365results about How to "Calculation speed" patented technology

The invention provides a log event correlation analysis system and a method, which comprises the steps of: collecting log data, extracting characteristic data of the log data through a preset regular expression, constructing log events with uniform format according to the extracted characteristic data, querying treatment strategies of the log events, implementing cross correlation analysis and event flow logic correlation analysis to the events according to the instruction of strategies, as well as implementing risk evaluation on the log events and automatically responding. The method effectively reduces false-alarm, improves the objectivity of risk evaluation and the warning thereof has higher actual direction on users. The invention also provides a log event correlation analysis system corresponding to the method.

The embodiment of the invention provides a face detection method and device, and the method comprises the steps: employing a pre-trained first convolution neural network model for the classification of a to-be-detected image, screening out at least one candidate region from a to-be-detected image input region, employing a pre-trained second convolution neural network model for the classification of the candidate regions, screening out at least one selected region from the candidate regions, carrying out the removing and clustering of detection frames according to at least one selected region,so as to obtain a human face detection region. Because the input region of the first convolution neural network is very small, the calculation speed of human face detection is improved. In addition, because the two convolution neural network models at different depths are employed, the secondary classification of the obtained candidate regions is carried out, and the classification prediction is enabled to be more accurate. Meanwhile, a large number of false detection samples are filtered out, and the detection performances are improved.

The invention discloses an approximate-computation-based binary weight convolution neural network hardware accelerator calculating module. The hardware accelerator calculating module is able to receive the input neural element data and binary convolution kernel data and conducts rapid convolution data multiplying, accumulating and calculating. The calculation module utilizes the complement data representation, and includes mainly an optimized approximation binary multiplier, a compressor tree, an innovative approximation adder, and a temporary register for the sum of the serially adding part. In addition, targeted to the optimized approximation binary multiplier, two error compensation schemes are proposed, which reduces or completely eliminates the errors brought about from the optimized approximation binary multiplier under the condition of only slightly increasing the hardware resource overhead expense. Through the optimized calculating units, the key paths for the binary weight convolution neural network hardware accelerator using the computation module are shortened considerably, and the size loss and power loss are also reduced, making the module suitable for a low power consuming embedded type system in need of using the convolution neural network.

A facial tracking method for detecting and tracking at least one face image in a region during a time period. The facial tracking method includes a step of performing an image acquiring operation, a step of performing a facial detecting operation to detect whether there is any face image in the entire of a current photo image, and at least one step of performing a facial tracking operation. For performing the facial tracking operation, plural tracking frames are located around a face image of the current photo image, and a similarity between the face image of the current photo image and the image included in each tracking frame in order to judge whether the face image exists in the next photo image. By the facial tracking method of the present invention, the time period of tracking face images is largely reduced.

The invention discloses a fully convolutional neural network-based screening face image identification method and device. The method includes the following steps that: screening face images and corresponding clear face images which form image pairs are collected, and the image pairs are utilized train a fully convolutional neural network which is used for restoring a clear face image from a screening image, namely performing de-screening; and when identification is carried out, a screening face image is inputted into a trained de-screening model, so that a clear face image can be obtained so as to be used for performing a subsequent face identification task. According to the method and device of the invention, the fully convolutional neural network is adopted as the main body of a learning frame, so that the characteristics of larger visual receptive field and faster computing speed of the fully convolutional neural network can be utilized; and according to the design of the training of a target function, pixel-level reconstruction loss and face feature-level reconstruction loss are combined, a spatial transformation module is used in a matched manner to perform precise perfect alignment on face regions in the network so as to realize the accurate extraction of the features of the face regions. With the method of the invention adopted, the clear face image can be restored from the screening image, face features can be kept relatively stable during a restoration process, and therefore, the identification accuracy of the screening face image can be greatly improved.

