15459results about How to "Improve computing efficiency" patented technology

The invention discloses a method for accelerating convolution neutral network hardware and an AXI bus IP core thereof. The method comprises the first step of performing operation and converting a convolution layer into matrix multiplication of a matrix A with m lines and K columns and a matrix B with K lines and n columns; the second step of dividing the matrix result into matrix subblocks with m lines and n columns; the third step of starting a matrix multiplier to prefetch the operation number of the matrix subblocks; and the fourth step of causing the matrix multiplier to execute the calculation of the matrix subblocks and writing the result back to a main memory. The IP core comprises an AXI bus interface module, a prefetching unit, a flow mapper and a matrix multiplier. The matrix multiplier comprises a chain type DMA and a processing unit array, the processing unit array is composed of a plurality of processing units through chain structure arrangement, and the processing unit of a chain head is connected with the chain type DMA. The method can support various convolution neutral network structures and has the advantages of high calculation efficiency and performance, less requirements for on-chip storage resources and off-chip storage bandwidth, small in communication overhead, convenience in unit component upgrading and improvement and good universality.

A system for detecting subtle differences in a signal in a set of linearly and / or non-linearly related signals that characterize a sensor-instrumented machine, process or living system. The system employs an improved similarity operator for signal differentiation. Signals or data representative of several linearly and / or non-linearly related parameters that describe a machine, process or living system are input to the inventive system, which compares the input to acceptable modeled states. If one or more of the input signals or data are different than expected, given the relationships between the parameters, the inventive system will indicate that difference. The system can provide expected parameter values, as well as the differences between expected and input signals; or the system can provide raw measures of similarity between the collection of input signals and the collection of acceptable modeled states. The system can be embodied in software or in a micro-controller.

The invention provides a neutral network processor based on data compression, a design method and a chip. The processor comprises at least one storage unit used for storing operating instructions and data participating in calculation, at least one storage unit controller used for controlling the storage unit, at least one calculation unit used for executing calculation of a neutral network, a control unit connected with the storage unit controllers and the calculation units and used for acquiring instructions stored by the storage unit through the storage unit controllers and analyzing the instructions to control the calculation units, and at least one data compression unit used for compressing data participating in calculation according to a data compression storage format. Each data compression unit is connected with the corresponding calculation unit. Occupancy of data resources in the neutral network processor is reduced, the operating rate is increased, and energy efficiency is improved.

A system and method facilitate estimating noise in a received signal. The received signal is formed of a plurality of tones, such as training tones and data tones. Noise is estimated at the training tones, which generally comprise a lesser number of the tones in the received signal than the data tones. The estimated noise at the training tones can be employed to facilitate demodulating and / or decoding data tones in the received signal. In one aspect, the estimated training tone noise can be utilized by a beamformer.

The invention discloses a transformer station inspection tour robot positioning navigation system and a method. Confidence obtained by a laser range finding module and a dead reckoning module is outputted to a map creation module and a pose resolving module; the map creation module creates a laser road sign map and a laser grid map which show a robot operation environment and are inputted into a map storage module for storage; the posture resolving module utilizes map data in the map storage module and output data of the dead reckoning module to perform real-time calculation on the current position and the posture of the robot and accesses the obtained posture data into a path planning module and a motion control module; the path planning module generates robot operation path data which is outputted to the motion control module; the motion control module generates motion control quantity according to the current position and posture data of the robot and the path planning data, and then is driven to execute by a motor. The transformer station inspection tour robot positioning navigation system realizes the accuracy positioning of the inspection tour robot in the transformer station.

The invention relates to a three-dimensional wire frame structure method and system fusing a binocular camera and IMU positioning. On the basis of binocular vision, the invention initializes and fusesinertial measurement information by using a divide-and-conquer strategy, implements tracking, positioning and drawing, and can robustly run in indoor and outdoor environments and complex motion conditions. On the basis of accurate positioning, 3D wireframe reconstruction and iterative optimization are carried out based on the posture of the key frame. Linear segments are matched by local featuresand spatial geometric constraints and back-projected into three-dimensional space. Through the angle and distance constraints, the straight line segments are divided into different sets. Based on thegrouping results, the fitting region is determined and the straight line segments are merged. Finally, a 3-D wireframe structure is output. The invention fuses multi-source information to improve thestability and robustness of the system on the traditional vision-based positioning and mapping method. At the same time, line information is added to the key frame to sparsely express the structuralcharacteristics of the three-dimensional environment, which improves the computational efficiency.

