Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

51results about How to "Improve sparsity" patented technology

Mechanical fault diagnosis method and system based on spiking neural network

The invention relates to the technical field of mechanical fault diagnosis, in particular to a mechanical fault diagnosis method and system based on a pulse neural network. The method comprises the following steps: constructing a fault diagnosis network, wherein the fault diagnosis network comprises an improved gating attention coding module and a pulse residual network; the method comprises the following steps: replacing a common convolution layer of a gating attention coding module with a one-dimensional sparse convolution layer, and replacing a two-dimensional batch normalization layer with a one-dimensional batch normalization layer to obtain an improved gating attention coding module; setting a pulse neuron in the fault diagnosis network as a PSN neuron, and embedding a time step shrinkage layer in the pulse residual network; and inputting the mechanical vibration signal of the current sampling period into a fault diagnosis network, and outputting a predicted fault category label of the current sampling period. According to the invention, high-efficiency and high-precision mechanical fault intelligent diagnosis is realized.
Owner:SUZHOU UNIV

Advanced control system of direct-current submerged arc furnace

The invention provides an advanced control system for a direct-current submerged arc furnace. The advanced control system comprises a sensor unit, a data acquisition unit, a central processing unit, a man-machine interaction unit, a model prediction control unit, a numerical control output unit and an execution mechanism unit, the central processing unit sends direct current submerged arc furnace production process data to the model prediction control unit for model prediction control data calculation, and then the model prediction control unit returns calculation result information to the central processing unit; the central processing unit processes the received calculation result information and adjusts a production process control strategy, and a control signal is transmitted to the execution mechanism unit through the numerical control output unit; the method can achieve the soft measurement of the insertion depth of the positive and negative electrodes, achieves the automatic adjustment of the electrodes of the direct-current submerged arc furnace through a generalized prediction control algorithm, stabilizes the production, improves the economic benefits, and improves the overall intelligent level of the direct-current submerged arc furnace.
Owner:DALIAN HEAVY MECHANICAL & ELECTRICAL EQUIP ENG CO +1

Interdisciplinary knowledge graph construction system and method

The invention relates to the technical field of information retrieval, in particular to an interdisciplinary knowledge graph construction system and method, and the system comprises a relation matrix construction module which analyzes a node relation based on nodes in a knowledge graph, carries out the statistics according to an association frequency, selects interdisciplinary nodes to construct an association matrix, calculates a node fitting degree, and determines an association node set; and generating an interdisciplinary incidence relation matrix. According to the method, through correlation frequency statistics and fitting degree calculation of interdisciplinary nodes, effective construction of comprehensive correlation between the nodes, decomposition of the feature matrix and elimination of non-key feature items, the sparsity of the matrix is improved, data are more concise and clear, and through screening of low-weight elements, reservation of important node relation and further optimization of matrix feature expression, the method has the advantages of being high in robustness and high in reliability. In the coupling analysis and partitioning process of the nodes, redundant connection of the low-coupling-degree nodes is reduced, the core relation is highlighted, the node structure is recombined, and the accuracy and compactness of the multidisciplinary knowledge graph are remarkably improved.
Owner:CHENGDU POLYTECHNIC

Environmental DNA data dimension reduction method and system based on hierarchical auto-encoder

The invention provides an environmental DNA data dimension reduction method based on a layered auto-encoder, and belongs to the field of bioinformatics and the technical field of data processing. The method comprises the following steps: S1, data preprocessing: dividing environmental DNA data into environmental DNA abundance data and environmental DNA sequence data; s2, denoising the abundance data of the environmental DNA; s3, performing length equalization and translation on the environmental DNA sequence data; s4, representing the sequence information of the sample; s5, compressing the environmental DNA sequence data; s6, performing dimension reduction by using a differential auto-encoder VAE; the denoised environmental DNA abundance data obtained in the step S2 and the compressed and encoded environmental DNA sequence data obtained in the step S5 are jointly used as input of a differential auto-encoder VAE, and the dimension of the sample is further reduced to a two-dimensional potential space; and S7, drawing a visual result graph of the two-dimensional space. The information of environmental DNA data is better reserved, and more accurate dimensionality reduction and visualization results are obtained.
Owner:DALIAN MARITIME UNIVERSITY

