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

137 results about "Matrix optimization" patented technology

Matrix Optimization is used to determine the most optimal parameters for Regular Re-optimization: how often and in what IS/OOS proportion it will be used. The Matrix Optimization feature also includes the system of Strategy Robustness estimation. The estimation is carried out according to the user specified criteria.

Road compaction degree real-time regulation and control method and system based on digital twinning

The invention relates to the field of road compactness monitoring, in particular to a road compactness real-time regulation and control method and system based on digital twinning, and the method comprises the steps: collecting vibration acceleration, temperature and position data, and generating a time-space aligned multi-source fusion feature data set after processing; inputting a pre-trained LSTM model to construct a dynamically updated digital twinborn body, and outputting a three-dimensional compaction energy spectrum; dispersing the atlas and calculating parameters, and generating a compaction degree deviation matrix; a regulation and control instruction is generated and issued based on matrix optimization; and according to the measured data and the predicted value residual error, triggering re-optimization and calibrating the sensor. According to the method, the problems of non-uniform compaction quality and over-high energy consumption caused by poor adaptability, decision lag and error coupling of a traditional static model are solved.
Owner:HANDAN HENGZHI ROAD BUILDING CO LTD

Large-scale satellite stereoscopic image data processing method, medium and system

The invention provides a large-scale satellite three-dimensional image data processing method, medium and system, and belongs to the technical field of satellite three-dimensional image data processing.The method comprises the steps that Gaussian filtering and wavelet noise reduction preprocessing is conducted on an image, and then cooperative computing of a GPU and a CPU is achieved based on a computing task distribution function. Through multi-scale feature extraction and matrix optimization, a stable feature matrix and a variable feature matrix are obtained. A quadtree spatial index is adopted to carry out data partitioning, and SIFT feature extraction and K-means clustering are combined to optimize feature representation. And establishing a stereoscopic image registration model, determining an optimal splicing sequence through a minimum spanning tree algorithm, realizing image splicing by adopting a progressive texture fusion method, and finally generating a high-precision three-dimensional earth surface model. According to the invention, the unification of processing efficiency and precision is realized, and the technical problem that the processing efficiency of large-scale stereoscopic image data is difficult to improve on the premise of ensuring the processing precision in the prior art is solved.
Owner:MINISTRY OF NATURAL RESOURCES LAND SATELLITE REMOTE SENSING APPL CENT

Unmanned aerial vehicle cluster patrol path decision-making method under resource constraint

The invention discloses an unmanned aerial vehicle cluster patrol path decision-making method under resource constraint, and relates to the technical field of unmanned aerial vehicle path planning, and the method comprises the steps: carrying out the discretization of an actual to-be-patrolled physical position, and constructing an undirected topological graph; generating steady-state distribution of each patrol node according to topological constraints and importance degrees of the nodes; generating a plurality of transfer matrixes with the same steady-state distribution and different transfer characteristics according to a multi-stage entropy driving random matrix optimization algorithm; initializing the position of a navigator according to the transfer matrix and determining a selected path; according to the reference path of the navigator, the self-adaptive active positioning decision is realized under the positioning constraint to ensure the path tracking effect; according to path selection and tracking of the navigator, the follower and the navigator form a humanoid marshalling cluster through a reward function; and according to the multi-state transfer matrix and the humanoid marshalling, automatically switching to the next transfer matrix when a transfer frequency threshold value is reached, and realizing unmanned aerial vehicle cluster intelligent patrol path decision under resource constraint.
Owner:SUN YAT SEN UNIV

InSAR and GNSS robust adaptive fusion method for high-precision three-dimensional surface deformation monitoring

The invention discloses an InSAR (Interferometric Synthetic Aperture Radar) and GNSS (Global Navigation Satellite System) robust adaptive fusion method for high-precision three-dimensional surface deformation monitoring, which belongs to the technical field of space geodetic survey and remote sensing, and comprises the following steps of: constructing a time sequence deformation field based on a small baseline set time sequence InSAR processing technology, and resampling GNSS observation data to a grid consistent with the InSAR by using Kriging spatial interpolation; a Helmert variance component estimation method is adopted to adaptively estimate variance components of InSAR and GNSS data, and reasonable weight fixing of a multi-source observation value is achieved; iterative reweighted least square estimation is introduced, outlier influences in various observation data are dynamically restrained through a Tukey double-weight function, robust optimization of a fusion model is achieved, and therefore a high-precision three-dimensional deformation field is reconstructed. The method comprises the steps of Helmert weight fixing, IRLS robust, variance component updating and a closed-loop feedback mechanism of weight matrix optimization.
Owner:SHANGHAI PUJIANG BRIDGE & TUNNEL OPERATION MANAGEMENT CO LTD +2

