18results about How to "Improve Feedback Accuracy" patented technology

The invention discloses a feedback method and system for patient intention brain wave recognition based on a brain-computer interface, and the method comprises the steps: collecting an electroencephalogram signal and associated data of the brain-computer interface of a patient, and carrying out the preprocessing of the electroencephalogram signal and the associated data; performing pattern classification on the electroencephalogram signals to obtain pattern data, and performing intention correction on the pattern data by adopting the associated data to obtain corrected data; electroencephalogram signal recognition is carried out on the correction data to obtain recognition data, and a patient intention brain wave recognition feedback model is constructed according to the recognition data; and optimizing the patient intention brain wave recognition feedback model according to the feedback error, inputting data to be fed back into the optimized patient intention brain wave recognition feedback model, and outputting a feedback result. The method not only can improve the feedback precision of patient intention brain wave recognition based on the brain-computer interface, but also has good interpretability, and can be directly applied to a feedback system of patient intention brain wave recognition.

The invention discloses a pneumatic control device and related equipment. The pneumatic control device comprises a positioner, an air cylinder and a connecting part; the positioner is connected with the cylinder through the connecting part; the connecting part comprises a feedback device, a feedback linear plate and a first connecting plate; the mounting stand column is used for fixing the positioner on the feedback device; the feedback device comprises a first feedback shaft, and the positioner connecting shaft is connected with the first feedback shaft and a second feedback shaft of the positioner so as to transmit a rotation angle fed back by the feedback device to the second feedback shaft; the first connecting plate is used for connecting a piston rod of the air cylinder and the feedback linear plate so that the piston rod can drive the feedback linear plate to move in the horizontal direction in the horizontal movement state, and displacement of the piston rod in the horizontal direction is converted into the rotation angle of a first feedback shaft in the feedback device through the feedback linear plate. Linkage and accurate position feedback between the air cylinder and the positioner can be achieved, the overall structure is compact, and the device is suitable for various installation spaces.

The present invention belongs to the technical field of intelligent mobile communication, and particularly relates to a CSI feedback method of a large-scale MIMO system based on deep learning, comprising: obtaining a CSI channel matrix of a downlink in a large-scale MIMO system under an FDD standard; performing a two-dimensional DFT transformation on the obtained CSI channel matrix of the downlink to obtain a CSI matrix that is sparse in an angle delay domain, and obtaining a truncated matrix according to the matrix; constructing an encoder of a CSI feedback network at a user end, and converting the truncated matrix into a codeword vector through the encoder; constructing a decoder of the CSI feedback network at a base station end, and passing the codeword vector obtained by the encoder through the decoder to obtain an estimated value of the truncated matrix; the present invention avoids the feedback network from being too deep, and adopts a horizontal expansion method, that is, increasing the generalization of the feedback network through multi-resolution convolution, and increasing the feature extraction capability of each convolution kernel through asymmetric convolution.

The invention relates to the technical field of air pressure sensing detection, in particular to an air pressure feedback method and equipment based on high-precision pressure sensing. The method comprises the following steps: carrying out pressure sensing element space positioning calculation on air pressure feedback equipment, carrying out topological distribution fitting, and constructing an element topological distribution diagram; acquiring a historical pressure sensing sample of the high-precision pressure sensing element; performing dynamic pressure deformation rendering on the element topology distribution map based on a historical pressure sensing sample, thereby constructing a dynamic pressure deformation visual network; performing environment barometric disturbance mapping on the dynamic pressure deformation visual network according to the barometric feedback equipment to obtain a barometric disturbance visual network; and carrying out real-time operation monitoring based on the barometric disturbance visual network, and carrying out pressure visual mapping to obtain a real-time pressure deformation visual network. According to the invention, efficient and accurate element air pressure feedback is realized.

