48 results about "Sparse methods" patented technology

The invention discloses a video motion identification method based on a sparse time slicing network. The method includes steps: extracting information from each training video, and performing first training and optimization on the time slicing network; adding a sparse to the network after the first optimization, and performing second training and optimization; performing cutting and dimension adjustment on the network after the second optimization; performing third training and optimization on the network after dimension adjustment until the identification precision or the sparsity reaches theexpectation; and extracting information from a to-be-identified video, inputting the extracted information to the network after the third optimization, and performing output and fusion on the time slicing network to obtain a motion identification result. According to the method, the information of the longer video can be obtained through the time slicing network, and a double-flow convolutional network structure can fully utilize the video information and greatly improve the motion identification precision; and a structured sparse method can enable the weight of a convolution layer to be sparse in groups, a model is further simplified by network cutting, and the storage space is reduced.

The invention provides a monocular infrared video three-dimensional reconstruction method based on a visual odometer. Firstly, a thermal infrared imager is calibrated; then, a direct method and sparse method visual odometer model is constructed; then, frames are managed, a key frame is generated from a continuous infrared image sequence to be processed, and the key frame is marginalized; point management is conducted on the pixel on the key frame; finally, sliding window optimization is conducted on the key frame, a photometric error of the direct method and sparse method visual odometer model is minimized, the reverse depths of thermal infrared imager pose, internal references and spatial points are solved in an iterative algorithm by a gauss-newton method, and finally, three-dimensional point cloud of a scene is obtained. According to the monocular infrared video three-dimensional reconstruction method based on the visual odometer, the direct method is applied to photometric error minimization, traditional feature point detection and matching are skipped, through direction operation on a grey value of the pixel, all variables which the photometric error to be optimized depend on is calculated directly, and therefore three-dimensional reconstruction of a night vision scene is achieved, the real-time capability of the three-dimensional reconstruction is ensured, and the spaciousness of the scene is enhanced.

The invention discloses an array sparse method for a broadband non-frequency-variable multi-beam imaging sonar. With the Bessel function, fitting of influences on array guiding vectors by different frequency points in the broadband signal bandwidth is performed and a broadband signal multi-beam forming model under the far-field situation is established; on the premise that the formed multiple beams approximate a reference beam, a minimum number of effective array elements are searched and multiple sets of weighting coefficients are calculated; a highly nonlinear sparse array optimization problem is transformed into a sparse signal reconstruction problem in the compressed sensing theory, a reconstruction weighting coefficient is calculated iteratively by an underdetermined system localizedsolution algorithm, and a sparse array structure is determined; a convex optimization theory is introduced so as to form a plurality of low-side-lobe beams and a multi-beam array sparse side-lobe suppression model for array element excitation is established. According to the invention, the main lobes of a plurality of formed beams are not extended with changes of signal operating frequencies; andpeak side-lobe levels of multiple beams formed by the sparse array are reduced effectively.

The invention discloses a side lobe suppression method and an array sparse method for a multi-beam imaging sonar sparse array. A sparse optimization problem of an array antenna is transformed into a linear regression problem of a sparse matrix, combination learning is carried out by taking the reconstruction of multiple beam direction patterns with different pointing directions as a target task, and a sparse semicircle array model for multi-task learning is established; based on the performance requirement of a preset main side lobe, a norm regular term of 1<1 / 2> of a weighted coefficient matrix is introduced on the basis of a least squares loss function, an iterative threshold converged method and an accelerating gradient descent method are used for solving an optimal weighting coefficient, and a weighting coefficient which minimizes a side lobe peak level is solved at the same time while optimizing the position of the sparse array. According to the side lobe suppression method and the array sparse method for the multi-beam imaging sonar sparse array, the problem that the sparse solution falls into the local optimum due to the mismatching of array position and weight vector is avoided, and peak side lobe levels of multiple beams formed by the array after sparseness is effectively reduced.