The invention discloses an image white balance method based on a convolutional neural network. The method is applied to a computing device. The method comprises the steps of collecting multiple real scene original images with reference colors in different scenes, and extracting two-dimensional chromatic value histograms of the real scene original images and to-be-processed images, wherein the chromatic values comprise two of R gain, B gain and G gain; obtaining ideal correction parameters set when a user corrects the real scene original images; designing the convolutional neural network for carrying out image white balance correction; training the convolutional neural network according to the two-dimensional chromatic value histograms of the real scene original images and the ideal correction parameters; and inputting the two-dimensional chromatic value histograms of the to-be-processed images into the trained convolutional neural network, thereby obtaining the ideal correction parameters of the images, and correcting the images according to the ideal correction parameters. The invention also discloses an image white balance device based on the convolutional neural network and the computing device.

The invention relates to a method for executing the phasor correcting for a synchronous phasor measuring apparatus, used for guaranteeing the accuracy of phasor calculating. In the method in the prior art, the hardware is adopted to measure the frequency and a method for adjusting a data window is adopted to guarantee the accuracy of the phasor measuring. In the method of the invention, a circuit positive sequence voltage is adopted to calculate the circuit frequency, after the offset deltaf of the system frequency relative to 50 Hz is calculated out, a least-squares method is adopted to fit the a series of amplitudes and angle error curve in 45 to 55 Hz, then the phasor is corrected by a look-up table. The method of the invention has fast computational speed, strong adaptability and high accuracy.

The invention discloses a method for detecting network traffic anomaly based on super-statistics theory, which comprises the steps that: (1) a distribution model is selected according to the actual characteristic of the network traffic and the distribution meets the requirements of test for the fitting of distribution of the network traffic; (2) slow variable sequence of the time sequence of the network traffic, namely, distribution parameter sequence, is calculated according to the distribution model; (3) the network traffic anomaly is detected according to the abnormal fluctuation of the slow variable sequence. By establishing the network traffic model based on the super-statistics (statistics of statistics), the method of the invention can describe the time sequence of the network traffic which shows abruptness, non-stationarity, long-range dependence and heavy-tail and carry out anomaly detection on the network traffic. The slow variable sequence of the time sequence of the network traffic calculated by the method of the invention accurately describes the characteristics of the network traffic; the network traffic can be accurately analyzed by analyzing the slow variable sequence and calculating work is greatly reduced. The experiments indicate that the method for detecting the network traffic anomaly based on the slow variable is obviously superior to the traditional detection method.

The invention discloses a high precision direction measurement method for linear arrays, comprising: forming frequency domain traditional wave beam for the two-dimensional space-time signals received by a linear array; scanning in the wave beam domain to obtain a target angle measured roughly; dividing the linear array into a plurality of sub arrays; in the target angle range measured roughly, processing frequency domain traditional wave beam formation and focusing on the space-time two dimension signals received by each sub array to form frequency domain-wave number data; in the target angle range measured roughly, processing the frequency domain-wave number data according to a wideband focusing minimum variance distortion-less method, to obtain the direction of target signal. The invention has high calculation speed, can realize real-time processing, has high algorithm robustness, and has high target detection precision.

The invention discloses an open type movement control card based on two-stage DSP parallel device and the control method. The system employs the two-stage control structure with plural CPU parallel processing for separating the general control function and the specific control function of the motor; the control-class CPU as the core of the control card, controls and coordinates the entire system operation; employing programmable logic gate array FPGA to construct communication interface, connecting the control central-class processing unit and execute-class motor control unit with the FPGA chip, realizing high-speed transmission of data and synchronizing control of motor vial FPGA controlling FIFO and the synchronizing status signal. The control method includes central processing discrete control trace, resetting and taking velocity inversion with execute-class CPU, and PID controlling servo motor via changing parameter position.

The invention is for a method and system for encrypting and decrypting image/signal, based on new column and/or row operation of the image/signal, and a new digital watermark system, based on the new encryption/decryption system. The column and row operation are introduced for creating a chaotic image/signal so that the resulting image/signal is unreadable/inaudible with a fast computational speed. The new digital watermark technology can sustain cropping damage for verification.