The utility model discloses a machining platform and laser machining equipment, the machining platform comprises a base, an adsorption platform, a linear motor driving mechanism and a grating ruler, the linear motor driving mechanism comprises a first driving assembly and a second driving assembly, the first driving assembly is arranged on the base, and the first driving assembly is connected with the second driving assembly; the adsorption platform is connected to the second driving assembly, the first driving assembly is used for driving the adsorption platform and the second driving assembly to move in the first direction, the second driving assembly is used for driving the adsorption platform to move in the second direction, the grating ruler is arranged on the base, and the length of the grating ruler extends in the moving direction of the adsorption platform. The grating ruler is used for detecting the moving distance of the adsorption platform. The linear motor is used for driving, transmission gaps are avoided to the maximum extent, errors caused by an intermediate mechanical transmission system are greatly reduced, the grating ruler is arranged, the feedback precision of a single-shaft system is improved, and therefore the machining quality of products is improved.

This application provides a self-feedback jitter control system for laser gyroscopes, relating to the field of laser gyroscope technology. It includes a jitter controller, a drive amplifier circuit, a jitter wheel, a sampling resistor R, and a jitter signal extraction circuit. The jitter controller outputs a jitter control signal, which is input to the drive amplifier circuit. The drive amplifier circuit amplifies the jitter control signal and outputs a jitter drive signal, which is connected to both the jitter signal extraction circuit and one end of the sampling resistor R. This application provides a self-feedback jitter control system for laser gyroscopes that eliminates the need for separate piezoelectric ceramic sensors, magnetoelectric sensors, or optical sensors found in traditional jitter control systems. It eliminates the need for additional piezoelectric ceramic sensors and allows all piezoelectric ceramics on the jitter wheel to be used for driving, significantly improving jitter drive efficiency, saving on sensor hardware procurement, installation, and maintenance costs, and simplifying the overall system structure.

The invention relates to the technical field of geographic image analysis, and discloses a geographic surveying and mapping data acquisition and processing system based on image analysis. According to the system, geographic image data are acquired by applying an unmanned aerial vehicle, a satellite and ground sensor equipment through a data acquisition module, image denoising, geometric correction, radiation correction and image enhancement are performed on an acquired image through an algorithm formula by a data preprocessing module, and geographic features are extracted from the preprocessed image by a feature extraction module; comprising surface feature classification, edge detection and texture analysis, a data analysis module analyzes extracted features and calculates a geographic image area and a geographic image perimeter, and a data visualization module displays an analysis result in a map superposition, chart image and 3D visualization mode. The geographic image is analyzed, the geographic information is displayed in a charting form, the latest geographic change is reflected, and the feedback accuracy of the geographic information is improved.

The present invention discloses a liquid nitrogen storage device for visualizing cell liquid nitrogen records, and belongs to the field of cell storage technology. A liquid nitrogen storage device for visualizing cell liquid nitrogen records comprises a liquid nitrogen storage tank and a cell culture dish, and also comprises a cell placement tube rack, which is arranged in a liquid nitrogen freezing chamber inside the liquid nitrogen storage tank, and a liquid nitrogen replenishing valve port is arranged on the surface of one side of the liquid nitrogen storage tank, and the liquid nitrogen replenishing valve port is connected with the liquid nitrogen freezing chamber. In order to solve the problem that it is inconvenient to check frozen cells due to the low temperature environment, the traditional paper version of the freezing and revival record is cumbersome, cannot be efficiently positioned to the designated position, and is inconvenient for the management and use of the cell bank, the NFC reader card on the surface of the tank body corresponds to the cell culture dish at the same height, and the cell information can be obtained conveniently, quickly and intuitively. When it is necessary to check the storage status of the cells, the current cell distribution can be obtained by using a mobile phone with NFC function or a reader close to the NFC reader card on the surface of the tank body.