A cluster computer system including multiple network accessible computers that are each coupled to a network. The network accessible computers implement host computer programs which permits the network accessible computers to operate as host computers for client computers also connected to the network, such that input devices of the client computers can be used to generate inputs to the host computers, and such that image information generated by the host computers can be viewed by the client computers. The system also includes a cluster administration computer coupled to the multiple network accessible computers to monitor the operation of the network accessible computers. A method for providing access to host computers by client computers over a computer network includes receiving a request for a host computer coupled to a computer network from a client computer coupled to the computer network, wherein the relationship of the host computer to the client computer is to be such that after the client computer becomes associated with a host computer, an input device of the client computer can be used to generate inputs to the host computer, and such that image information generated by the host computer can be viewed by the client computer. Next, a suitable host computer for the client computer is determined, and the client computer is informed of the network address of the suitable host computer.

Disclosed is an automatic sorting system for household refuse. The system comprises a refuse target identification unit, a refuse sorting control unit, a mechanical arm and a sampling camera which is mounted at the fixed position of a conveying belt for conveying household refuse; the sampling camera shoots the household refuse on the conveying belt in real time and transmits obtained optical images to the refuse target identification unit; the refuse target identification unit receives the optical images in real time and displays the images, according to the characteristics of presorted target refuse, the optical images are treated, targets in the images are identified, and target posture information frames are obtained, and are input into the refuse sorting control unit; and the refuse sorting control unit judges whether a target enters the working section of the leisure mechanical arm or not according to the input target posture information frames and the opposite position of the mechanical arm and the conveying belt, the posture information of the target entering the working section of the mechanical arm is converted into a mechanical arm coordinate system and sent to the corresponding mechanical arm, and the corresponding mechanical arm is controlled to grab the corresponding target.

The invention relates to a three-dimensional entity model surface finite element mesh automatic generation method which has the characteristics of good dimension control performance of mesh quality, density and dimension, good convergence in a dividing process, high calculation efficiency, stability and reliability. The method comprises the following steps: (1.1) establishing a three-dimensional geometrical model, reading an STL neutral file of a model surface, and reconstructing a topology relation of triangle patches; (1.2) according to a relation between a triangle patch and an adjacent patch, grouping surface triangle patches, wherein each group of triangle patches is a characteristic face; (1.3) determining boundaries of each characteristic face, and determining characteristic edges on each characteristic face boundary; (1.4) according to mesh density distribution, generating mesh nodes on each characteristic edge, and expressing boundaries of the characteristic face with mesh node rings on the boundaries; (1.5) selecting a cut surface and an optimal dissection surface, and generating mesh nodes on cut lines and dissection lines; (1.6) generating a surface mesh on each characteristic face, and carrying out smoothing process.

An intelligent vehicle highway system collects and provides real-time traffic data to a vehicle traveling on a continental roadway network. A digitized continental roadway network has nodes interconnected by links that define a digitized representation of the continental roadway network. To enable intelligent data collection and navigation over large expanses of the continental network, which would otherwise be computationally onerous, the digitized continental roadway network is partitioned into a plurality of digitized roadway subnetworks. The onboard vehicle navigation device has a processor for executing an application that instantiates a subset of the digitized roadway subnetworks in a vicinity of a current position of the vehicle to collect and provide relevant real-time traffic data to the vehicle in a computationally efficient manner.

The invention provides a three-level midpoint potential balance control method based on zero sequence voltage injection, which is a control method capable of effectively controlling the balance of the midpoint potential in a high-power diode clamped three-level inverter. The control method comprises: collecting to obtain voltage values and three-phase output current values of two capacitors on the two sides of a direct current bus through voltage and current sampling circuits, calculating the voltage difference of two capacitors, judging whether the midpoint level is balanced and judging the relation of the three-phase output current and midpoint current during vector output under multi-carrier wave PWM modulation policy, calculating to generate a three-phase modulation voltage by using a zero sequence voltage injection method according to a zero sequence voltage selection principle, comparing with carrier waves to generate a needed switching sequence so as to achieve the purpose of controlling the midpoint level balance in the three-level inverter. The invention not only controls the midpoint level effectively, but also has the advantages of simple control method and strong robustness, and can ensure the inverter to work stably in a total range.