The invention provides a planar antenna array sparse method based on a quantum spider population evolution mechanism. The planar antenna array sparse method comprises the steps of 1, establishing a planar antenna array sparse model; 2, setting system parameters; 3, performing evaluation on advantages and disadvantages of each spider coding position in a population by a fitness function, and taking the optimal position of the fitness function as the global optimal position of the whole population; 4, dividing genders of spiders in the population; 5, calculating weight of each spider; 6, updating quantum positions of female spiders by adopting an analog quantum vector rotation door rotation based on the updated quantum vector rotary angle; 7, updating quantum positions of male spiders by adopting an analog quantum vector rotation door rotation based on the updated quantum vector rotary angle; 8, updating the respective historical optimal positions; and 9, judging whether the maximum number of iterations is reached or not. By adoption of the planar antenna array sparse method, the difficulty existing in multi-constraint planar array antenna sparsity is solved, and various requirements on the planar sparse array are satisfied.

The invention discloses a knowledge assisted-based sparsity recovery STAP color loading method. The steps include: establishing a sample data model; calculating a priori space-time steering vector matrix; calculating a sparsity recovery vector; calculating sample clutter information; calculating a sample covariance matrix and a prior clutter covariance matrix; and calculating a STAP color loadingmatrix and performing filtering. The solution of the invention combines color loading and a sparsity method, that is, the sample covariance matrix of the color loading is a covariance matrix obtainedfrom a sparsity sample after sparsity processing is performed on a sample. In a process of sparsity recovery processing of the sample, an algorithm to suppress dense interference is performed. The sample sparsity processing is performed in a solving process of the sample covariance matrix of the color loading. A knowledge assisted-based method used to suppress the dense interference, and a minimumthreshold method for determining a clutter element solve a problem of moving target cancellation, and the algorithm has better robustness.

The invention discloses a neural network column sparse method based on weight saliency. When the neural network model carries out feedforward operation, the four-dimensional weight tensor can be expanded into a two-dimensional matrix in a tensor expansion mode, and therefore convolution operation is converted into matrix multiplication. Therefore, on the basis of a tensor expansion operation mode,the invention discloses a method for carrying out column sparsity on a weight matrix, namely deleting columns of the weight matrix in a neural network parameter layer to obtain a sparse model, and the dimension of the operation matrix is reduced at the moment, thereby reducing the model scale of the neural network and accelerating the operation of the neural network. Network re-training is performed on the remaining weight parameters to callback the accuracy, and re-training is stopped when the accuracy of the model is not increased any more to obtain a final model. According to the method, the deep learning model can be deployed on mobile and embedded equipment, a certain actual acceleration effect is obtained, and the application of an intelligent algorithm on a mobile terminal is promoted.

The invention provides an annular antenna array sparse method based on a quantum chicken evolution mechanism. The method comprises the following steps that: 1: establishing an annular antenna array sparse model; 2: setting an initial parameter; 3: designing a fitness function; 4: calculating the fitness value of each chick in a population, distinguishing the category of the chicken, and dividing sub-populations; 5, 6, and 7: independently constructing the quantum vector rotation angle update formula of roosters, hens and chicken, updating the quantum vector rotation angle, and updating a quantum position; 8: through a measurement way, converting into a [0,1] coding position, calculating the fitness value of the [0,1] coding position, and updating the individual historical optimal solutionand the global optimal solution of each chick; and 9: judging whether a maximum iteration is achieved or not. The method is higher in rate of convergence and higher in accuracy of convergence, and hasa good spare effect on solving the problem of annular antenna array sparse construction, the complexity and the cost of antenna array system are greatly lowered, and an expectant requirement is achieved.