The invention provides a non-contact valve position feedback method and device, relates to the technical field of valve position monitoring, is applied to an electric control valve, and comprises the following steps: acquiring reference capacitance values and position information of a plurality of capacitive sensing electrodes arranged along the displacement direction of a valve rod, and responding to the displacement of the valve rod; collecting the current capacitance values of the plurality of capacitive sensing electrodes in real time, performing signal preprocessing on the current capacitance values of the plurality of capacitive sensing electrodes, calculating the capacitance variation of each capacitive sensing electrode based on the preprocessed current capacitance values and the corresponding reference capacitance values, and calculating the capacitance variation of each capacitive sensing electrode according to the capacitance variation. And determining the current position information of the valve rod on the basis of each capacitance variation and the corresponding position information, thereby solving the technical problem that the valve position feedback precision is difficult to guarantee because the existing valve position feedback technology generally faces inherent limitations such as mechanical wear, complex structure or weak anti-interference capability. The effect of improving the valve position feedback precision is achieved.

The invention relates to the technical field of computer systems, in particular to a self-adaptive model updating method of a full-data AI management and control system. The method comprises the following steps: step 1, acquiring original data of a system, performing tensor decomposition on the original data, and extracting spatial-temporal features to obtain feature tensors; projecting the feature tensor into a nonlinear dynamic space through the interaction of the vortex field and the nonlinear function to obtain a mapping result; 2, performing dynamic evolution of the feature flow on the mapping result to obtain an evolution result; outputting the prediction model output; calculating the entropy increase rate of the system; 3, calculating a feedback correction value of the system according to the entropy increase rate; and updating the adaptive model of the system according to the feedback correction value. Through the self-adaptive feedback mechanism, the system can realize efficient and real-time dynamic adjustment in a complex and changeable environment, and the prediction accuracy and stability of the system are remarkably improved.

The invention relates to a puncture robot system. The puncture robot system comprises a robot; a puncture needle attached to the robot; the main control device is in communication connection with the robot, an operator is arranged on the main control device, and the operator is used for controlling the robot to drive the puncture needle to execute puncture operation; the computed tomography equipment is in communication connection with the main control device and used for scanning and at least outputting an image of the area where the puncture needle is located; the slave end force measuring piece is mounted on the puncture needle and is used for detecting puncture resistance when the puncture needle is inserted; the driving part is connected to the operator, the slave end force measuring part is in communication connection with the driving part, and the driving part is used for applying feedback resistance to the operator based on the puncture resistance; the main end force measuring piece is installed on the operator and used for detecting the feedback resistance, the main end force measuring piece is in communication connection with the driving piece, and the driving piece can conduct negative feedback adjustment on the feedback resistance based on the puncture resistance and the feedback resistance so as to reduce the difference value between the feedback resistance and the puncture resistance. The puncture robot system can improve the feedback precision of puncture resistance.

The invention relates to a data generation method and device, computer equipment and a storage medium. The method comprises the following steps: selecting a target sub-graph from a target knowledge graph, wherein the target sub-graph relates to at least one triple; generating a first question by using a target question generation network according to the at least one triple and the first answer in the target sub-graph, the target question generation network being a trained neural network, and the target question generation network being a second answer in the target sub-graph; the training data of the target question generation network comprises a triple involved in a sub-graph used for training in a knowledge graph used for training, an answer used for training in the sub-graph used for training, a labeled question corresponding to the answer used for training and difficulty information of the labeled question, and the difficulty information of the labeled question represents the difficulty of the labeled question; the difficulty information of the annotation problem is determined according to the credibility of the entities in the annotation problem and the number of other entities matched with the entities in the annotation problem in the sub-graph for training; and generating a first question-answer pair according to the first question and the first answer.

The present application discloses an information reporting and information receiving method, device, equipment and storage medium, and relates to the field of mobile communications. The method comprises: a terminal sends channel state information to a network device, the channel state information comprises time domain parameters and / or Doppler domain parameters, and the terminal reports the channel state information comprising the time domain parameters and / or Doppler domain parameters to the network device, the time domain parameters and / or Doppler domain parameters can indicate the coherence time of the channel, so as to determine the time domain correlation of the channel based on the determined channel coherence time, reduce the signaling overhead and improve the CSI feedback accuracy.