The invention discloses a method for realizing server hardware acceleration by using an FPGA (field programmable gate array). A specific realizing process of the method comprises the following steps: constructing a QPI (quick path interconnect) bus module, a hardware acceleration module, a high-speed buffer storage region and a message conversion module in the FPGA, wherein the massage conversion module is used for converting memory reading-writing operation launched by the hardware acceleration module into a series of QPI messages and sending the QPI messages to the QPI bus module, and sending reading-writing response returned by the QPI bus to the hardware acceleration module. Compared with the prior art, the method for realizing server hardware acceleration by using the FPGA disclosed by the invention can configure different acceleration algorithms for different computational scenes by virtue of the reconfigurability of the FPGA, is relatively high in flexibility and expansibility. The QPI bus is utilized to access a memory space of the system, so that higher bandwidth and smaller memory accessing delay, in comparison with those of a mainstream PCIe bus, are provided.

The invention discloses a whole bridge deck moving load spatial distribution monitoring system based on dynamic weighing and multi-video information fusion. A dynamic weighing system is arranged at the starting position of the bridge deck to obtain the vehicle weight information of the moving load, A plurality of cameras are arranged along the bridge to obtain video information of traffic flow covering the whole bridge deck, There is an overlap area in the field of view of two adjacent cameras, information collection and network communication system is arranged on site, and deploy the information processing and analysis master control system in the cloud, Combined with Kalman filter and visual field demarcation line method to track vehicle trajectory and position in visual field, Accordingto the time that the vehicle crosses the online slot of the piezoelectric sensor of the dynamic weighing system, the dynamic weighing and monitoring multi-video information are fused to realize the accurate and real-time identification of the magnitude and position of the moving load in the whole bridge deck. The invention has the advantages of fast calculation speed and high identification accuracy, and is suitable for monitoring the full coverage of various bridge decks or pavement moving vehicle loads in a designated area.

The invention discloses a video object identification method and a relevant system based on support vector machines; with structure training samples and according to resolution that is selected from the training samples, utilize a method combined with wavelet outline description symbol, shape factor and invariant torque, to describe outline characteristics of the training samples; gain a support vector machine model according to the outline characteristic training, and meanwhile, determine decision-making function parameters at the optimum category aspects in the support vector machine model; then, extract outline characteristics from the video object to be identified; the support vector machine model after training can follow the video object outline characteristics that is input, in order to perform category for the acquired video objects with a decision-making function operation for the optimum category face. The invention has advantages of high calculation speed, high identification accuracy, reliable arithmetic performance and multi-category identification; and moreover, with increase of objects to be identified, the identification performance can still be kept stable, and the identification speed can still meet real-time monitoring demands.

The invention provides a method for recovering phases from interferograms containing a phase-shift error. The method comprises the following steps of: testing a tested member by using a universal phase-shift interferometer; introducing a linear carrier frequency into the interferograms, and operating the interferometer for acquiring a group of phase-shift interferograms; rearranging data on the phase-shift interferograms to acquire a new image, and performing fast Fourier transform on the new image to acquire frequency spectrum of the new image; and filtering the frequency spectrum to obtain a phase spectrum and remove errors. After inverse Fourier transform is performed on the phase spectrum, an expanded recovery phase is obtained via arc tangent calculation and unwrapping operation; after the expanded phase is recovered to the original size, the tested phase can be obtained. The invention can remove the influences caused by the phase-shift error by using a few (for example four) phase-shift interferograms, and recover the exact tested phase so as to achieve the aim of improving the measurement precision of the phase-shift interferometer under non-ideal measurement environments and instrument conditions.

The invention discloses a method for obtaining a load density index based on cellular historical data. The method for obtaining the load density index based on the cellular historical data is characterized by comprising the following steps: a cellular is generated, the power supply area of a 10KV feeder line serves as class cellulars, and the class cellulars contain actual measurement data; the power supply area is divided according to square meshes of the same size to form the class cellulars, and a load is to be forecasted. An electric power geographic information system (GIS) is set up, historical loads, power supply areas and land information of the class cellulars are integrated in the GIS, the cooperation index of the load density is determined, the maximum value of the load density of the class cellulars serves as a benchmark, and the load densities of other similar cellulars are normalized. The classified load densities over the years are obtained, a relation equation between the cellular load and the classified load densities is set up, and the load density is obtained through the least square method. A spatial load is forecasted, the size of the spatial load in a target year is forecasted according to the obtained index of the classified load densities, and the load value of each class cellular is further worked out.

