36 results about "Portable electroencephalogram" patented technology

The invention discloses an execution function evaluating and training system for autism spectrum disorder children, wherein a problem of evaluating and training the execution function of the autism spectrum disorder children is settled by means of advanced man-machine interaction technology and brain information sensing technology. The execution function evaluating and training system comprises the components of a student intelligent terminal, a portable electroencephalogram, a portable set-top-box, a cloud server and a parent handheld smart phone. The functional units are connected through wireless communication technology, wherein the student intelligent terminal provides a user interaction interface and records a user face expression image and spatiotemporal dynamics behaviors of buttons in real time. The portable electroencephalogram records the brain wave rhythm of the user. The data set-top-box is a system data collecting and analyzing center and analyzes the collected data through an algorithm for realizing sensing and estimating of the execution function on the user. Furthermore the man-machine interaction interface is constructed for realizing execution function training based on the analysis. The parent handheld smart phone acquires the execution function evaluating and training result of a child through the cloud server.

The invention provides a novel movement imagery electroencephalogram control-based intelligent wheelchair system, and aims to provide a service auxiliary motion tool for paralyzed patients or elderly people and help them to take free activities outdoors. The system consists of a portable electroencephalogram acquisition system, a signal processing device, an interface circuit and an electric wheelchair, which are connected in turn. The portable electroencephalogram acquisition system is a set of simple and practicable electroencephalogram acquisition system and is used for recording electroencephalogram signals under user imaginary left and right hand motion tasks; the signal processing device is a signal processing module which operates on a laptop, extracts imagery motion-related electroencephalogram characteristics and identifies the subjective intention of the user; the interface circuit converts the identified subjective intention of the user into four paths of voltage signals; and the electric wheelchair receives the four paths of control voltage signals and controls the operating conditions of left and right rear wheel motors. The intelligent wheelchair system implementing mode can be applied to other application fields of direction control.

The invention discloses a brain-myoelectricity artificial limb control device and method based on scene steady-state visual evoking. The method is characterized by comprising the following steps: stimulating the brain of a subject by adopting a scene steady-state visual evoking unit to induce the generation of an operation intent; picking up the electroencephalogram and myoelectricity signals of an operator respectively by adopting a portable electroencephalogram acquisition unit, a myoelectricity acquisition unit and a wireless Bluetooth technology; transmitting the electroencephalogram and myoelectricity signals onto a microprocessor; performing target action identification through a method for combining the electroencephalogram and myoelectricity signals; and coding an identification result to drive an intelligent artificial limb to finish corresponding actions. The key points are that a certain action is decomposed into a plurality of different scenes; two inverse color pictures with sharp contrast between black and white are obtained respectively after each scene is subjected to gray-scale processing; two inverse color pictures of each scene flicker continuously and alternatively through pulse width modulation of different frequencies to stimulate the brain of the subject in order to induce the generation of the operation intent.

The invention discloses a hand rehabilitation system based on brain-computer interaction hybrid intelligence for cerebral apoplexy patients. A portable electroencephalogram signal acquisition device is connected with a mechanical glove through a motion imagery electroencephalogram signal processing and recognition module; a visual stimulation module comprises an SSMVEP visual stimulation interfaceand a motion imagery visual interface and is used for providing SSMVEP visual stimulation options and pictures of hand actions executed by the mechanical glove for a testee; the portable electroencephalogram signal acquisition equipment is used for acquiring SSMVEP electroencephalogram signals and motor imagery electroencephalogram signals of the testee; the SSMVEP electroencephalogram signal processing and recognition module classifies and recognizes the SSMVEP signals, wherein classification results are transmitted to the mechanical glove and visual stimulation module at the same time; an the motor imagery electroencephalogram signal processing and recognizing module classifies and recognizes the motor imagery electroencephalogram signals and converts the motor imagery electroencephalogram signals into instructions to control the mechanical glove to drive the affected limb of the testee to complete pre-selection hand action. According to the invention, the misoperation rate of the mechanical glove is reduced, and the applicability of the hand rehabilitation system is improved.

The invention discloses a portable electroencephalogram collection system which comprises a collection electrode and a signal processing system. The signal processing system comprises a microcontroller, an input filter, a static protection unit, an instrument amplifier, an analog-digital converter, a storage module, a radio frequency transceiver, a power source management system and a display operation module, the power source management system comprises a power source module, a program storage unit and an induction eddy current charging circuit, and a display input module comprises a state display lamp and a button configuration unit. Electrodes are placed at foreheads of Fp1, FpZ and Fp2, and interference caused by hair is avoided, so that medical pasted wet electrodes are used, and interference of electrode contact impedance is avoided. A low-power-consumption device is adopted mainly, and the power source management system is arranged, so that state of a power source can be monitored, noise can be removed effectively, and elimination of electro-oculogram noise is based on an improved algorithm of discrete wavelet transformation and self-adaptive noise offset.