Method for generating front-end prototype based on artificial intelligence technology

The invention provides a method for generating a front-end prototype based on an artificial intelligence technology. The method comprises the steps of data acquisition, knowledge base construction, model training and optimization, demand analysis and prototype generation. The method comprises the following steps: constructing a knowledge base supporting multi-dimensional query by collecting and verifying historical data; in combination with the content of the knowledge base, a large language model is used for performing field specialized fine tuning, and low-rank matrix optimization and comparative learning are adopted to improve the task similarity detection precision; semantic analysis and structured conversion are carried out on the natural language requirements of the user; a front-end prototype is automatically generated based on structured data, and user interaction feedback and dynamic optimization are supported. According to the method, efficient data processing, intelligent model optimization and flexible prototype design are realized, the intelligent level and development efficiency of prototype generation are improved, and powerful support is provided for front-end design under rapid iteration and complex requirements.
Owner:BEIJING GUODIANTONG NETWORK TECH CO LTD +1

Normalized minimum sum decoding and post-processing decoding method for BCH codes

ActiveCN119154894BCode conversionCyclic codesAlgorithmShort loop
The present invention belongs to the technical field of decoding algorithms, and specifically relates to normalized minimum sum decoding of BCH codes and post-processing decoding methods thereof, the steps of which include optimizing the standard form of the check matrix of the BCH code to obtain the best check matrix; inputting the received sequence into the improved normalized minimum sum decoding algorithm NMS based on the best check matrix for decoding; if the decoding is successful, outputting the best decoding estimate; if the decoding fails, inputting the sequence iteration trajectory after the NMS decoding failure into the DIA neural network model, analyzing and outputting the reliability metric of each bit, and then decoding again through the ordered statistical decoder OSD to obtain the best decoding estimate. The present invention successfully achieves the low density of the check matrix, the reduction of the number of short loops, and the uniform distribution of column weights through an innovative check matrix optimization algorithm, and provides a more efficient and better performance BCH code decoding solution.
Owner:SHANDONG INST OF BUSINESS & TECH

Multi-modal emotion recognition method based on heart and brain coupling and graph neural network

The invention relates to a multi-modal emotion recognition method based on heart and brain coupling and a graph neural network, and belongs to the field of artificial intelligence. Comprising the steps of data preprocessing, graph representation construction, multi-view graph convolutional network construction, fusion graph network construction and cross-domain joint optimization and sentiment classification. The method has the advantages that an adaptive adjacency matrix optimization strategy based on a triple constraint mechanism is proposed to solve the modal alignment and deviation problems represented by a multi-modal diagram in a data-driven branch, redundant noise is eliminated by adopting global regularization constraint, and unique feature representation in a modal is enhanced through modal specificity; a deep association rule is mined in combination with a cross-modal interaction module, the modeling ability of a heart and brain emotional state is improved, a multi-view image convolutional network is further designed, global features and local features are extracted, features of a cognitive heuristic branch and a data driven branch are combined by adopting an attention mechanism-based image fusion network, a domain confrontation strategy is introduced, and a cognitive network is constructed. And the generalization of the method is enhanced.
Owner:JILIN UNIVERSITY

Bayesian Cramer-Rao bound beamforming optimization method for near-field flux and inductance integration

The invention discloses a near-field flux-sensing integrated Bayesian Cramer-Rao bound beamforming optimization method, which aims at minimizing the Bayesian Cramer-Rao bound of an extended target response matrix, and constraint conditions comprise the maximum transmitting power of a base station, the minimum signal to interference plus noise ratio requirement of a communication user and the minimum energy efficiency of a system. Auxiliary variables are introduced, an original optimization problem is converted into an equivalent full-digital beam forming matrix optimization problem, and iteration is carried out by adopting a sequential convex approximation method until convergence is carried out to obtain a local optimal solution; aiming at the local optimal solution, constructing an optimization problem by using a method of approaching an equivalent full-digital beam forming matrix by using a hybrid beam forming matrix; and an analog beam forming matrix and a digital beam forming matrix are obtained through an alternate optimization method. According to the method, the Bayesian Cramer-Rao bound minimum transmitting beam design problem of the near-field communication and sensing integrated system is researched, and sensing of an extended target can be realized under the condition that the communication energy efficiency of the system is met.
Owner:SOUTHEAST UNIV

Normalized minimum sum decoding and post-processing decoding algorithm of BCH code