Method for accelerating chemical exchange saturation transfer contrast imaging

PendingCN119001566Aachieve accelerationReduced imaging timeInternal combustion piston enginesSensorsk-spaceComputational physics
The invention discloses a method for accelerating chemical exchange saturation transfer contrast imaging, which relates to the field of magnetic resonance imaging, and comprises the following steps of: acquiring k space data with different frequency offsets by adopting a non-Cartesian sequence, inputting the k space data with different frequency offsets into a deep learning algorithm, iterating to obtain a CEST image reconstruction model, and obtaining a CEST image according to the reconstruction model. According to the method, multi-dimensional sparse sampling can be realized based on the improved non-Cartesian acquisition sequence, so that high-multiple acceleration is realized, and the scanning time is shortened; the deep learning algorithm can realize high-quality reconstruction of high-power under-sampling data of specific scanning under the condition of no full-sampling data.
Owner:SHANGHAI JIAOTONG UNIV

Signal transmission method, system and equipment based on generalized chirp division multiplexing and medium

The invention discloses a signal transmission method, system and device based on generalized chirp division multiplexing and a medium, and the method comprises the steps: employing a specific pulse forming window for each chirp subcarrier at a transmitting end, and employing a matching filtering window for each chirp matching subcarrier at a receiving end; fractional time delay and fractional Doppler effects introduced by a double-dispersion channel in a communication system, namely diffusion of received symbols, are suppressed, sparsity of an equivalent channel of the system is improved, and interference between symbols received by a communication receiving end is greatly reduced. The diffusion degree of a receiving pilot symbol for channel estimation is slowed down, so that the channel estimation is more accurate, the number of protection symbols required by a sending end is reduced, and the reachable capacity of a communication system is improved; compared with the prior art, an equivalent channel is more sparse, interference between a pilot symbol and a data symbol of a receiving end is reduced, so that pilot-data separability of the system is higher, signal detection complexity of the communication system is lower, and the detection effect is better.
Owner:SUN YAT SEN UNIV

Bearing compound fault sparse classification method and system based on adaptive feature selection

The invention provides a bearing compound fault sparse classification method and system based on adaptive feature selection, and the method comprises the steps: firstly, enhancing sample features through intra-class and inter-class distance measurement, and removing a redundant feature set to achieve the adaptive fault feature screening, and effectively improving the fault recognition performance; constructing a single-class fault initialization dictionary by using the feature training set, and enhancing sparsity and keeping model convexity through a norm constraint term; and iteratively training the over-complete dictionary by using the corresponding sample set of each fault category, and finally realizing the discriminant classification of the bearing compound fault through a discriminant vector. Compared with a traditional method in simulation and test, the method can effectively solve the feature adaptive selection problem in the LC-KSVD algorithm, improves the accuracy and robustness of fault classification under the small dictionary condition and the strong noise condition, reduces the time cost, and provides valuable technical reference for engineering application.
Owner:JIANGSU UNIV

Multi-view learning method and device based on low-rank constraint and hypergraph learning, and medium

The invention discloses a multi-view learning method and device based on low-rank constraint and hypergraph learning and a medium, and relates to the technical field of multi-view clustering. The method comprises the following steps: performing depth non-negative matrix factorization on a data matrix of multiple views to obtain a coefficient matrix; constructing a reconstruction error of depth non-negative matrix factorization through a norm; performing low-rank constraint on the coefficient matrix to obtain a low-rank constraint term; performing hypergraph structure learning on the coefficient matrix to obtain a hypergraph regular term; establishing a multi-view learning objective function based on the reconstruction error, the low-rank constraint term and the hypergraph regular term; and solving the objective function to obtain a learning result of the multiple views. Low-rank constraint is used for a coefficient matrix, sparsity of the coefficient matrix is enhanced, redundant information of the coefficient matrix is removed, a hypergraph structure is learned while the coefficient matrix is constructed, multivariate relations between data points are learned, manifold structure information of a source space is reserved, expression of the coefficient matrix on data deep information is enhanced, and then accuracy of a clustering result is improved.
Owner:SOUTHWEST UNIV

Sparse Bayesian remote sensing image reconstruction method and system based on Laplace level prior and GAMP

