48 results about "Common spatial pattern" patented technology

A computer system is disclosed herein that surveys numerous legal documents which memorialize business or legal transactions and then determines common provisions in such documents. The forms of these “core provisions” are then stored in a knowledge base of the system. The system then allows attorney users to apply the system to analyze unsurveyed documents and use the knowledge base to recognize the core provisions that are most similar to the text of these unsurveyed documents. The user can then edit these unsurveyed documents in a rapid accurate fashion by automated means to revise text to match these core provisions. Document editing functionality is also present, along with means to use correlations to determine the likelihood of the presence/absence of specific provisions and the presence/absence of various particular documents in groups of documents used to memorialize certain types of transactions.

A method and apparatus for analyzing patterns in semiconductor wafers wherein the patterns are compared to a plurality of patterns stored in a common pattern library. A spatial pattern recognition engine is operable to receive a first set of data corresponding to a pattern on a semiconductor wafer and to generate a normalized contour representation of said first data set. A pattern analyzer compares the normalized data set to a plurality of reference contour data sets stored in a common pattern data reference library and generates a correlation label associating the first data set with one of the plurality of reference contour data sets. The label associated with the first data set is stored in a label storage database that can be accessed to perform subsequent analysis on the data associated with a specific wafer. The system can be used to analyze multiple types of patterns, including defect data, bin data, positional parameter data and in-line site data.

The invention discloses a common spatial pattern and deep learning method based on brain-computer interface auxiliary rehabilitation therapy. The method comprises the following steps that: S1: preprocessing an electroencephalogram signal to obtain the electroencephalogram signal of which the noise is filtered; S2: through an improved OVR-CSP (One Versus Rest- Common Spatial Pattern) algorithm, carrying out feature extraction on various categories of motor imagery EEG (electroencephalogram) signals of which the noise is filtered to obtain the feature of each category of motor imagery electroencephalogram signal, forming one-dimensional feature data, and meanwhile, taking a variance as the input of a classifier; and S3: utilizing a transformed CNN (Convolutional Neural Network) which is suitable for a one-dimensional input sample to carry out secondary feature extraction and classification. When the technical scheme of the invention is adopted, the movement position and the limb movementstate of a patient can be more accurately judged so as to provide an objective data support for realizing the scale evaluation of the rehabilitation degree of a patient.

The invention relates to a dual-tree complex wavelet and common spatial pattern combined electroencephalogram characteristic extraction method. The method comprises the steps that electroencephalogram signals with suitable channels are selected at first, up-sampling or down-sampling is conducted on the original frequency according to the characteristics of dual-tree complex wavelet frequency partitions, frequency bands corresponding to the frequency ranges of delta, theta, alpha and beta rhythm waves are obtained by means of dual-tree complex wavelet multi-scale decomposition, signal reconstruction is conducted in the scales, a plurality of reconstruction signals in the corresponding frequency bands are obtained, the same decomposition and reconstruction are conducted on the suitable channels, reconstruction signals of all the frequency bands of all the channels are combined to be input into a spatial filter, a six-dimensional feature vector is obtained, and motor imagery task classification is accomplished by means of a support vector machine at last. The dual-tree complex wavelet and common spatial pattern combined electroencephalogram characteristic extraction method not only conducts frequency information analysis on motor imagery electroencephalogram signals, but also can effectively overcome electrode selection defects.

The invention discloses an eye movement signal identification system and method based on a common spatial pattern. The eye movement signal identification system comprises an eye movement signal preprocessing module, a spatial filter training module and an eye movement signal identification module. The eye movement signal identification method comprises the steps of collecting eye movement data based on an electro-oculogram and preprocessing the eye movement data; dividing all the preprocessed data into training data and testing data; adopting a CSP algorithm to conduct spatial filtering on the training data, and using the result obtained after filtering as feature parameters which are input into an SVM classifier for SVM model training; using the CSP algorithm to conduct feature extraction on the testing data, feeding the result obtained after the feature extraction into the trained SVM classifier for identification, and finally obtaining the identification result of eye movement. The eye movement signal identification system and method have the advantages that the accuracy of eye movement signal identification is higher, the eye movement signal spreading and classification capability is higher, and the application potential is large.