The invention discloses a neural network structured sparse method based on incremental regularization. The method comprise the steps of when the branches of a neural network are pruned, according to the relative importance of each weight group, distributing different regularization increments to different weight groups step by step, then updating the regularization factors of the weight groups iteratively and continuously, and when the regularization factor of a certain weight group reaches a specified regularization upper limit, deleting the corresponding weight in the network permanently toincrease the structured sparsity of the network model; and when the sparsity of a certain layer reaches a preset sparsity rate, automatically stopping pruning of the layer until the pruning of all thelayers is completed; and finally, retraining the whole network to callback the accuracy, and when the accuracy of the model does not rise any more, stopping retraining to obtain a sparse model. According to the method, a large deep learning model can be deployed on the mobile and embedded equipment, a remarkable actual acceleration effect is obtained, and the application of a deep learning algorithm on a mobile terminal is promoted.

The invention discloses a method for reducing a frequency aliasing effect of undersampled magnetic resonance imaging. The method comprises the following steps of (1) obtaining space K through a nuclear magnetic resonance spectrometer and performing undersampling on the original data of the space K by using a random oscillometric method to obtain undersampling data; (2) forming an over-complete dictionary by selecting a sparse method; and (3) performing recovery reestablishment on the undersampled data in the step (1) by using a recovery algorithm according to the over-complete dictionary to obtain original data, performing Fourier transform to obtain images and performing real-time imaging. The random oscillometric method comprises a variable-density oscillating spiral track and a variable-density oscillating radiation track.

This invention discloses one dialogue control and sparse method based on flexible exchange in the telephone network, which comprises the following steps: making statistics for router link and aim number set, if the volume achieves the set length, then combing the calls according to the set router and pattern to change call directions and to comb set router to achieve dialogue control and combing without human interface.

The invention discloses a mechanical fault sparse representation method based on a wolf pack parameterization joint dictionary, and belongs to the technical field of mechanical fault diagnosis. The invention provides a grey wolf optimization sparse method based on a joint dictionary in combination with a sparse representation principle. An optimization algorithm is fused into orthogonal matching pursuit, a joint dictionary atom most matched with a fault is selected through inner product operation, the optimal atom is used for reconstructing a fault signal, and then envelope analysis is performed on the reconstructed signal, so that extraction of transient characteristic components in the signal is realized, fault information is effectively represented, and the fault type is judged more accurately. The method is suitable for rolling bearing fault diagnosis.

The invention discloses a main speed reducer multi-fault intelligent diagnosis method based on multi-channel data deep mining, and the method comprises the steps: obtaining a vibration signal of a main speed reducer through a multi-channel sensor, and carrying out the noise reduction of the vibration signal through the combination of a wavelet contraction noise reduction method and a structured sparse method; based on the vibration signal after noise reduction processing, adopting a deep belief network to perform multi-channel deep feature extraction, and fusing multi-channel deep features; and based on a deep feature fusion result, performing online state monitoring and multi-fault intelligent diagnosis on the main speed reducer by adopting a sparse Bayesian extreme learning machine. According to the invention, single-fault and multi-fault modes can be identified at the same time, and quantitative analysis of state monitoring and intelligent fault diagnosis of the main speed reducer is realized.

The invention provides a reverse operation sparse method of a neural network and a computing chip. The method is used for executing sparse processing in neural network operation and then performing reverse operation. The technical scheme provided by the invention has the advantages of small calculation amount and low power consumption.

The invention relates to an ultrahigh-voltage power transmission line point cloud data semantic segmentation method based on deep learning, which belongs to the field of ultrahigh-voltage power transmission line inspection, and specifically comprises the following steps: for actual ultrahigh-voltage power transmission line point cloud data, firstly establishing a deep learning training data set by using a scene division method based on a safety buffer distance; secondly, realizing feature acquisition in a deep learning network model by using a two-step sparse method based on a combination coefficient and a feature abstraction method based on importance of sparse data and local position related information; training the network model to obtain accurate network parameters; and finally, inputting the test sample set into the network to obtain a category label of each point, thereby realizing semantic segmentation of the point cloud data. According to the method, the problems of lack of data sets, low calculation efficiency and low calculation precision in deep learning semantic segmentation of the point cloud data of the power transmission line at present are effectively solved.

