45 results about "Cognitive neuroscience" patented technology

An encephalic electrode individualization locating method based on multimode medical image data fusion relates to the fields of medical instruments and medical image processing and neuroimaging. By means of multimode medical image data including magnetic resonance images, X-ray images and intranperative optical photos, the space position relation of an encephalic electrode and a brain tissue structure is comprehensively measured, a relation between the position of the encephalic electrode and a brain anatomical structure is established, and accurate and fast individualization locating of the encephalic electrode is achieved. The encephalic electrode individualization locating method based on multimode medical image data fusion can be used in the fields of cognitive neuroscience basic research, clinic neurosciences and the like, provide accurate brain space position information for an encephalic electroencephalogram signal, and enhance application value in the aspect of electrophysiological basis research.

The invention belongs to the field of cognitive neuroscience, and specifically relates to a human action intention recognition training method based on cooperative computation of multiple brain areas.The human action intention recognition training method comprises the steps of 1, performing image collection on a human body action; 2, obtaining human body joint information, and recognizing the category of the human body action; 3, calculating a robot action strategy according to the category of the action executed by the human by adopting a mode of cooperative computation of multiple brain areas based on a brain-like computing model; 4, inputting a correctness judgment for the robot action strategy calculated in the step 3; 5, adjusting parameters of the brain-like computing model throughan STDP mechanism based on the correctness judgment inputted in the step 4; and 6, if the correctness judgment inputted in the step 4 shows that the robot action strategy is wrong, executing the step1 for repeated training until the correctness judgment inputted in the step 4 shows that the robot action strategy is correct. The human action intention recognition training method overcomes the defect of being not flexible enough because programming and the like need to be performed in advance in the traditional human-computer interaction technology, and improves the use experience.

The invention relates to a system for acquiring and analyzing event-related optical signals and a lie detecting method, and relates to recognition technology and a recognition method for honesty and cheat of a litigant in national security, public security, justice and civil dispute. The invention provides a lie detecting method using EROS by overcoming the defects of the prior lie detecting technology and products, absorbing the experiences of the prior lie detecting technology and the products, and also absorbing latest theory and technological achievement of the contemporary cognitive neuroscience and photoelectric technology. The system consists of a photoconductive cap, a near infrared laser, a scattered light signal acquisition control system, event-related optical signal processing software and lie detecting software, and plays a main role in acquiring objective data that whether a testee is honest to respond to detecting stimulation.

The invention relates to a method and a system for judging whether combatants meet an emergency or not through their electroencephalogram signals. By the method, without any body movement and languages, whether the combatants meet the emergency or not can be analyzed by recording the electroencephalogram signals of the combatants and analyzing the corresponding electroencephalogram signals, quick response and alarm can be made to prompt of others. The method and the system belong to comprehensive application of fields of cognitive neuroscience, information technology and automatic control.

The invention discloses an MI and SSVEP dual paradigm-based few-channel asynchronous control brain computer interface system, and belongs to the technical field of cognitive neural science, information processing and automation control crossing. For a few-channel electroencephalogram signal BCI system, an MI paradigm is adopted as a switch module of the BCI system; an SSVEP paradigm is adopted asa BCI multi-choice module; the two modules are connected in series to form the asynchronous control BCI system; a few-channel EEG signal is decomposed into multiple intrinsic mode functions by utilizing a multi-variable empirical mode decomposition algorithm; based on a spectrum distribution characteristic of MI, the IMFs are preferentially selected as characteristics for realizing MI classification; an improved canonical correlation analysis method is proposed for calculating canonical correlation coefficients between the IMFs and SSVEP frequency templates; the optimal canonical correlation coefficient is preferentially selected out for realizing SSVEP classification; and therefore, the control effect and the classification accuracy of the few-channel BCI system can be improved.

The invention discloses a mechanical arm writing device based on electroencephalogram control and a control method, and relates to the technical field of cognitive neuroscience. The device is characterized by at least comprising electroencephalogram collection equipment, signal processing equipment and a mechanical arm executing the writing action; the signal processing equipment receives collection information of the electroencephalogram collection equipment, and the collection information is subjected to data processing; the specific data processing process sequentially comprises the steps of data filtering, wavelet filtering, feature extraction, classification and classification result conversion; the mechanical arm receives a control command of the signal processing equipment and executes the corresponding command action according to the control command. The mechanical arm writing device and the control method have the advantages of being easy to operate, safe to use, high in anti-noise capacity and good in stability, and a practical and feasible scheme is provided for achieving human-computer interaction.

The invention relates to a P300 single extraction technique based on independent component analysis and Kalman smoothing. The invention aims at improving efficiency and accuracy of a dynamic system based on P300. According to the P300 single extraction technique provided by the invention, by removing winking artifacts and random noise in electroencephalogram signals (EEG), a signal-to-noise ratioof the electroencephalogram signals (EEG) can be improved, so that the electroencephalogram signals can be recognized more easily; with time domain characteristics of the processed electroencephalogram signals (EEG) as classifying characteristics, a characteristic vector can be obtained; the characteristic vector undergoes dimension reduction and mode recognition, so as to judge whether the current electroencephalogram signals (EEG) belong to a P300 potential, and corresponding commands are outputted. The invention is significant for improving the efficiency and accuracy of the dynamic systembased on the P300. The invention belongs to comprehensive application of human-computer interaction science and cognitive neuroscience fields.