The invention provides a sleep staging method based on single-channel electroencephalogram signal ocular artifact removal, and relates to a sleep staging method of ocular artifact removal. The sleep staging method solves the problems that in a traditional method, reference electro-oculogram signals are lacked, a removal method is difficult, knowledge extraction and expression are difficult, astringency of the method can not be ensured sometimes, knowledge can not be directly learned, and sleeping information contained in electroencephalogram signals can not be fully mined. The method is achieved through the steps of firstly, obtaining M wavelet coefficients; secondly, using P wavelet coefficients containing no ocular artifact as pure electroencephalogram signals; thirdly, obtaining the number and the residual error sum of IMF components; fourthly, obtaining electroencephalogram components and electro-oculogram components; fifthly, reconstructing the pure electroencephalogram signals; sixthly, obtaining X(n); seventhly, extracting seven characteristic parameters; eighthly, obtaining the sleeping state staging index. The sleep staging method is applied to the field of sleep staging.

The invention discloses a method and a device for dynamically analyzing the big arch springing CRD stratified excavation footage of a cross-section tunnel. The method comprises the following steps: stratified excavation: building a three-dimensional numerical model to achieve the numerical simulation during the excavation process; obtaining the deformation and the safety indexes of surrounding rocks, and forming a data sample using the mechanical parameters and the footage as the input and the deformation and the safety of the surrounding rocks as the output; building a surrounding rock parameter identifying sample set and a footage determining sample set; building a surrounding rock parameter identifying neural network model and a footage determining neural network model; performing the dynamic classification on the surrounding rocks; obtaining the deformation of the surrounding rocks of the tunnel; obtaining the distribution range of the mechanical parameters of the surrounding rocks; obtaining the mechanical parameter of the surrounding rocks; determining the neural network model through the footage to obtain the excavation footage in next-stage construction. According to the method and the device, the blindness of artificially selecting footage due to the uncertainty and the variability of a geologic body is overcome, and the method and the device have great economic and social meanings.

The invention provides a navigation image matching filtering method based on K-means clustering algorithm, which comprises the following steps: 1. Obtaining an image of the motion process through the camera by the mobile terminal; 2. Extracting feature points for the image acquired by the camera; 3. Obtaining the matching point pairs by matching the extracted feature points of the image; 4. Using the K-means clustering algorithm to eliminate the mismatching point pairs to correct the measurement error of the mobile terminal to calibrate the coordinate position. Using the method, highly accurate matching point pairs can be obtained in a stable and real-time way, the accuracy of image matching and navigation route can be improved, and the accuracy of navigation can be finally improved. Compared with the existing navigation image matching filtering method, the proposed method has the characteristics of simplicity, high efficiency, timeliness and strong stability, which can improve the calculation speed of SLAM system and reduce the burden of SLAM system.

The invention discloses a fault-tolerant control method for a discrete integral sliding mode of a satellite control system. A discrete integral sliding mode controller is designed based on the discrete linear system mode of a satellite, the virtual control law of the controller obtains a health factor W of an actuator through fault diagnosis and parameter identification; adopting a direct distribution method based on the reachable set of a moment to obtain the control moment uk of each actuator according to the controlling quantity vk and the health factor W of the actuator; and arranging the surfaces of reachable sets according to the sequence of angles between a surface normal vector and a target vector from small to large through the direct distribution method based on the reachable set of the moment. According to the method, the satellite attitude control problems of coexisting inaccurate health factors, multiple faults and multiple uncertainties can be effectively processed on line.