The invention relates to a zero attraction penalty and attraction compensation combined sparse LMS method, and belongs to the field of signal processing. According to the method, zero attraction penalty and attraction compensation are combined, coefficients of an estimation filter are divided into a near-zero coefficient, a small coefficient and a large coefficient, and then different attraction methods are adopted; in each iterative update, for estimating a near-zero coefficient of the filter, only a product term in an iterative update formula is used for calculation; then trace attraction compensation is carried out on the large coefficient of the estimation filter, so that the convergence speed of the coefficient of the estimation filter to approach the large coefficient of the channel is accelerated; for the small coefficient of the estimation filter, if the coefficient approaches the zero coefficient value of the channel or the large coefficient value of the channel in the iteration process, processing is carried out according to the method for estimating the near zero coefficient and the large coefficient of the filter, otherwise, simple zero attraction punishment is carried out on the coefficient. The method is high in convergence speed, low in complexity and wide in tuning parameter application range.

The invention relates to a sparse LMS method combining zero attraction penalty and attraction compensation, belonging to the field of signal processing. The method combines zero attraction penalty and attraction compensation, divides the coefficients of the estimated filter into near zero coefficients, small coefficients and large coefficients, and then adopts different attraction methods. In each iterative update, for the near-zero coefficients of the estimated filter, only the product term in the iterative update formula is used to calculate; for the large coefficients of the estimated filter, a slight attraction compensation is performed to speed up the estimated filtering The coefficient of the filter is used to approximate the convergence speed of the large coefficient of the channel; for the small coefficient of the estimated filter, if the coefficient approximates the zero coefficient value of the channel or the large coefficient value of the channel during the iteration process, then the estimation filter is approximated as described above. method with zero and large coefficients, otherwise, a simple zero-attraction penalty is applied to the coefficient. The method has fast convergence speed, low complexity and wide range of tuning parameters.

The invention provides a neural network sparse method and a computing chip. The method is used for executing sparse processing in neural network operation and then performing operation. The technicalscheme provided by the invention has the advantages of small calculation amount and low power consumption.

The invention discloses a mixed granularity-based joint sparse method for neural networks. The joint sparse method includes independent vector-level fine-grained sparseness and block-level coarse-grained sparseness. The bitwise logical AND operation is performed on the branch mask to obtain the final pruning mask, and then obtain the weight matrix of the sparse neural network. The joint sparsity of the present invention always achieves an inference speed between block-sparse and balanced-sparse modes, regardless of the vector row size for vector-level fine-grained sparsification and the vector block size for block-level coarse-grained sparsification. It is used for the pruning of the convolutional layer and the fully connected layer of the neural network. It has the advantages of variable sparse granularity, general hardware inference acceleration, and high model inference accuracy.

The invention discloses a mechanical fault sparse representation method based on wolf group parameterized joint dictionary, which belongs to the technical field of mechanical fault diagnosis. The present invention combines the principle of sparse representation to propose a gray wolf optimized sparse method based on the joint dictionary, integrates the optimization algorithm into the orthogonal matching and tracking, selects the joint dictionary atom that best matches the fault through the inner product operation, and uses the optimal atom to process the fault signal Reconstruction, and then perform envelope analysis on the reconstructed signal, so as to realize the extraction of transient characteristic components in the signal, effectively characterize the fault information, and judge the fault type more accurately. The invention is suitable for fault diagnosis of rolling bearings.

The invention discloses a method for reducing a frequency aliasing effect of undersampled magnetic resonance imaging. The method comprises the following steps of (1) obtaining space K through a nuclear magnetic resonance spectrometer and performing undersampling on the original data of the space K by using a random oscillometric method to obtain undersampling data; (2) forming an over-complete dictionary by selecting a sparse method; and (3) performing recovery reestablishment on the undersampled data in the step (1) by using a recovery algorithm according to the over-complete dictionary to obtain original data, performing Fourier transform to obtain images and performing real-time imaging. The random oscillometric method comprises a variable-density oscillating spiral track and a variable-density oscillating radiation track.