The invention relates to a portable electroencephalogram detection system which comprises a background cloud computing server, an intelligent mobile phone terminal and a headband hardware convenient to carry, wherein a headband is composed of a singlechip, an electroencephalogram sampling chip, an electrocardio sampling sensor, a temperature-and-humidity sensor, a wireless data transmission module, a forehead camera, a forehead detection electrode and a power supply system. A power box, a metal electrode, a sensor group, a camera and a main electric box are fixed on the headband, the sensor group is located on the camera, and the power box, the metal electrode, the sensor group, the camera and the main electric box are connected through conductive wires fixed inside the headband. The output end of the metal electrode is connected with the input end of an electroencephalogram signal amplifier, the output end of the electroencephalogram signal amplifier, the output end of a microphone, the output end of the sensor group, and the output end of the camera are connected with the input end of the singlechip, the output end and the input end of the singlechip are connected with the output end and the input end of a wireless communication module in a double-way mode, and the output end and the input end of the wireless communication module are in wireless connection with the output end and the input end of the intelligent mobile phone terminal, and the input end and the output end of the background cloud computing server in a double-way mode.

The invention provides a portable electroencephalogram depression detection system in combination with a demographic attention mechanism. On one hand, the accuracy of electroencephalogram signal sequence learning and modeling is improved by using a convolutional neural network, and on the other hand, demographic information of individuals is introduced in combination with the attention mechanism,and more effective depressive disorder detection is realized. The system comprises an electroencephalogram data acquisition module, a data preprocessing module and a depressive disorder detection module, wherein the electroencephalogram data acquisition module is used for acquiring resting state electroencephalogram original data of a subject; the data preprocessing module is used for carrying outdata preprocessing on the collected original data; and the depressive disorder detection module is used for completing depressive disorder detection based on the electroencephalogram data after datapreprocessing, constructing and training a model by adopting an artificial neural network to classify electroencephalogram signals, and fusing the demographic information into a modeling process of the electroencephalogram signals by jointly using convolution operation and the attention mechanism.

The invention discloses a portable electroencephalogram collection system with a real-time marking function, and belongs to the field of marking. The portable electroencephalogram collection system comprises an N-channel integration electroencephalogram collection analog front end, a master controller, a communication module, an upper computer and a power module; the N-channel integration electroencephalogram collection analog front end is used for collecting electroencephalograms; the N-channel integration electroencephalogram collection analog front end is connected with the master controller through an SPI bus, and the master controller is connected and communicated with the upper computer through the communication module; the power module supplies power to the N-channel integration electroencephalogram collection analog front end, the master controller and the communication module; a real-time marking system is arranged inside the master controller; the hardware marking mode is adopted; compared with a traditional software marking mode, the marking signal real-time performance can be ensured, and the mark loss rate can be effectively decreased.

The invention discloses a severe depression identification system based on a brain-computer interface and deep learning and application. The system comprises a portable electroencephalogram acquisition device, an electroencephalogram analysis system and a classification and recognition system, the portable electroencephalogram acquisition device acquires EEG electroencephalogram signals from the brain of a testee. After the acquisition processes, the electroencephalogram analysis system is used for analyzing the acquired EEG electroencephalogram signals and establishes a multi-layer brain complex network. The classification and recognition system accurately recognizes the brain state on the basis of a multi-layer brain complex network, and completes the recognition process. The system gives out the possibility that a testee belongs to a normal person or severe depression through the collection process and the recognition process for specified times, and then completes the recognition task of a patient suffering from severe depression. According to the system, relatively high severe depression identification accuracy can be achieved, a system can rapidly and accurately carry out preliminary identification on a patient suffering from severe depression, and a basis is further provided for later diagnosis.

The invention relates to an epilepsy non-invasive detection data analysis method based on a GRU circulating neural network. The electroencephalogram data of a volunteer is analyzed, and whether or notthe volunteer suffers from epilepsy is judged according to electroencephalogram information. The method solves the problems of high misdiagnosis rate, high missed diagnosis rate and the like of epilepsy diagnosis due to the fact that electroencephalogram data and detection data are high in dimension, strong in time sequence performance and the like. The collected electroencephalogram data is processed according to the data analysis method based on the GRU circulating neural network, and the method mainly comprises the following steps of S1, utilizing a portable electroencephalogram signal collecting side to collect and save electroencephalogram signals of the volunteer; S2, preprocessing the collected electroencephalogram data such as filtering; S3, utilizing GRU to train a preprocessed training set; S4, adjusting parameters through feedback signals in a training process; S5, obtaining a classification model which is suitable for classifying the electroencephalogram signals and judging whether or not the volunteer suffers from epilepsy.