Weather forecasting systems and methods for deriving and producing very short-term weather forecasts. Weather data and forecast information maybe input to derive very short-term weather forecasts in the 0-6 hour time frame. The system and methods include an expert system employing a hybrid or blending of forecasting approaches, with dynamic or intelligent arbitration of the different numerical, statistical, and human-driven techniques to produce more accurate weather forecasts for very short-term time periods. A calibration or internal verification against ground truth may be run independently with a time lag to produce more accurate future predictions of atmospheric state. The systems and methods may run in modes that produce either high resolution weather forecasts in the short-term period of 0-6 hours or a combination of synthetic, real-time weather observations / conditions and high resolution, short-term weather forecasts.

The invention discloses a method of compressing a neural network. The connection relation of the neural elements of the neural network is expressed by a plurality of matrixes. The compression method comprises steps that a dividing step: a plurality of matrixes are divided into a plurality of matrixes, and every matrix is divided into a plurality of sub-matrixes; a compressing step: every sub-matrix is compressed, and every sub-matrix is compressed into a sparse matrix; and an encoding step: every compressed sparse sub-matrix is encoded. The invention provides a device used for compressing the neural network.

The invention provides a prospective interpolation system for compressing and smoothening small segment paths. The prospective interpolation system comprises a path smoothening module, a curve scanning and segmenting module, a bidirectional acceleration module, a speed planning module and an interpolation module, wherein the path smoothening module is used for extracting small segment coordinate information in codes by reading information of G01 segments of numerical control codes G, conducting calculation according to the coordinate information and conducting path compression and smoothening on small segments; the curve scanning and segmenting module, the bidirectional acceleration module and the speed planning module complete S-shaped speed planning tasks with limited jerk; the interpolation module is used for generating discrete interpolation points according to planning speed obtained through calculation; the interpolation points can be stored and used for position closed-loop control. The prospective interpolation system is high in calculation efficiency in the whole process, small in calculation quantity, simple in programming realization and capable of being further applied to a high-speed and high-precision numerically-controlled machine tool.

The invention discloses an information recommendation method based on graph convolution and neural collaborative filtering. In combination with the advantages of a graph convolution neural network model, fusion processing can be carried out on various information in an intuitive manner, so that not only feature information of a user but also attribute information of the user can be received, and relatively good recommendation performance can be achieved for sparse score data; and input and parameters of the model are subjected to optimization modeling by using multiple skills, so that the detail problems encountered possibly are solved. In addition, a nonlinear neural network-based collaborative filtering method is introduced as a decoder part of the model, so that user and article codes output by a graph convolution encoder can be well utilized, and through an end-to-end model, all processes run in the same framework without being trained separately. Through the processing of input data and the training and prediction of the model, a complete score prediction matrix can be obtained.

The invention discloses a method for autonomously localizing robots on the basis of laser radar. The method includes randomly generating N particles to form particle swarms around initial locations ofthe robots, and updating the particle swarms according to robot real-time movement distances and real-time rotation angles measured by sensors of the robots at current operation moments of the robots; computing the superposition quantity of point cloud of the laser radar and obstacles of maps for each particle to use the superposition quantity as a score of the particle, computing weighted position and posture average values of the particle swarms by the aid of the score, which is used as a weight, of each particle and utilizing the weighted position and posture average values as AMCL (adaptive Monte Carlo localization) estimation positions and posture; utilizing the AMCL estimation positions and posture as initial values, acquiring scanned and matched positions and posture by the aid ofscanning and matching algorithms on the basis of Gauss-Newton iterative processes and utilizing the scanned and matched positions and posture as the optimal positions and posture of the robots at thecurrent operation moments; re-sampling the particle swarms by the aid of AMCL algorithms to ultimately obtain the global optimal positions and posture of the robots during operation. The global optimal positions and posture of the robots are used as localization results. The method has the advantage that the localization convergence rate can be greatly increased, and the localization precision andthe localization stability can be greatly enhanced.