The invention belongs to the technical field of decoding algorithms, and particularly relates to a normalized minimum sum decoding and post-processing decoding algorithm of a BCH code, which comprises the following steps of: for the BCH code, optimizing a check matrix in a standard form of the BCH code to obtain an optimal check matrix; inputting the receiving sequence into an improved normalized minimum sum (NMS) decoding algorithm based on the optimal check matrix for decoding; if the decoding is successful, outputting the optimal decoding estimation; and if the decoding fails, inputting a sequence iteration track after the NMS decoding fails into the DIA neural network model, analyzing and outputting the reliability measurement of each bit, and then decoding again through an ordered statistical decoder OSD to obtain the optimal decoding estimation. Through an innovative check matrix optimization algorithm, low density of the check matrix, reduction of the number of short rings and uniform distribution of column weights are successfully realized, and a BCH code decoding scheme which is more efficient and better in performance is provided.
Owner:SHANDONG INST OF BUSINESS & TECH

Intelligent industrial control parameter self-tuning method and equipment

The invention relates to an intelligent industrial control parameter self-tuning method and equipment. The method comprises the following steps: performing piecewise linearization processing on an actuator input and output characteristic curve in the industrial control system, constructing an upper-layer agent model and a lower-layer agent model, and combining to obtain a system dynamic characteristic prediction model; performing state observer design and gain matrix optimization on the industrial control system based on the system dynamic characteristic prediction model to obtain a system state observation vector and an interference compensation vector; inputting the system state observation vector and the interference compensation vector into a fixed time convergence controller for control parameter calculation to obtain a system control input matrix; and performing adaptive gradient descent operation and momentum item optimization on the system control input matrix, and outputting an optimal control parameter matrix in combination with the system dynamic characteristic prediction model. According to the invention, real-time automatic adjustment of the control parameters is realized, the steady-state error of the system is effectively reduced, and the control performance of the control system under different working conditions is ensured.
Owner:SHENZHEN BAIQIANCHENG ELECTRONICS CO LTD

New energy station transient voltage and frequency coordination stability control method

The invention relates to the technical field of power system stability control, in particular to a new energy station transient voltage and frequency coordination stability control method, which comprises the following steps of: analyzing a transient energy evolution rule of an equivalent synchronous motor and stored energy by constructing an alternating current and direct current hybrid dynamic model and fusing with multi-time scale characteristics; based on dynamic weight matrix optimization and a multi-target coordination control strategy, self-adaptive balance of power distribution is realized; a nonlinear feedback algorithm and a real-time compensation mechanism are designed in combination with the Lyapunov theory, and voltage frequency fluctuation in a disturbance scene is suppressed; establishing a multivariable cooperative control architecture, and dynamically adjusting a power adjustment priority and an inertia time constant through coupling iterative optimization of a source storage cooperative strategy to realize adaptive compensation of a transient energy propagation path; according to the method, the dynamic stability and the anti-interference capability of the new energy station under transient impact are remarkably improved, and safe operation of a high-proportion new energy power grid is guaranteed.
Owner:YUNNAN POWER GRID CO LTD +1

Beam generation method of BD-RIS-assisted dual-function radar communication system

The invention provides beam generation of a BD-RIS-assisted dual-function radar communication system, and particularly relates to the technical field of wireless communication, and the scheme comprises the following steps: constructing the BD-RIS-assisted dual-function radar communication system, and constructing a user weighting and rate optimization problem under communication and perception constraints; decomposing a user weighting and rate optimization problem into a base station transmitting precoding matrix optimization problem and a BD-RIS matrix optimization problem; alternately and iteratively executing the step of solving the base station transmitting precoding matrix optimization problem and the BD-RIS matrix optimization problem to obtain an optimal precoding matrix and an optimal BD-RIS matrix; and based on the optimal precoding matrix and the optimal BD-RIS matrix, converting an initial beam pointing to the BD-RIS and the target area into a target beam. According to the scheme, the joint optimization problem is solved, the sensing performance is guaranteed, the communication rate of the communication user is remarkably improved, and the user communication and target detection requirements are met at the same time.
Owner:SHENZHEN UNIV

Fluid antenna position and radar communication precoding matrix optimization method in URLLC scene

The invention discloses a fluid antenna position and radar communication precoding matrix optimization method in a URLLC scene. The method comprises an integrated architecture supporting communication and perception of multiple user terminals and a single perception target; constructing a communication signal model between the base station and the user terminal in the URLLC scene and a sensing signal model between the base station and the detection target; establishing a mathematical model of a radar communication signal optimization problem by taking maximization of a radar sensing signal-to-noise ratio as a target and taking base station transmitting power, URLLC time delay requirements and fluid antenna position limitation as constraints; the optimization problem is decomposed into three sub-problems, an alternating iteration optimization algorithm is adopted, the three sub-problems are alternately optimized, and a convergence solution is obtained through iteration. According to the invention, the URLLC technology and the multiple-input-multiple-output antenna array and fluid antenna technology are utilized, communication and radar sensing are executed on the same frequency spectrum at the same time, and the requirements of communication and radar sensing in a future network are met.
Owner:NANJING UNIV OF POSTS & TELECOMM