The invention discloses novel active hand full-finger rehabilitation equipment based on an artificial intelligence technology. The equipment comprises a portable electroencephalogram acquisition device, a physiological state analysis module and a hand rehabilitation device which are connected in sequence, a brain-controlled active training interface and an auxiliary brain-controlled training interface are both wirelessly connected to the physiological state analysis module, a user selects a required hand rehabilitation training mode through the brain-controlled active training interface or theauxiliary brain-controlled training interface, and the portable electroencephalogram acquisition equipment is used for acquiring electroencephalogram signals of the user; the physiological state analysis module receives the electroencephalogram signal, is combined with transfer learning, intelligently recognizes rehabilitation actions selected by the user, sends the actions to the brain-controlled active training interface or the auxiliary brain-controlled training interface to be displayed, and sends the actions to the hand rehabilitation device; and the hand rehabilitation device makes corresponding finger or palm actions according to the rehabilitation actions selected by the user and recognized by the physiological state analysis module to help the user to do hand movement. The equipment can assist a user in completing rehabilitation training.

The invention provides a sleep assisting system and method based on portable electroencephalogram equipment. The sleep assisting system comprises the portable electroencephalogram equipment, a cloud server and a terminal. The portable electroencephalogram equipment is configured to collect electroencephalogram data; the cloud server is configured to perform sleep staging and mental state evaluation according to the electroencephalogram data and send a sleep staging result and a mental state evaluation result to the terminal; and the terminal executes corresponding sleep auxiliary control according to the received sleep staging result, and adjusts the sleep auxiliary control according to the mental state evaluation result obtained in real time. Sleep intelligent assistance is achieved through the arrangement of the portable electroencephalogram device, the cloud server and the terminal in a multi-terminal cooperation mode, sleep assistance control is adjusted in real time through real-time sleep staging and mental state, sleep assistance measures can be adjusted in real time according to mental state changes in the adjusting process, personalized recommendation can be achieved, andthe user experience is improved. The working efficiency of the sleep assisting system can be improved, and meanwhile the user satisfaction is improved.

The invention discloses a brain-controlled intelligent automatic photographing system based on portable electroencephalogram acquisition equipment and application. The system comprises portable electroencephalogram acquisition equipment, a human brain intention recognition module and an automatic photographing system which are connected in sequence, the portable electroencephalogram acquisition equipment collects electroencephalogram signals from the brain of a testee, the electroencephalogram intention recognition module analyzes the electroencephalogram signals and determines the photographing intention of a user, and the automatic photographing system automatically executes a photographing task according to the photographing intention of the user. According to the invention, data can beacquired and processed in real time without any early-stage preparation work, so that the real-time performance is relatively high. Accurate acquisition and effective identification of EEG signals can be achieved, and therefore the automatic photographing function controlled by the human brain is achieved. By automatically collecting and analyzing the electroencephalogram signals, automatic photographing controlled by the electroencephalogram signals is realized, and convenience is brought to patients with hand disability or equipment users in some special environments to smoothly meet photographing requirements.

A hand full-finger rehabilitation training and evaluation system based on the artificial intelligence technology is provided with a portable electroencephalogram collecting device, a man-machine interaction interface, an electroencephalogram intelligent decoding module and an intelligent rehabilitation hand device which are connected in sequence, and the system comprises two working modes of a rehabilitation training mode and a rehabilitation effect evaluation mode. In the rehabilitation training mode, display of rehabilitation actions of the user is given, the user carries out motor imagery of the corresponding actions, the corresponding finger joints are driven to move through the air pump according to the imagery, and the corresponding rehabilitation actions are completed. In the rehabilitation effect evaluation mode, the user selects rehabilitation actions and makes corresponding selected finger actions, and rehabilitation effect evaluation is carried out according to the finger actions of the user. By recognizing the action intention of the user, the intelligent rehabilitation hand equipment is driven to make corresponding actions, and the user is assisted in completing all-finger rehabilitation training of the hand. In addition, the user can evaluate the hand rehabilitation effect, a rehabilitation training closed loop is formed, and rehabilitation training is promoted more efficiently.

The invention discloses a portable electroencephalogram sleep monitor, which comprises a shell, an annular plate is fixedly connected to the inner side wall of the shell, an annular sliding groove is formed in the inner side wall of the annular plate, an annular block is rotatably connected to the inner wall of the annular sliding groove, an annular air bag is fixedly connected to the inner side of the annular block, and an air outlet is formed in the inner side of the annular air bag. An annular clamping plate is fixedly connected to the side, away from the annular block, of the annular air bag, a cavity is formed in the annular clamping plate, a plurality of mounting grooves are formed in the side wall of the annular clamping plate, and a plurality of limiting plates are slidably connected to the inner side walls of the mounting grooves. According to the device, an arc-shaped plate moves towards an annular clamping plate, so that a limiting plate, a fixing rod and a spring wire move towards a cavity, then the device is worn on the forehead part of a user to carry out a fixing test, the fixing test can be carried out on users with different forehead sizes by moving the arc-shaped plate, and the practicability of the device is improved.

The present invention provides a portable electroencephalogram signal monitoring method and a system thereof. The method comprising the following steps: acquiring an electroencephalogram signal of a wearer in response to an input monitoring instruction; detecting a current network connection status of the system; when the system is in a networked state, transmitting the obtained electroencephalogram signal to a cloud server and stored to a local server; and when the system is in a networkless state, saving the obtained electroencephalogram signal to the local server.