The invention discloses a sparse Bayesian remote sensing image reconstruction method and system based on Laplace level prior and GAMP, and the method comprises the following steps: S1, selecting a remote sensing image data set, setting image pixels, converting a remote sensing image into an amplitude diagram, and carrying out the sparse processing of the amplitude diagram; s2, establishing a sparse Bayesian model; s3, calculating a likelihood function, Laplacian hierarchical prior distribution of sparse signals and a marginal likelihood function; s4, performing Bayesian inference according to a maximum likelihood method, and calculating posterior distribution of sparse signals; s5, obtaining a mean value and a variance of a sparse signal and an updating formula of a hyper-parameter through an expectation maximization algorithm; s6, introducing a GAMP algorithm to update the mean value and the variance; s7, adding a damping factor to the GAMP structure; s8, judging whether an iteration termination condition is met or not, if so, outputting posteriori estimation of the sparse signal, and otherwise, executing S5; and S9, performing inverse wavelet transform on the output sparse signal to obtain a reconstructed image. The method is low in reconstruction error and high in reconstruction precision and efficiency.
Owner:ZHEJIANG SCI-TECH UNIV

A UAV visual relocalization method based on object semantics

The present invention provides a method for visual relocation of unmanned aerial vehicles based on object semantics, including: constructing a visual relocation model of unmanned aerial vehicles: an image processing and representation module, a scene matching module and a relocation module. The current scene is photographed by a camera of the unmanned aerial vehicle, and the semantic information of the object contained in the picture is obtained by using the YOLOv3 target detection network in the image processing module, and a topological map is constructed using the semantic information as a sparse description of the environment; in the case of prior knowledge of the map, an accompanying map of the picture to be matched is constructed, and a random walk algorithm is used to match the semantic features and the scene; the EPnP algorithm is used to solve the position and posture of the unmanned aerial vehicle to complete the relocation. The present invention can realize real-time relocation of unmanned aerial vehicles with strong robustness when the scene lighting conditions change dynamically, and is particularly suitable for automation tasks such as industrial inspections.
Owner:ZHEJIANG JIANDE GENERAL AVIATION RES INST +1

Brittleness parameter direct inversion method and system based on reweighting

The invention relates to a brittleness parameter direct inversion method and system based on reweighting, and belongs to the technical field of oil-gas exploration seismic inversion. The method comprises the following steps: performing angle superposition on pre-stack seismic data; establishing a forward modeling model based on the initial model, the difference matrix and the wavelet kernel matrix; on the basis of the forward modeling model, constructing a brittleness parameter inversion objective function based on reweighting; and inverting the objective function based on the seismic data obtained by angle superposition and the brittleness parameter based on reweighting to obtain an inversion result. According to the method, the accumulative error is reduced by adopting direct inversion, and the accumulative error is continuously increased by a conventional method for converting the brittleness index through pre-stack inversion, so that the prediction of the brittleness index is not accurate. According to the brittleness parameter direct inversion method, the problem can be well solved, the brittleness index is represented through direct inversion of E < rho >, accumulated errors are reduced to a great extent, and the brittleness index prediction precision is improved.
Owner:PETROCHINA CO LTD

Training method, recommendation method, device and electronic device for click rate prediction model

The present invention provides a training method, a recommendation method, a device, an electronic device and a storage medium for a click rate prediction model; the training method for the click rate prediction model includes: obtaining sample features and the click results of the sample features corresponding to the user; initializing the click rate prediction model according to the set weight parameters; processing the sample features through the click rate prediction model to obtain the predicted click rate; constructing an objective function according to the error between the click result and the predicted click rate, and a zero-norm regularization term; back-propagating the error in the click rate prediction model through the objective function, and updating the weight parameters of the click rate prediction model during the propagation process. Through the present invention, the sparsity of the weight parameters can be improved, the file size of the generated click rate prediction model can be reduced, and the accuracy of click rate prediction can be improved.
Owner:TENCENT TECHNOLOGY (SHENZHEN) CO LTD

Rolling bearing fault method and system based on Riesz atlas sparse decomposition

The invention belongs to the technical field of time-frequency analysis, and particularly relates to a rolling bearing fault method and system based on Riesz atlas sparse decomposition, which utilizes a new time-frequency analysis method-Riesz four-parameter spectrum time-frequency analysis method to obtain four-parameter information of amplitude, frequency, phase and direction of a vibration signal in a time-frequency domain. The time-frequency aggregation and the anti-noise performance of an analysis result are improved; in order to screen out an optimal parameter spectrum and expand the symbol dynamics entropy to a two-dimensional scale, a new entropy calculation method, namely cosine symbol dynamics entropy, is provided; and reconstructing components of the parameter spectrum obtained by entropy screening, and constructing a sparse filter parameter optimization component amplitude, so that a decomposition result has physical significance. The bearing vibration signal under the variable speed working condition and the bearing vibration signal under the constant speed are analyzed, the RSSD method is provided on the basis, and feature extraction and diagnosis of rolling bearing faults under the constant rotating speed working condition and the variable rotating speed working condition are achieved.
Owner:HUNAN UNIV OF SCI & TECH