The invention relates to an indoor scene three-dimensional reconstruction method based on a single depth vision sensor. The method is technically characterized by including the following steps of firstly, continuously scanning a whole indoor scene through the single depth vision sensor; secondly, conducting preprocessing including denoising, hole repairing and the like on collected depth data to obtain smooth depth data; thirdly, calculating point cloud data corresponding to the current depth frame according to the depth data collected in the second step; fourthly, conducting registration on point cloud obtained through different viewpoint depth frames to obtain complete point cloud of the indoor scene; fifthly, conducting plane fitting, achieving segmentation of the special point cloud, and establishing an independent and complete three-dimensional model of each object in the indoor scene. Scanning devices used by the method are simple; scanned data information is comprehensive, and the point cloud registration accuracy calculation efficiency is effectively improved; finally, a complete and high-quality three-dimensional model set with a geographic structure and a color map can be established for the indoor scene.

An enhanced multi-point statistical (MPS) simulation is disclosed. A multiple-grid simulation approach is used which has been modified from a conventional MPS approach to decrease the size of a data search template, saving a significant amount of memory and cpu-time during the simulation. Features used to decrease the size of the data search template include: (1) using intermediary sub-grids in the multiple-grid simulation approach, and (2) selecting a data template that is preferentially constituted by previously simulated nodes. The combination of these features allows saving a significant amount of memory and cpu-time over previous MPS algorithms, yet ensures that large-scale training structures are captured and exported to the simulation exercise.

The invention discloses a simulating method of the forming process of an unconventional oil and gas reservoir hydraulic fracturing complex fracture net. The method includes the steps of a, reestablishing natural fracture distribution, estimating the properties of natural fractures, obtaining rock mechanical information and stratum stress information of a stratum from log data or a geological model, and obtaining a data file related to the well factory construction process; b, inputting the obtained parameters in an established natural fractured reservoir fracturing model coupling a well cylinder, fractures and the stratum; c, conducting numerical value solving on the model to obtain after-fracturing information such as fracture forms, opening degree distribution and pressure intensity distribution; d, analyzing the fracturing effect through a model calculating result, and making a preparation for numerical value simulation of the later-period production process. The fractured reservoirfracturing numerical value simulating method coupling the well cylinder flowing, the fracture deformation expanding, the multi-state natural fractures and the flowing of fluid in the fractures can quantitatively analyze the form of the unconventional reservoir segmented volume fracture net and is an effectively means for evaluating and optimizing the fracturing scheme.

The invention relates to an image classification method capable of effectively preventing a convolutional neural network from being overfit. The image classification method comprises the following steps: obtaining an image training set and an image test set; training a convolutional neural network model; and carrying out image classification to the image test set by adopting the trained convolutional neural network model. The step of training the convolutional neural network model comprises the following steps: carrying out pretreatment and sample amplification to image data in the image training set to form a training sample; carrying out forward propagation to the training sample to extract image features; calculating the classification probability of each sample in a Softmax classifier; according to the probability yi, calculating to obtain a training error; successively carrying out forward counterpropagation from the last layer of the convolutional neural network by the training error; and meanwhile, revising a network weight matrix W by SGD (Stochastic Gradient Descent). Compared with the prior art, the invention has the advantages of being high in classification precision, high in rate of convergence and high in calculation efficiency.

The invention discloses a multi-target detection method based on short-time Fourier transform and fractional Fourier transform, which belongs to the technical field of the radar target detection. The method comprises the following steps that the short-time Fourier transform is firstly used for conducting the primary detection on a signal, then a binaryzation method is used for processing a primary detection result, phase position of the signal is kept in the processing, the fractional Fourier transform is used for detecting a signal after being restored by the short-time Fourier transform, by adopting multiple methods for combined processing, advantages of overcoming phenomenon that a strong signal side lobe presses a weak signal main lobe, improving the signal-to-noise ratio of the signal to be detected, and solving the problem of the large false alarm possibility which is caused by adopting traditional method to detect the signal at the low signal-to-noise ratio can be realized; and meanwhile, an image contrast method and a gradual elimination method are adopted, multiple strong signals and weak signals with different or identical frequency modulation rates can be detected by utilizing the space and power strength information of the signal, so that the detection probability and the calculation efficiency can be further improved, easiness in project realization is realized, and the method is worth of being adopted and popularized.

The invention discloses a method and system for map matching of transportation vehicle GPS (Global Position System) data. In the invention, a map matching process of the transportation vehicle GPS data is completed by structuring high-efficiency map matching grid indexes and using a simplified and accurate matching calculation, so that the operation efficiency of matching of the transportation vehicle GPS data is greatly improved, and the processing efficiency is thousands times higher than that of the traditional map matching method; and the matching positioning of a vehicle in a complex road network is assisted and judged by tracking the historical matching road state of the vehicle and using the topological connectivity of the road network, so that the accuracy of the map matching of the transportation vehicle GPS data can be greatly improved.