The invention provides a single-time P300 detection method based on matrix grey modeling, belongs to the field of cognitive neuroscience and relates to a feature extraction and recognition detection method of an event related potential P300, in particular to a single-time P300 detection method based on matrix grey modeling in a grey theory.The method comprises the steps that 1, a original acquired electroencephalogram signal is preprocessed; 2, electrocardiographic lead combinations are selected, namely four electrocardiographic leads with most obvious top occipital region waveform differences are selected as optimal electrodes according to oscillograms of target stimulus and non-target stimulus of training set data; 3, segmented matrix grey modeling is conducted on the data of the four electrocardiographic leads, and model parameters are extracted to serve as feature vectors; 4, a Fisher ratio value method is utilized to perform optimal feature selection, and meanwhile the purpose of decreasing the number of feature vector dimensions is achieved; 5, a support vector machine classifier is utilized to classify feature vectors, and single-time P300 detection recognition is achieved.Experimental data tests show that the method can improve single-time P300 detection recognition rate, and the correct recognition rate can be further improved during less-time superposition.

The invention discloses a brain-computer interface system based on steady-state visual evoked potential physiological characteristics, and belongs to the cross technical field of cognitive neural science, information processing and automatic control. The brain-computer interface system comprises a time delay reaction module, a CCA module, a typical correlation coefficient selection module and an output module. A delay reaction of SSVEP is modeled, a characteristic frequency point capable of reflecting the frequency spectrum energy change is selected as a frequency reference signal of SSVEP stimulation, all components of the frequency reference signal are linearly combined to obtain a spectral energy distribution model, and an analysis result of a CCA is optimized under the constraint of the ratio of the components of the frequency reference signal. The quality of SSVEP signals can be improved, the characteristics can be effectively extracted, the analysis capability of the CCA is improved, and finally the classification accuracy of a BCI system is improved.

The invention relates to a universal model of gesture action intention detection based on an electroencephalogram signal. Specifically, by processing the collected electroencephalogram signal, a universal model is constructed by a convolutional neural network method to detect whether a subject has an intention to perform a hand action. The model proposed by the invention is a universal model, which is different from a personal model in the previous work. The model does not train the electroencephalogram signal of a participant to directly participate in the test, the training data are from theother participants, and an experimenter obtains the accuracy of the model by analyzing the electroencephalogram signal. The invention belongs to the comprehensive application of the computer field, the vehicle design field, the human-computer interaction science, the psychology science, the cognitive neuroscience and the automatic control field.

The invention belongs to the technical field of cognitive neuroscience, particularly relates to a TMS coil pose map generation method, system and device based on electromagnetic simulation calculation, and aims to solve the problem that an existing TMS coil cannot be quickly and accurately positioned according to an electromagnetic regulation and control effect. The method comprises the following steps: constructing coil array sites and directions on the surface of scalp in an MNI standard space, and matching the coil array sites and directions to an individual brain space to obtain coil array sites and directions of the individual brain space; simulating coil array sites of the individual brain space by a finite element calculation method to obtain brain tissue induced electric field distribution in different coil directions; in combination with brain tissue induced electric field distribution, obtaining an optimal regulation and control effect; and obtaining coil sites and directions corresponding to the optimal regulation and control effect to serve as optimal coil poses of all subareas of the individual brain area, and constructing a TMS pose map of the individual. Rapid and accurate positioning of the TMS coil is realized.

The invention relates to a brain link mining system and method based on document analysis and functional nuclear magnetic resonance imaging analysis, and belongs to the fields of computer technologies and cognitive neuroscience technologies. The system comprises a dynamic causal model module, an activation analysis module, a document link analysis module, a seeking sub-network module, a document database and a brain network link database. The method comprises the steps of firstly, by calculating the activated probabilities of all brain coordinates in all documents, figuring out the activated probabilities of corresponding anatomical areas to obtain activated brain areas, mining modes which frequently appear in the brain areas through the association rules algorithm, calculating confidence coefficients to obtain a trusted brain function network, establishing the corresponding documents to generate a brain network database, then collecting corresponding functional nuclear magnetic resonance imaging data by utilizing a functional nuclear magnetic resonance imaging system, and verifying the actual link direction and weight numbers of a network edge by utilizing the dynamic causal model module. In this way, the problem that calculating is overlong in time and low in accuracy in the brain link analysis process is solved.

The invention discloses a non-language graph symbol communication method. The method comprises the steps of firstly determining a communication content range and constructing a contextual database; secondly according to the contextual database, designing a non-language symbol system in an initial stage; thirdly performing a cognitive experiment, screening out graph symbols and sentence expressionswith high correlation, and analyzing characteristics of the graph symbols and the sentence expressions; and through linguistics, cognitive psychology, cognitive neuroscience, semiology, plane designand animation design knowledge establishment rules, performing re-design, re-experiment and repeated iteration to achieve a certain effect, summarizing a method and a mode, performing computer programming, and converting a result into the graph symbols and the rules. The communication identification capability of the provided graph symbols is that a receiver can understand and identify an intention to be expressed by a transmitter through the graph symbols, and the original intention of the transmitter is reflected as more as possible.

The application provides a textual emotion marking method, device and system. According to the present invention, a tester reads the to-be-classified texts, a brain electrical signal of a text reader is acquired, and then the emotion mark is carried out on the text according to the brain electrical signal, so that the emotion of a marker can be reflected really from a cognitive neuroscience angle, and a very high accuracy is guaranteed. Moreover, by the application, the marking personnel do not need the long-time training, when a text emotion analysis system is developed, a lot of time and funds can be saved.