Machine learning algorithm for screening of metal elements in diatomic catalysts throughout the whole cycle based on product yield prediction and application thereof

PendingCN122266546ARealize screeningEffectively distinguish the effects of catalytic performanceChemical property predictionEnsemble learningPtru catalystAlgorithm
The application discloses a machine learning algorithm for screening of metal elements in a diatomic catalyst full cycle based on product yield prediction and application thereof, and the algorithm comprises the following steps: (1) collecting attribute features of metal elements in the diatomic catalyst as a feature space 1; (2) preliminarily screening the attribute features according to comprehensive scores of feature importance to obtain a feature space 2; (3) performing feature operation processing on the feature space 2 to generate a multivariate descriptor space matrix; (4) performing dimension reduction processing on the multivariate descriptor space matrix by combining a gradient boosting regression model with a recursive feature elimination algorithm; (5) further screening to obtain an interpretable descriptor by using a least absolute shrinkage and selection operator; and (6) applying the interpretable descriptor to a random forest regression model to screen a catalyst for a propane dehydrogenation reaction to prepare propylene. The application can solve the problem that a traditional descriptor is difficult to directly predict a catalytic product yield.
Owner:DALIAN UNIV OF TECH

Virtual multi-view fusion millimeter wave point cloud imaging method

The invention discloses a virtual multi-view fusion millimeter wave point cloud imaging method, which belongs to the field of millimeter wave radars, and realizes three-dimensional point cloud imaging of a target by constructing a virtual observation view angle and fusing perception data of different view angles: establishing a multi-view synthetic aperture radar imaging model; a single-bit compressed sensing framework is introduced to construct a sparse imaging optimization problem, an accurate relay angle is solved by minimizing a model error, and a relay plane model error is corrected; and high-precision 3D point cloud imaging of the region of interest is realized based on the accurate angle. According to the method, a three-dimensional point cloud of a target is constructed by fusing virtual visual angle detection shielding characteristics formed by reflection of a plurality of relay surfaces, joint estimation of relay surface angle prior and 3D point cloud is realized by a nested iteration method, and artifacts and offset caused by prior errors are eliminated; the sparsity and the target continuity of the three-dimensional point cloud can be improved through the additional composite norm constraint, and the accuracy of virtual multi-view 3D point cloud imaging is effectively improved.
Owner:HUAZHONG UNIV OF SCI & TECH

GIS fault diagnosis method and system based on acoustic monitoring

The invention relates to the technical field of power systems, and discloses a GIS fault diagnosis method and system based on acoustic monitoring, and the method comprises the steps: obtaining the initial sound data of each monitoring point in a GIS; carrying out first fault positioning according to the initial sound data, and obtaining an area where a fault source having a fault in the GIS is located; extracting positioning sound data; performing second fault positioning according to the positioning sound data to obtain position information of a plurality of fault sources in the GIS; performing voiceprint feature analysis according to the positioning sound data to obtain fault types of a plurality of fault sources in the GIS; the fault type comprises a partial discharge fault and a mechanical fault; and performing GIS fault diagnosis according to the position information of the plurality of fault sources and the fault types of the plurality of fault sources. According to the GIS fault diagnosis method and system based on acoustic monitoring, the determination precision of the positions of the fault sources is remarkably improved, and timeliness diagnosis of the multiple fault sources is achieved at the same time.
Owner:国网山西省电力有限公司超高压变电分公司

A vascular flow velocity estimation method based on sparse pulses

The present invention discloses a method for estimating blood flow velocity by transmitting sparse pulses, and specifically designs a blood flow velocity estimation method based on sparse pulses. The present invention transmits sparse pulses to obtain echo signals, and then performs autocorrelation operation and vectorization on the echo signals to obtain virtual echo signals with equivalent uniform emission and a larger number of pulses. The result of spectral estimation of the echo signals is compared with the result of spectral estimation of the virtual echo signals, and finally the value of blood flow velocity estimation is obtained. The method used in the present invention can obtain high-resolution, low-artifact blood flow velocity estimation results with a small number of pulses, which is beneficial for medical ultrasound systems to further improve the refresh rate and real-time performance of B-mode imaging.
Owner:SOUTH CHINA UNIV OF TECH