The invention discloses an informationized physical education platform management system, and particularly relates to the field of physical training data management, which is used for solving the problem of accurate classification and feedback of multi-instrument training data, and comprises the following steps: firstly, based on physiological data fluctuation characteristics, capturing switching period data, and ensuring the continuity and timeliness of the training data; then, by means of the transition response consistency index and the target instrument feature matching degree, effective transition data are precisely defined, physiological feature data of all instruments are clearly distinguished, and the classification precision is improved; fine classification and label generation are carried out on defined effective transition data through a target instrument dynamic feature model, and independence and consistency of the data are ensured; finally, abnormal data are screened out by adopting a self-adaptive elimination mechanism, high-quality data are reserved to generate personalized feedback, the pertinence of the feedback is enhanced, a closed-loop system from data acquisition to feedback generation is constructed, and scientific support is provided for physical training data management.

The invention discloses a CPR feedback detection method based on pressure detection and acceleration cosine reconstruction, and the method specifically comprises the following steps: S1, collecting acceleration data and pressure data, and carrying out the preprocessing; s2, pressing starting and ending points are detected according to the preprocessed pressure data, the period of changing the pressure value from the minimum point to the maximum point is recorded as a pressing period, the period of changing the pressure value from the maximum point to the minimum point is recorded as a springback period, and pressing frequency is calculated; s3, respectively performing cosine reconstruction on the accelerations of the press-down period and the rebound period according to the press starting point and the press ending point to obtain a corresponding first acceleration reconstruction coefficient and a corresponding second acceleration reconstruction coefficient; s4, according to the first acceleration reconstruction coefficient and the second acceleration reconstruction coefficient, the pressing depth and the rebound depth are calculated.

The present invention belongs to the field of mechanical processing technology, and proposes an electric-driven high-precision force-controlled polishing device for complex surface processing. It includes a linear drive module, a rotary drive module, a motion transmission module, a force sensing module, a displacement sensing module and a posture sensing module. The motion transmission module transmits linear and rotary motions to the end polishing tool; the sensing module feeds back force, displacement and posture signals to the controller in real time, and combines the gravity compensation algorithm and the force control algorithm to achieve real-time control of the end polishing process force. The present invention realizes the layout optimization of the drive module and the force sensing module with a smart motion transmission structure, avoids the interference of the inertial force of the rotary drive mechanism and the electromagnetic force of the voice coil motor, improves the force control performance during the polishing process, and improves the controllability of the tool speed by using a servo motor with closed-loop control, which provides a prerequisite for achieving accurate material removal and is suitable for high-precision force-controlled polishing of complex surfaces.

The utility model relates to a somatosensory equipment control system, which comprises a main control module, a motor driving module, an electric stimulation driving module, somatosensory clothes, a motor and an electrode bandage, wherein the motor and the electrode bandage are arranged on the somatosensory clothes; the main control module is in wired connection with the motor driving module, the motor driving module is electrically connected with the motor, the main control module is in wireless connection with the electrical stimulation driving module, and the electrical stimulation driving module is electrically connected with an electrode on the electrode bandage; the main control module is used for converting the somatosensory data into motor control data and / or electrical stimulation control data after receiving the somatosensory data; the motor driving module is used for controlling the motor to work according to the motor control data; the electrical stimulation driving module is used for generating charging and discharging signals of positive and negative electrodes on the electrode bandage according to the electrical stimulation control data. According to the utility model, motion sensing data feedback is carried out through two modes of motor and electrical stimulation, the wearable motion sensing device has the beneficial effects of convenient wearing, high feedback precision, low delay and the like, and the user experience is greatly improved.

The present invention discloses a crane arm motion control method, system and crane, wherein the control system comprises a combined inertial navigation system, a handle, and a controller, wherein the handle transmits handle angle information to the controller, the combined inertial navigation system collects crane arm measurement information, outputs feedback parameters after processing and feeds back to the controller, and the controller determines the crane arm target motion parameters in the current state according to the handle angle information and the working condition, and adjusts the output parameters after performing parameter judgment based on the feedback parameters. The present invention solves the problems of low control accuracy, poor controllability and safety control caused by motion control through indirect physical quantities in the prior art.