The invention discloses a method for ordering microblog network node weights based on multi-link, which is used for solving the technical problem of low recall rate in existing methods for ordering microblog network node weights. The technical proposal is as follows: a microblog network is constructed as a network directed graph G = (E, V), and the scale of the network graph is then remarkably reduced by defining a user effective fan set Ef(u) to improve the calculation speed; secondly, a node message is tracked, the issuing, forwarding, replying and collecting of the node message and other information are recorded, the additional link relation of nodes is determined, and the content of specific messages is not analyzed in the section so as to enhance the network analysis speed; and finally, the interaction of network nodes is identified and processed in combination with network dynamics, thereby lowering overall system overhead and improving the accurate rate and recall rate of the calculation method.

The invention provides a method for tracking and solving a Thevenin equivalent parameter in a transient process of a power system. The method solves the system Thevenin equivalent parameter on an arbitrary load bus by a compensation method by using a network algebraic equation generated in each calculation step of a transient stability operation program. The method has good operability and applicability without any assumption premise, and has high precision of the Thevenin equivalent parameter which is obtained by calculation. The result of the method can be applied to any analysis and calculation of the power system which is required to form a Thevenin equivalent system.

The invention relates to a method for predicting the crude oil characteristic through near infrared spectrum. The method comprises: collecting different types of crude oil samples; determining the near infrared spectrums and the physical data; carrying out second order differentiation treatment on the near infrared spectrums, and then carrying out main component analysis; taking previous w scores and four physical data, carrying out standardization treatment, and then carrying out main component analysis; taking previous w+1 scores to establish a crude oil identification database; treating the near infrared spectrum of a crude oil sample to be tested, and carrying out the same identification analysis as the database establishing to obtain the identification variable of the crude oil sample to be tested; determining the crude oil sample mostly approaching the crude oil sample to be tested in the database through the identification variable; carrying out spectrum fitting on the crude oil sample to be tested through the spectrums of the crude oil samples, and determining the fitting property through the comparison of the fitting degree and the threshold value; and for the completely-fitting sample to be tested, predicting the physical data of the crude oil sample to be tested by using the physical data corresponding to the database spectrum participating the fitting.

The invention discloses a people stream trajectory tracking and area dwell time statistics method based on a heterogeneous network. The method comprises the following steps: deploying wireless access points and iBeaocn base stations, collecting and recording AP (Access Point) RSSI (Received Signal Strength Indicator) values collected by a plurality of sampling points and the coordinate values of the corresponding sampling points by a handheld mobile terminal, taking collected data as training data to determine a BP (Back Propagation) neural network model, integrating training results as an output value which is used as a function of a current mobile terminal coordinate value, obtaining a current position coordinate through an iBeacon and RSSI-distance relational expression, and obtaining a current position according to the distance; connecting the position coordinates to form a people stream trajectory tracking route graph; and meanwhile, recording the dwell time of a people stream at each point. The invention also provides a corresponding system. The invention combines the advantages of high calculation speed of wifi technology and high precision of iBeacon technology, and realizes people stream trajectory tracking and area dwell time statistics in a complex large building by combing with the multiuser support of a smartphone.

The invention discloses a land-based cloud chart classification method based on classification trees of a support vector machine. The land-based cloud chart classification method comprises the steps as follows: firstly, training samples are selected from land-based cloud charts; secondly, a Gabor filter bank is utilized to perform frequency domain decomposition on the training samples; thirdly, sorting histogram spectrum characteristic vectors and interested operator characteristic vectors of each filter image are extracted, so that training sample sets can be obtained; fourthly, K types of the training samples in the training sample sets are clustered to form ni types according to the specified clustering number, and then centers of the ni types are used as training samples of the ni types, so that new training sample sets can be obtained; fifthly, a classification tree model based on a sorter of the support vector machine is established; and sixthly, the samples in T are classified, and the land-based cloud charts can be classified. The land-based cloud chart classification method considers various characteristic values among different cloud genera based on the land-based cloud charts, combines an SVM (Support Vector Machine) learning algorithm with a classification tree algorithm so as to classify and recognize a plurality of types of the cloud charts automatically, and has the advantages of stronger robustness, higher classification speed and high classification accuracy rate.