The invention discloses a remote sensing image sparseness estimation method based on mixing transformation, which belongs to the technical field of remote sensing image processing, and solves the problem that image detail information is lost and a good sparse effect of a remote sensing image with rich details is difficultly obtained as the majority of image energy is mainly retained in an existing sparseness estimation method. The method combines the advantages of smooth image presentation based on tensor product wavelet transform and the characteristic of effective expression of detail information such as texture and edge of Tetrolet transform, has no limitation on image characteristics, and has certain universality. An experimental result shows that in comparison with a simple remote sensing image sparseness estimation method, the method based on the mixing transformation can be used for effectively performing sparse representation on the remote sensing image. The method is specially suitable for sparseness treatment on remote sensing images.

The invention discloses an image recognition method and system based on a lightweight convolutional neural network, comprising: loading a pre-trained deep convolutional neural network model for image recognition; using a kernel-based sparse method to calculate the model The cropping factor of the middle convolutional layer, the convolutional layer is cropped, and then the cropping factor of each convolution kernel in the uncropped convolutional layer is calculated, and the convolution kernel is cropped; for the convolutional neural network after the cropping is completed model, the standard convolution method is replaced by the convolutional and separable group convolution method, and the weight coefficient matrix of the convolution kernel is quantized and encoded to obtain a lightweight convolutional neural network model; the image dataset is used to quantify the lightweight model. For training, input the image to be recognized into the trained lightweight convolutional neural network model for image recognition. The light-weight image recognition model disclosed by the invention can be loaded on a terminal with limited computing power and storage resources, and has a relatively broad application prospect.

The invention discloses a mixed granularity-based combined sparse method for a neural network. The method comprises independent vector magnitude fine granularity sparsification and block level coarsegranularity sparsification. According to the method, bitwise logic AND operation is performed on a pruning mask which is independently generated through the two sparsification modes, so that a final pruning mask can be obtained, and a weight matrix of the sparsificated neural network is obtained. According to the method, the reasoning speed between the block sparsification mode and balance sparsification mode is always obtained through joint sparsity, and the vector line size of vector magnitude fine-grained sparsification and the vector block size of the block level coarse-grained sparsification do not need to be considered. The method is used for pruning a convolutional layer and a full connection layer of the neural network, and has the advantages of variable sparse granularity, accelerated general hardware reasoning and high model reasoning precision.

The invention provides an annular antenna array sparse method based on a quantum chicken evolution mechanism. The method comprises the following steps that: 1: establishing an annular antenna array sparse model; 2: setting an initial parameter; 3: designing a fitness function; 4: calculating the fitness value of each chick in a population, distinguishing the category of the chicken, and dividing sub-populations; 5, 6, and 7: independently constructing the quantum vector rotation angle update formula of roosters, hens and chicken, updating the quantum vector rotation angle, and updating a quantum position; 8: through a measurement way, converting into a [0,1] coding position, calculating the fitness value of the [0,1] coding position, and updating the individual historical optimal solutionand the global optimal solution of each chick; and 9: judging whether a maximum iteration is achieved or not. The method is higher in rate of convergence and higher in accuracy of convergence, and hasa good spare effect on solving the problem of annular antenna array sparse construction, the complexity and the cost of antenna array system are greatly lowered, and an expectant requirement is achieved.

