of the user during the training process.

The application relates to the technical field of upper limb rehabilitation, and discloses an upper limb rehabilitation intention recognition feedback training method based on electroencephalogram signal analysis. The method integrates upper limb motor imagination electroencephalogram signals of multiple people, constructs a data set containing multiple effective electroencephalogram features of actions through quality screening, trains an initial electroencephalogram decoding model and a feature template through transfer learning, and stores clinical data of patients; an acquisition unit is deployed to screen effective signals, and a report containing time sequence and clinical information is generated through decoding; subsequently, a multi-modal feedback and exoskeleton assistance guiding training are performed, an evaluation matrix is generated, and a personalized rehabilitation path is dynamically adjusted; finally, qualified signals are screened, the model and the template parameters are updated through incremental transfer learning, and the threshold is corrected and adapted, and then stored. The application effectively improves the accuracy, adaptability, rehabilitation effect and efficiency of upper limb rehabilitation training.

This invention provides a method, control device, storage medium, and visualization system for visualizing electroencephalograms (EEGs), belonging to the field of EEG technology. The EEG visualization method includes: acquiring EEG signals; extracting feature indicators from the EEG signals; and generating an EEG feature indicator report based on the extracted feature indicators. Through EEG signal data processing technology, time-domain, frequency-domain, and spatial-domain features of the EEG signals are extracted to obtain feature indicators. Multiple algorithms can be selected for each feature indicator. Different users (e.g., clinical electrophysiologists) can choose different EEG features and corresponding algorithms (or default algorithms) to extract feature indicators, and then visualize the extracted feature indicators to form a customized EEG feature indicator report, helping clinical electrophysiologists obtain more valuable diagnostic information from EEG signals.

The application provides a wearable adaptive electroencephalogram signal processing system and method based on brain-like deep reinforcement learning, and relates to the technical field of electroencephalogram signal processing. In the method, multi-modal physiological signals are synchronously collected through a flexible electrode array, a micro-accelerometer and a temperature sensor; cross-modal feature alignment and fusion are performed by using contrast learning and an attention mechanism; a hierarchical reinforcement learning framework initialized by synaptic learning is adopted to dynamically suppress noise and extract personalized electroencephalogram features; and finally, real-time inference and interpretable decision are completed in an edge computing unit through a lightweight neural network model. While improving the signal-to-noise ratio and artifact suppression rate, the application realizes fast personalized calibration, millisecond-level real-time processing and ultra-low power consumption operation, and significantly enhances the practicability and reliability of electroencephalogram technology in clinical diagnosis and human-computer interaction.

The application belongs to the technical field of vestibular medicine, and particularly relates to a vestibular electroencephalogram detection and analysis system, which comprises a vestibular multi-modal stimulation module, a multi-modal signal synchronous acquisition module, a vestibular electroencephalogram feature analysis module, a vestibular function corroboration reference module and a result generation and output module, wherein the vestibular multi-modal stimulation module is used for applying vestibular physiological stimulation to a user; the multi-modal signal synchronous acquisition module is used for synchronously and in parallel acquiring multi-modal data signals in a time synchronization manner while the vestibular multi-modal stimulation module applies the vestibular physiological stimulation; the vestibular electroencephalogram feature analysis module is used for adaptively selecting an analysis algorithm to perform vestibular electroencephalogram feature analysis on the multi-modal data; the vestibular function corroboration reference module is used for constructing a corroboration parameter set; and the result generation and output module is used for determining a vestibular electroencephalogram analysis and evaluation result of the user.