Construction progress monitoring method for highway construction project monitoring platform

The present invention relates to the field of image communication technology, and in particular to a construction progress monitoring method for a highway construction project monitoring platform, comprising: using a segmentation threshold to segment a differential image between a target image and a reference image to obtain a target pixel on the target image and a reference pixel on the reference image; grayscale values ​​of the target pixel are grayscale transformed, the sparse fusion degree of the transformation curve used and the historical curve is the largest, the sparse fusion degree is obtained by the sparsity of the difference between the grayscale value after the grayscale transformation and the grayscale value of the reference pixel, the similarity between the transformation curve and the historical curve, and the similarity of the grayscale distribution of the target pixel at the first two positions, grayscale transformation is performed on the target image using the transformation curve, and the target image is compressed and transmitted using the difference between the target image after the grayscale transformation and the reference image; the segmentation threshold is corrected according to the error of the transformation curve. The present invention increases the compression transmission efficiency of the target image and saves network resources.
Owner:DONGGUAN CLOUD MEDIA INTELLIGENT TECH CO LTD

Blast furnace sintered ore particle size detection method and system based on RGB and laser feature fusion

The present invention discloses a blast furnace sinter ore particle size detection method and system based on RGB and laser feature fusion. By acquiring an RGB data set and a laser data set, a deep learning network of an encoder-decoder structure is constructed to obtain an RGB initial feature tensor and a laser initial feature tensor. A multi-source feature weighted fusion subnetwork is constructed at the last layer of a fusion branch. Based on the multi-source feature weighted fusion subnetwork, the RGB initial feature tensor and the laser initial feature tensor are adaptively weighted fused to obtain a fused feature tensor, and the fused feature tensor is input into a decoding process to obtain a segmented image. The particle size of the blast furnace sinter ore is detected according to the segmented image, and the technical problem of low detection accuracy of the existing blast furnace sinter ore particle size is solved. By adding a multi-source feature weighted fusion subnetwork to the deep learning network of the encoder-decoder structure, the adaptive weighted fusion of multi-source features can be achieved, and the supplementary role of the laser is fully utilized, which is beneficial to improving the detection accuracy of the blast furnace sinter ore particle size.
Owner:CENT SOUTH UNIV +1

Power data sparsity compression observation method for non-intrusive load monitoring

ActiveCN116842369BImprove learning efficiencySparse, efficient and accurate
This invention relates to a power data sparsity compression observation method for non-intrusive load monitoring, comprising the following steps: Step 1, acquiring power monitoring data and determining its electricity consumption behavior pattern; Step 2, initializing wavelet sparse basis for sample data based on simple power behavior patterns; Step 3, based on the determination results of the electricity consumption behavior pattern of the completed training samples and the results after wavelet basis initialization in Steps 1 and 2, performing improved K-SVD training and generating sparse basis; Step 4, training the sample dataset Y based on Step 3 to obtain a sparse dictionary D, and performing power monitoring data compression observation based on the improved sparse basis.
Owner:TIANJIN UNIV

Community division method based on information granularity

The invention discloses a community division method based on information granularity. The method comprises the steps of generating an initial equivalence relation set; dividing an initial community; further processing the initial equivalence set, generating a generalized equivalence relation set, and realizing community division; and merging classes. The community division method based on the information granularity has the advantages that on one hand, a comprehensive judgment mechanism of user individuals and social attributes is achieved by fusing the user social relation and the comprehensive similarity of label themes, so that the users in the community have high interest similarity, and the user experience is improved; the social relationship closeness of the user is relatively high; and on the other hand, an information granularity method is adopted to perform user clustering and cluster merging, and an interval can be set, so that self-optimization can be realized at a certain step length.
Owner:CHANGZHOU TEXTILE GARMENT INST