The invention discloses a face mage super-resolution method which fuses global features and local detail information. The invention can synthesize a high-resolution face image according to a low-resolution face image based on a sample image. Firstly, a local maintaining mapping algorithm and a radial basic function return algorithm are combined together to get a global high-resolution face image; then a neighborhood reconstruction method is adopted to synthesize a high-resolution face residual image block and consequently form a high-resolution face residual image by combination; finally, the high-resolution face residual image is overlapped to the high-resolution face image to obtain a final super-resolution effect. The technology provided by the invention can synthesize the clearer high-resolution face image, improve the recognition of the face image and have important application significances on video monitoring, face recognition and other aspects.

The invention relates to an airline routing algorithm of an unmanned plane in a large-range complicated three-dimensional space. The algorithm comprises the following steps: first dividing a three-dimensional space on the basis of a 2.5-dimensional grid (each grid point includes longitude, altitude and elevation information); improving the A* cost function by comprehensively considering the influence factors such as airline height, detected probability, airline distance under the constraint conditions of radar, disaster weather and forbidden areas, and determining an initial airline on the basis of an algorithm search flow; serially processing the initial airline to obtain a final flying airline for meeting the performance constraint of the unmanned plane (such as minimal step length, turning radius, climbing rate, safety height). The algorithm is good in stability and astringency, high in efficiency, capable of meeting the wide-range low-altitude airline routing requirement and applicable to relevant fields such as military, national defense, emergency relief.

A method of and computer-readable medium containing instructions for high accuracy, reliable position determination. A high precision GPS-RTK system using the present novel techniques is initialized instantaneously or near instantaneously. To improve the computational efficiency and to improve the reliability of the procedure, advances in data functional and stochastic modeling, validation criteria, adaptation and system design were achieved. A position estimate using an integrated method is determined. Ambiguity resolution of the position estinate is enhanced by applying a quality control procedure using derived validation criteria. A second position estimate based on the enhanced ambiguity resolution is derived.

A system to provide enhanced computational efficiency in a simulation of particle transport through a medium, program product, and related methods are provided. The system can include a simulation data administrator server having access to an interaction database including records related to parameters describing interactions of particles in an absorbing medium to provide particle interaction parameters, and a simulated dose calculation computer in communication with the simulation data administrator server through a communications network. The system can also included simulated dose calculation program product stored in memory of the simulated dose calculation computer and including instructions that when executed by a processor causes the processor to perform for each of a plurality of particles deliverable from a particle source the operations of providing parameters for a medium to perform a Monte Carlo simulation to develop a map of simulated absorbed dose in the medium, and artificially adjusting simulation particle fluxes to achieve a substantially constant variance throughout a depth of the medium.

The present invention discloses an integrated support vector machine mixed intelligent diagnosis method of machine failure. Said method includes the following steps: respectively adopting and lifting small wave packet, utilizing frequency band and empirical mode decomposition process to decompose vibration signal according to the eigen mode component and extract time domain statistical character of decomposed signal to form total characteristic set; providing characteristic distance evaluation technique and characteristic evaluation index; utilizing said characteristic evaluation index to select most sensitive characteristic set from the total characteristic set; using said most sensitive characteristic set as diagnosis characteristics and creating integrated support vector machine mixed intelligent diagnosis model so as to implement intelligent diagnosis of machine failure state.

The invention discloses a real-time precise orbit determining method of a short orbit arc low earth orbit (LEO) navigation satellite. The method is characterized in that four or more ground receivers are used for tracking navigation signals of a plurality of GNSS (Global Navigation Satellite System) navigation satellites and LEO navigation satellites, and transmitting the navigation signals to a data center in real time. The method comprises the following steps: I, acquiring and preprocessing observing data; II, performing precise time synchronization on the receivers; III, calculating tropospheric delay in an LEO gazing direction by using tropospheric delay in a vertical direction and a projection function; IV, correcting hardware delay of the receivers to build an LEO determining geometric observing equation; V, solving an LEO precise orbit and a precise clock error through a dynamical model and the geometric equation of the LEO; VI, distributing the LEO precise orbit and the precise clock error in real time. By adopting the method, the problem of need of post-processing due to incapability of calculating the precise orbit of a low earth orbit satellite can be solved.