A technical method of diagnosing rationality of city spatial patterns includes the following steps: 1, constructing an index system comprising a master target layer, a sub-target layer, a factor layer and a divisor layer; 2, after standard data processing, using an analytic hierarchy process and an entropy weight process to determine a weight of the divisor; 3, constructing HL comprehensive diagnosis models for rationality of city developing patterns, the models comprising a scale pattern USR diagnosis model, a spatial pattern UKR diagnosis model and a function pattern UFR diagnosis model; 4, using a fuzzy membership grade function process and a linear weighting summation process to calculate a rationality index for each sub-model; and 5, dividing cities into a highly reasonable city, a relatively reasonable city, an intermediate reasonable city, a lowly reasonable city, and an unreasonable city according to HL comprehensive indexes. The comprehensive diagnosis index system provided by the present invention has universality and comprehensiveness, and has availability and effectiveness when evaluating the data. The completed system evaluating method enables the calculated result of the rationality indexes of the urban developing patterns to be more accurate, and achieves a more scientific evaluation of the urban developing patterns.

The invention discloses a CSP (Common Spatial Patterns) and cross-correlation based motor imagery electroencephalogram classification method which mainly aims at solving the problems that the adaptability to individuals is poor and the classification accuracy difference is large in the prior art. The CSP and cross-correlation based motor imagery electroencephalogram classification method comprises the implementation steps of step 1, collecting electroencephalogram signals and obtaining a training set and a test set; step 2, extracting a common spatial feature of the training set in CSP, simultaneously extracting a cross-correlation feature of the training set through a cross-correlation function and combining into a training feature vector of the training set through the two features; step 3, extracting a test feature vector of the test set by the same method in the step 2; step 4, performing training on a support vector machine through the training feature vector, obtaining a support vector machine classifier and performing classification of imagery movement tasks on the test feature vector through the support vector machine classifier. The effect of the individual difference on the classification result is reduced, the classification accuracy is improved, and the CSP and cross-correlation based motor imagery electroencephalogram classification method can be applied to the control on electroencephalogram products comprising motor imagery BCI (Brain Computer Interface) on-line systems.

The invention discloses a single-time brain wave feature extraction and classification method for motion execution. According to the method, a multi-element empirical mode decomposition algorithm anda common spatial pattern algorithm are combined to process a single-time brain wave in motion execution; and after brain wave signal characteristics representing different motion intentions are extracted, the extracted brain wave signal characteristics are classified, and a motion execution category represented by the single-time motion execution brain wave is obtained. Through the method, the problem that existing multi-classification motion execution tasks are low in classification correct rate can be solved; and through combination of multi-element empirical mode decomposition and a commonspatial pattern, the recognition rate of multi-task brain wave signals is effectively increased, and the complexity in the operation process is lowered.

The invention discloses a brain-computer interface method and device based on logic thinking and imaginal thinking and relates to the field of novel pattern of brain-computer interface technology and feature extraction and classification. An experiment requires a testee for mental calculation and a three-dimensional object to rotate, signals of six electrodes are collected, and a common spatial pattern is adopted to extract feature values. Aiming at the problem that the common spatial pattern is suitable for multiple electrodes and the feature values, a common spatial filter algorithm is improved, electroencephalogram signals of one electrode are subjected to separation of different frequency bands and time periods, and the electroencephalogram signals are subjected to feature extraction calculation. The feature values are subjected to classification of a support vector machine, and excellent classification effect can be realized by the data processing mode through offline data analysis. A brain-computer interface based on logic thinking and imaginal thinking is constructed, reliability of a system is improved, experiment imaging difficulty and visual fatigue caused by long-term experiments are reduced, comfortability of the brain-computer interface system is improved, and application population range is expanded.

The invention discloses a novel motor imagery (MI)-steady state somatosensory evoked potential (SSSEP) mixed brain-computer interface method. The method comprises: two electrocardioelectrodes are placed at a left wrist and a right wrist, electrical simulation is carried out a left hand and a right hand according to a preset frequency, thumbs are induced to tremble slightly, thereby inducing obvious steady-state somatosensory evoked potentials; a tester is simulated and is processed by motor imagery, electroencephalogram data are collected, and pretreatment is carried out; feature extraction and pattern recognition are carried out on the electroencephalogram data by using a common spatial pattern algorithm and a single-task electroencephalogram feature vector is obtained; the single-task electroencephalogram feature vector is inputted into a support vector machine to train a classifier and classification identification is completed by using the support vector machine based on a ten-fold cross validation strategy, so that six sub frequency bands are built by using 4 Hz as stepping at frequency bands of 8 to 32Hz so as to complete classification identification. With the method, the ERD feature and the SSSEP feature are integrated, thereby realizing performance improvement; and robustness of neural-feedback-based rehabilitation training is enhanced.