Absolute magnetostrictive displacement measurement tape

The invention discloses an absolute magnetostrictive displacement measurement tape, which is characterized in that a magnetic mark is embedded in a through hole of a groove layer according to a certain coding rule and is fixed between a steel wire layer and a coating layer, the tape is vertically suspended in the application process, and the perpendicularity of the tape is guaranteed through the pulling force provided by a spring at the bottom; the magnetostrictive displacement sensor is installed on a measured object and can sense the magnetic marks in the magnetic tape at any time, and the magnetic mark coding rule ensures that the distance between any group of interphase magnetic marks is not larger than the measurement range of the magnetostrictive displacement sensor so as to ensure that at least two magnetic marks can be sensed at any time. Meanwhile, the coding rule ensures that any group of adjacent magnetic marks are inconsistent, so that the absolute position of the first sensed magnetic mark can be determined by combining the time interval of pulses excited by the magnetic marks on the displacement sensor with the sound velocity to convert the distance between the adjacent magnetic marks, and then the transition time of the first pulse signal in the magnetic marks is combined; therefore, the absolute position of the object fixed by the magnetostrictive displacement sensor can be measured and determined in real time.
Owner:HUZHOU INST OF ZHEJIANG UNIV

Linear noise suppression method and device based on rotation time shift FK transformation

The invention relates to a linear noise suppression method and device based on rotation time shift FK transformation, and the method comprises the steps: leveling a linear event in a rotation manner based on the idea of multi-focus separation, and then carrying out the random time shift of each time point in the horizontal direction; frequency differences are formed between events similar to linear noise in apparent velocity due to random time shifting of data. And finally, carrying out linear noise suppression in the frequency-wave number FK domain by applying a compressed sensing reconstruction algorithm. According to the technical scheme, random time shifting is applied, energy near the dominant frequency of the FK domain is evenly distributed to all frequencies, the sparseness of a transform domain is enhanced, and therefore the algorithm can effectively suppress linear noise and reduce event energy loss with the apparent velocity and the frequency similar to those of the linear noise. The technical scheme is suitable for seismic data prestack linear noise suppression, powerful technical means support is provided for high-fidelity and high-signal-to-noise-ratio processing, and the problem that seismic data generally have a low signal-to-noise ratio is solved.
Owner:CHINA PETROLEUM & CHEMICAL CORP +1

A total variation regularized direction finding method and system based on acoustic features

The present invention provides a total variation regularized direction-finding method and system based on acoustic features, comprising obtaining an output acoustic signal of an incident sound source based on a planar array; calculating an estimated value of the direction of arrival of the incident sound source based on a pre-constructed two-dimensional total variation sparse direction of arrival estimation model; wherein the construction process of the two-dimensional total variation sparse direction of arrival estimation model is specifically as follows: establishing a spatially extended sound source model according to the spatial distribution characteristics of the sound source; constructing a two-dimensional array manifold matrix to obtain an overcomplete representation of the two-dimensional array manifold matrix, and determining a two-dimensional sparse representation of the incident sound source based on the overcomplete representation of the two-dimensional array manifold matrix; constructing a two-dimensional total variation structure matrix, and constructing a two-dimensional total variation sparse direction of arrival estimation model based on the two-dimensional total variation structure matrix; the present invention promotes piecewise constant solutions and embodies spatial smoothness, and thus effectively improves DOA estimation performance in situations involving block sparsity or a mixture of peaks and flat areas.
Owner:QINGDAO UNIV OF TECH

A text summary generation method and system based on sparse attention acceleration

This invention discloses a text summarization method and system based on sparse attention acceleration, comprising: reading long text data, performing word segmentation and embedding encoding processing, extracting sequence feature vectors, and mapping them to a query matrix Q, a key matrix K, and a value matrix V; constructing a summarization generation network, including a sparse attention calculation module, a feedforward calculation module, a prediction head module, and a key-value caching module; inputting the query matrix Q, key matrix K, and value matrix V into the summarization generation network, first passing through a backbone network composed of multiple stacks of the sparse attention calculation module and the feedforward calculation module, and then being processed by the prediction head module, while the key-value caching module caches historical decoding states in real time to obtain an initial text feature vector; based on the initial text feature vector, performing an autoregressive decoding process through the summarization generation network to output the final summary result. This invention can accelerate the decoding process and ensure the semantic integrity and coherence of the generated summary.
Owner:ZHEJIANG UNIV

A hybrid dynamic pruning method for large medical model compression

The present invention discloses a hybrid dynamic pruning method for large medical model compression, which adopts a sparse predictor based on hybrid sparse prediction, and has the advantage of reducing performance loss compared with other dynamic pruning methods based solely on dynamic sparse prediction. It effectively solves the problem of serious performance degradation after compression of large medical models, improves the model reasoning speed, and provides a feasible solution for the promotion and application of high-sparse, high-performance large models in practical applications.
Owner:SICHUAN UNIV