The invention discloses a sparse technology based on an improved adjacency matrix. Aiming at that an adjacency matrix of a storage network topological structure has the characteristic of high sparsity, pattern of manifestation of the adjacency matrix is improved, and the improved adjacency matrix is applied to node optimal numbering, in-advance determination of retrieving information and formation of an admittance matrix. In a LU decomposition process, in order to realize nonzero retrieval of line direction, storage information of the line direction is increased, and corresponding retrieval modes are customized. According to correlation property of newly added branches and factoring nonzero injection elements in the optimal numbering process, while executing optimal numbering, positions of the newly added elements are recorded and a storage framework is formed. The sparse technology based on the improved adjacency matrix is suitable for being used in calculation process of an electric power system, and can effectively increase efficiency of related calculation through improving the retrieval modes and the storage framework.

The invention relates to the technical field of industrial data acquisition visualization, in particular to a high-frequency time series data real-time sparse display method based on the number of pixels. The method comprises the following steps: when an oscillogram of a time series data point is displayed on a computer graphical interface, a point tracing display method is adopted, points in an actual coordinate system are converted into pixel coordinate system points for point tracing, the time sequence is horizontal coordinates, the amplitude is vertical coordinates, the time sequence is converted into horizontal coordinate pixels, the amplitude is converted into vertical coordinate pixels, and then the points are connected through folding lines. Under the condition of high-frequency data acquisition, data can be acquired; the data point density is very large, if a signal waveform curve is displayed in real time without distortion, a large amount of computer performance and networkperformance can be consumed, the data sparse method based on the number of pixel points is provided, and the signal waveform curve can be displayed in real time without distortion under the conditionthat the computer hardware performance is not improved.

The invention discloses a method for predicting the remaining life of an IGBT. By means of the phase space frame reconstruction technology, on the basis of reconstructing the phase space by differential entropy rate, the reconstructed phase space is arranged with input signal vectors of Volterra series; Considering the correlation between the input data and the target output, the optimal selection of the input data of each frame is carried out. The present invention adopts the relatively mature forward-backward algorithm and the minimum angle regression algorithm to select the better input data in the input vector to As the input of the model; on the basis of the original ELM model, add multi-response sparse regression algorithm and one-by-one extraction method to cut out useless or little hidden layer nodes, and use three mixed neuron activation functions, so that The established network is more robust and generalizable; the present invention fully considers the difference between different input pairs of prediction models, and designs an adaptive algorithm to dynamically update the prediction model of each group of input data, which greatly improves the Improved prediction accuracy.

The invention discloses a knowledge-assisted sparse restoration STAP color loading method. The steps include: establishing a sample data model; calculating a priori space-time steering vector matrix; calculating a sparse restoration vector; calculating sample clutter information; and calculating a sample covariance matrix and the prior clutter covariance matrix; calculate the STAP color loading matrix and perform filtering. The scheme of the present invention combines the color loading and the sparse method, that is, the sample covariance matrix of the color loading is to obtain the covariance matrix of the sparse sample after the sample is sparsely processed; Algorithm for suppressing dense interference. In the process of solving the color loading sample covariance matrix, the sample sparse processing is carried out; the knowledge-based method for suppressing dense interference, and the minimum threshold value method for judging clutter elements solve the problem of moving target cancellation. good robustness.

The invention discloses a side lobe suppression method and an array sparse method for a multi-beam imaging sonar sparse array. A sparse optimization problem of an array antenna is transformed into a linear regression problem of a sparse matrix, combination learning is carried out by taking the reconstruction of multiple beam direction patterns with different pointing directions as a target task, and a sparse semicircle array model for multi-task learning is established; based on the performance requirement of a preset main side lobe, a norm regular term of 1<1 / 2> of a weighted coefficient matrix is introduced on the basis of a least squares loss function, an iterative threshold converged method and an accelerating gradient descent method are used for solving an optimal weighting coefficient, and a weighting coefficient which minimizes a side lobe peak level is solved at the same time while optimizing the position of the sparse array. According to the side lobe suppression method and the array sparse method for the multi-beam imaging sonar sparse array, the problem that the sparse solution falls into the local optimum due to the mismatching of array position and weight vector is avoided, and peak side lobe levels of multiple beams formed by the array after sparseness is effectively reduced.