The invention discloses a common-spatial-pattern (CSP) spatial-domain feature extraction method based on quantized minimum error entropy (QMEE). The QMEE is applied to improve a cost function of a traditional algorithm to enable the same to be robust for outliers, a better spatial-domain filter and better features can be obtained when the outliers occur, and then a good classification effect is obtained. The QMEE is an improvement on MEE, and can effectively solve the problem of a too high calculation cost of the MEE. Calculation of the MEE requires double summation, and time complexity is O(N2), and N is the number of samples, but complexity of the QMEE is O(MN), and M<<N. At the same time, the QMEE retains the advantages of the MEE, and has good robustness for nonlinear and non-Gaussiansignal processing and machine learning problems.

The invention relates to a multi-task motor imagination EEG feature extraction and pattern recognition method for vehicle control. The multi-task imagination EEG signals were collected by EEG amplifier and transmitted to PC. The frequency domain and spatial feature combinations of imaginary EEG were extracted by Welch power spectrum and one-to-one common spatial pattern algorithm. A plurality of GMM classifiers are constructed according to the categories to which the training set data belongs. The original EEG signal is passed through the GMM classifier, and the probability density is comparedwith the set credible threshold. The samples below the credible threshold are classified twice by artificial neural network, and the final classification result is transmitted to the vehicle throughwireless serial port to realize the real-time movement of the vehicle. The invention utilizes welch power spectrum and CSP to extract frequency domain and spatial domain features related to motion imagination, utilizes GMM and artificial neural network two-level classifier, effectively improves real-time performance of vehicle control and safety of vehicle driving, and lays a foundation for practical application of brain-controlled vehicle.

The invention discloses a control method for the movement of a two-dimensional cursor of a brain machine interface based on motor imageries, which only selects three types of motor imageries. The control method comprises the following steps of: 1, an electroencephalograph of a subject is transmitted to signal amplifying equipment through an electrode on an electrode cap; 2, the signal amplifying equipment amplifies and preprocesses the signal; 3, a computer terminal carries out feature extraction on the electroencephalograph by adopting a common spatial pattern algorithm; 4, pattern classification is carried out by using a support vector machine algorithm to obtain three output probabilities; 5, control command distribution and command translation are carried out on classified results by applying a control method for mapping the probabilities to vectors and combining the vectors; and 6, a translated control command is transmitted to a cursor control interface, and the movement of a cursor is displayed according to the control command to finish the whole control process. The control method has the beneficial effects that the movement of the two-dimensional cursor in a plane is controlled by adopting the three types of motor imageries, the imaginary burden of the subject is reduced, the use by the subject is facilitated, and the application field of a BCI (Brain Computer Interface) system is broadened.

The invention relates to a left-right hand motor imagery electroencephalogram characteristic extraction method mixing a wavelet and a common spatial pattern, and belongs to the technical field of electroencephalogram identification control. In the method, the wavelet and the common spatial pattern algorithm are mixed to process a left-right hand motor imagery electroencephalogram, and time-frequency-space characteristics capable of representing the left-right hand motor imagery electroencephalogram can be extracted. The left-right hand motor imagery electroencephalogram characteristic extraction method specially comprises the following steps: 1) decomposing the left-right hand motor imagery electroencephalogram by wavelet transform to obtain a wavelet coefficient capable of reflecting the time-frequency characteristics of the left-right hand motor imagery electroencephalogram; 2) analyzing the wavelet coefficient D2 capable of reflecting the time-frequency characteristics of the left-right hand motor imagery electroencephalogram by a CSP (Common Spatial Pattern) algorithm to obtain an optimal spatial filter of the wavelet coefficient; 3) extracting a characteristic value capable of reflecting the time-frequency-space characteristics of the left-right hand motor imagery electroencephalogram by the optimal spatial filter. According to the method, the problem that the time-frequency characteristics and the space-domain characteristics of the electroencephalogram cannot be simultaneously extracted by an electroencephalogram extraction method in the prior art can be solved.