Global sparse texture filtering method based on edge structure preservation

The invention provides a global sparse texture filtering method based on edge structure preservation, which comprises the following steps of: introducing a texture suppression function into a penalty term, constraining the gradient of an output image, and suppressing texture, noise and unnecessary detail information in the image by setting two threshold values through the texture suppression function, then, the suppressed gradient is used as input of a denominator of a penalty term, so that the penalty term can fully distinguish the texture from the structure; a penalty term is constrained by adopting a sparse regular L1 norm, non-convex optimization is converted into convex optimization by introducing subgradient, and iterative solution is carried out by adopting an alternating direction multiplier method, so that better edge preservation is achieved; and an Lp norm with relatively high sparsity is adopted to constrain a penalty term, and a preprocessing conjugate gradient method is adopted to accelerate and improve the calculation efficiency, so that a more robust and sparsity image smoothing effect is achieved. According to the method, the robustness of an algorithm for distinguishing textures and structures can be improved, relatively good semantic information is reserved, and relatively good smooth performance of edge structure maintenance is achieved.
Owner:CHONGQING UNIV OF TECH

Trigonometric function implementation method based on memristor

The invention provides a trigonometric function implementation method based on a memristor, and belongs to the technical field of storage and calculation integration. According to the method, firstly, precision is calculated based on a cordic algorithm angle, a target angle is split, split angle set coefficients are grouped, iterative calculation is performed in a trigonometric function calculation module according to grouping, all groups are performed synchronously, finally, grouping calculation results are summarized, and a final result is calculated in a summarized trigonometric function calculation module. According to the method, a trigonometric function storage and calculation integrated calculation framework designed in a grouping and parallel pipeline mode and corresponding data streams are adopted, a nonlinear function calculation task based on a cordic algorithm is achieved, high-precision trigonometric function calculation is achieved, the blank of trigonometric function hardware acceleration in the storage and calculation integrated field is perfected, and the calculation efficiency is improved. And further development of a storage and calculation integrated technology and a large model technology is promoted.
Owner:PEKING UNIV

Sea surface small target detection method based on optimized characteristic modal decomposition

ActiveCN120871067BAchieve dual collaborative optimizationImprove the ability to distinguishWave based measurement systems
This invention belongs to the field of radar signal processing technology and discloses a method for detecting small sea targets based on optimized feature mode decomposition, including: S1: acquiring the signal data to be detected; S2: decomposing the original signal into several modal components using FMD, and selecting envelope spectral entropy as the fitness function; S3: using the SOS algorithm to globally optimize the fitness function in FMD; S4: introducing the PSO algorithm to locally optimize the key parameters of FMD; S5: retaining components with low envelope spectral entropy values ​​and correlation coefficients greater than a threshold; S6: extracting envelope spectral entropy and frequency band energy proportion features from the selected modal components, introducing the Gini coefficient as a weighting factor, and constructing GSEBE joint features; S7: inputting the envelope spectral entropy value into a DELM classifier with controllable false alarm rate, and achieving target detection based on the comparison between the predicted value and the decision threshold. This invention enhances the ability to distinguish between sea clutter and target echoes, achieving more accurate classification and detection.
Owner:NANTONG INST OF TECH

Health state recognition method based on image statistical characteristics

The invention relates to a health state recognition method based on image statistical characteristics. Comprising the following steps of: firstly, acquiring an original vibration signal of a bearing by using a sensor, converting the original vibration signal into a time-frequency domain color image by adopting short-time Fourier transform, and then converting the time-frequency domain color image into a grayscale image by using grayscale transform; secondly, extracting six types of image statistical characteristics from the grayscale image, wherein the six types of image statistical characteristics comprise a mean value, a variance, a contrast ratio, correlation, energy and homogeneity; then, six types of image statistical features are used as input, and a fusion feature vector is output through a designed stability-enhanced sparse PCA (Principal Component Analysis) module; and finally, performing health state recognition on the fused feature vector by using a state change detection function. The method is good in recognition effect and high in industrial scene adaptability, and provides high-precision and high-reliability technical support for predictive maintenance of equipment; the method is high in calculation efficiency, good in real-time performance and high in robustness, unification of precision, efficiency and robustness is achieved, and the method is very suitable for online real-time monitoring application in engineering practice.
Owner:XIAN TECH UNIV