The invention discloses a method for selecting an SAR (spaceborne synthetic aperture radar) scene matching area on the basis of an SVM (support vector machine), which is combined with SAR imaging characteristics, adopts nonlinear transformation to convert the partition problem of a sample characteristic space into the linear classification problem of a high dimensional characteristic space by selecting suitable multidimensional characteristic parameters which represent image information and utilizes linear combination of limited support vector points to establish a classification decision function and select the scene matching area. The method considers the relation between various characteristic values of a reference image and correct selection of the matching area. A test result shows that the method has high computing speed and higher adaptability and an anti-interference performance and can carry out correct decision guide on selection of a matching subarea of a complex SAR reference image.

The invention discloses a non-steady flow simulating method for a pipe network system. The invention provides the non-steady flow simulating method which solves a non-steady flow by combining an obvious format and a hidden format and is suitable for complex pipe network systems. The method is based on a chasing method, three methods of a basic solution, a local iteration solution and a layered solution are provided for meeting the arraying modes of different pipe network systems and the dividing features of obvious and hidden format pipelines, and the hidden pipe network matrix equitation is solved by adopting a simple method. The non-steady flow simulating method for the pipe network system is suitable for the pressure pipeline systems and pressure-free drainage systems in large-scale river network non-steady flows in the transition process of a hydropower station as well as the non-steady flow simulation of an obvious full mixed flow system, and the non-steady flow simulating precision can be improved.

The invention relates to a method for recognizing grid topology based on a measurement spanning tree, belonging to the technical field of electric power system dispatching automation. The method comprises the steps of: firstly, generating a bus-branch model of a network and a tree structure, and calculating voltages and phase angles of nodes by layers; calculating active and passive powers of two ends of the branches according to impedance parameters of the branches; checking the calculating values and the measurement values, if having larger deviation, adding a bad mark on a corresponding network element, sequencing suspicious degrees of the bus and the branches according to the quantity of the bad marks; speculating switch brakes with telecommands possibly having errors and lines with operation states possibly having errors from the suspicious bus and the suspicious branches; and determining whether the deflection of the switch brakes is reasonable or not through judging whether the quantity of the bad marks in the network after the corresponding switch brake deflects is reduced or not. The method is used for recognizing topological errors without state estimation results and convergence problems, and has the advantages of higher calculating speed and wide application range compared with the algorithm using state estimation.

The invention provides a method for monitoring a low-frequency oscillating source based on PMU data, and relates to safety operation of an electric system. The method comprises: using a phasor measurement unit PMU to obtain information of a bus outlet side of a generator of an electric power system power plant, the information specifically including active output power, reactive output power, voltage phase angles, voltage amplitude values, and power angles of the power plant outlet bus, and according to the obtained data, calculating oscillation energy of the power plant bus, and using a TLS-ESPRIT algorithm to identify the obtained data, extracting a dominant oscillation mode of a power plant generator side, and obtaining corresponding oscillation characteristic parameters. If an oscillation source is in the power plant, oscillation energy flows out of the power plant, an oscillation energy flow is a positive value, and conversely, the oscillation energy flow is a negative value. The method is advantaged in that the PMU can be directly used to obtain input signals and monitor the low-frequency oscillating source of the electric power system in real time, and the method is convenient and fast, and is fast in computation speed, and is good in practicability.

The invention relates to a seismic wave impedance inversion method based on frequency spectrum fusion. Background field factors are extracted from well logging data to control an overall trend of inversion wave impedance; the frequency spectrum fusion is performed on low-frequency components of the well logging data and effective frequency-band components of seismic data; and an in-well wave impedance curve is extended to an overall seismic cross section under the restriction of the seismic data. The frequency spectrum fusion is performed on the well logging data and the seismic data, the background field factors are introduced to control the overall trend of the inversion wave impedance and the in-well wave impedance curve is extended to the overall seismic cross section under the restriction of the seismic data. Basic characteristics (fault, occurrence) of seismic reflection are relatively completely retained without a general problem of multiplicity in solutions on the basis of a model inversion algorithm so that spatial variation in lithofacies and lithology can be obviously reflected, and thus the method has characteristics of being rapid in calculating speed, great in stability, high in calculating accuracy and high in anti-noise capacity.