The invention discloses a block selection common spatial pattern feature extraction method for motor imagery electroencephalogram, which comprises the following steps of: firstly, preprocessing original data in a mode of constructing a data block by dividing a frequency band by each channel, and secondly, performing correlation calculation on each block to obtain an index Fisher ratio for representing classification performance; then, selecting data blocks according to the indexes and a reasonable threshold value; and finally, carrrying out feature extraction and classification on data formedby the optimal blocks by using CSP and SVM. The selected blocks can effectively avoid difference between different individuals and different channels, the channels to which the blocks belong are reasonable in distribution and moderate in number, the classification performance of a BCI system is improved to a certain extent, and a new thought is provided for feature extraction of electroencephalogram signals.

The invention discloses a screening method for motor imagery (MI) response ability based on resting-state electroencephalography (EEG) features. The method includes the following steps: preprocessingacquired EEG data, performing data segmentation, and extracting common spatial pattern features of MI tasks; establishing a multiple classification recognition model by using a support vector machine,calculating a classification correct rate through 10-fold cross-validation, and characterizing the MI response ability by using the classification correct rate; extracting normalized energy, power spectrum entropy and Lempel-Ziv complexity of each eye-open resting lead EEG in a 8-13 Hz frequency band (alpha frequency band) respectively; calculating the correlation between the above resting-stateEEG features and the MI response ability, and screening optimal features to establish a classification model and a regression prediction model; and based on the classification model and the regressionprediction model, screening the motor imagery response ability. The method can screen out ''BCI blindness'', avoid an invalid training process, and predict the MI response ability of a subject in advance and formulate a matching training program for the subject, thereby optimizing an experimental training process and ultimately reducing an error rate of a user in operating brain-computer interface (BCI).

The invention discloses an intra-class distance and inter-class distance combined transfer learning method based on motor imagery classification, which comprises the following steps of: 1) taking cross-session data of other subjects except a current subject as a training set and taking the cross-session data of the current subject as a test set; 2) extracting a target signal by using a Butterworthband-pass filter; 3) extracting features by using a CSP (common spatial pattern); 4) performing feature migration in combination with distribution self-adaptation, intra-class distance and inter-class distance; 5) performing classification by using an ensemble learning method. According to the method, the distribution self-adaption, the intra-class distance and the inter-class distance are combined to perform feature migration, the ensemble learning method is used for classification, and the problem that the classification accuracy is not high due to the fact that the motor imagery data is scarce is effectively solved.

The invention discloses a multichannel electroencephalogram signal channel selection method based on time-frequency co-melting, and belongs to the field of brain-computer interface data processing. The method comprises the following operation steps: 1) performing data preprocessing, namely reducing sampling frequency, and performing baseline drift correction, band-pass filtering and independent component analysis by using wavelet transform to remove electrooculogram signal interference; 2) acquiring inter-channel correlation information by a time-frequency co-melting method; 3) performing feature extraction by using a common spatial pattern (CSP) 4) performing feature classification by using a support vector machine; and 5) performing result analysis. The method has remarkable innovativeness and feasibility, and has important reference significance for real-time processing and optimization of electroencephalogram signals.

The invention provides an electroencephalogram signal feature extraction and classification method based on SCSP-LDA. The method comprises the following steps: firstly, characteristic value decomposition is carried out on electroencephalogram data, searching and screening are carried out to obtain a new characteristic space, then characteristics of the electroencephalogram data are extracted through a CSP, and finally characteristic optimization and data classification are carried out on the data obtained after characteristic extraction through LDA to realize motor imagery EEG signal decoding.The CSP algorithm is converted into a generalized eigenvalue solving problem, an optimal spatial filter is searched by combining the generalized eigenvalue solving problem with a sparse search algorithm, a sparse common spatial pattern (SCSP) algorithm is introduced, the SCSP is a channel with the most obvious characteristic which can be effectively extracted by the algorithm to realize channel sparsity, and EEG decoding can be completely realized by combining the characteristic classification algorithm LDA.