Tea color automatic evaluation method and system based on machine vision

The invention relates to the technical field of machine vision and optical detection, in particular to a tea color automatic evaluation method and system based on machine vision. The method comprises the following steps: constructing a stable and repeatable optical measurement environment and calculating radiation baseline parameters; performing multi-band polarization sequence imaging on the tea sample to obtain original data with spectrum and structural characteristics; separating mirror surface and diffuse reflection components on the surfaces of the tea leaves, and performing spectrum consistency correction by combining a radiation baseline; performing multiband spectrum reconstruction and normalization processing on the basis of the corrected diffuse reflection image, mapping to a CIE Lab color space, extracting pixel-level brightness, chromaticity and color distribution statistical indexes, and generating a color feature vector in combination with spatial weighting matrix optimization; a final score is calculated by constructing a quantitative evaluation and grade judgment model and integrating perception color separation, drying calibration color separation and a penalty term, and a grade result is output. According to the method, objective, accurate and automatic evaluation of the color of the tea leaves is realized.
Owner:PINGLI COUNTY CUIMINGJIAN AGRICULTURAL DEVELOPMENT CO LTD

Multi-mode enterprise intelligent brain system based on artificial intelligence

The invention discloses a multi-mode enterprise intelligent brain system based on artificial intelligence, and belongs to the technical field of big data processing. The method and the device are used for solving the technical problems of poor multi-modal data processing precision and poor system robustness in the existing scheme. Semantic alignment of multi-modal features can be realized through a closed-loop process of pre-extraction, comparative learning, dimension alignment, dynamic optimization and verification and fine adjustment, cross-modal semantic association is established through comparative learning, space mismatching is solved through dimension alignment, dynamic matrix optimization fits task requirements, and actual effects are ensured through verification and fine adjustment. Through a progressive process of confidence evaluation, task coding, weight calculation, feature fusion and end-to-end optimization, intelligent weighting of multi-modal features is realized, and through confidence evaluation, reliable data is screened, a decision target is determined through task coding, a gating network dynamically allocates weights, and end-to-end optimization ensures that a strategy meets service requirements.
Owner:BEIJING FUTURE CHAIN TECH CO LTD

Sanitation vehicle intelligent scheduling method and system, and storage medium

The invention relates to a sanitation vehicle intelligent scheduling method and system and a storage medium, and the method comprises the steps: a data collection step: collecting environment data and vehicle information in real time, the environment data including garbage accumulation amount, traffic condition and weather forecast, and the vehicle information including vehicle position and state; a data processing step: cleaning and formatting the collected environment data and vehicle information, and constructing a feature vector and an input matrix; a scheduling optimization step: processing the data generated in the data processing step by using a quantum heuristic evolutionary algorithm, and finding out an optimal scheduling scheme; and an execution monitoring step: executing a cleaning task according to the optimal scheduling scheme generated in the optimization scheduling step, monitoring the cleaning progress in real time, collecting the cleaning progress and state information, and feeding back the information to the data acquisition step to form closed-loop control. According to the invention, the accuracy and reliability of scheduling decisions are improved.
Owner:CHONGQING ENVIRONMENT & SANITATION GRP CO LTD

Marketing operation method based on big data analysis

The invention relates to the technical field of marketing operation based on big data analysis, and discloses a marketing operation method based on big data analysis. Preprocessing the user-commodity interaction data to construct an initial interaction matrix; constructing a co-occurrence counting matrix; automatically calculating a sparse penalty coefficient and a convergence threshold; setting an optimization objective function and a soft threshold function; initializing a projection matrix and iteratively solving a sparse projection matrix through a coordinate descent algorithm; constructing a commodity sparse co-occurrence adjacency set; and generating a personalized recommendation result in combination with user historical behaviors. The analysis quality is improved through data preprocessing and denoising, commodity potential correlation is mined through co-occurrence modeling, adaptability is enhanced through automatic parameter adjustment, a projection matrix optimization result is sparse and interpretable, the structure sensing capacity of recommendation is improved through an adjacent structure, and finally high-precision and high-correlation recommendation is achieved. The structure definition, the calculation efficiency and the model generalization ability are excellent, and an efficient and stable personalized marketing recommendation system is constructed.
Owner:BEIJING HIXI BRAND MANAGEMENT CO LTD

Finite element design analysis method and system for end structure of belted layer of engineering tire

The invention belongs to the technical field of tire engineering design, and discloses an engineering tire belted layer end structure finite element design analysis method and system. Comprising the steps of obtaining and preprocessing tire carcass contour data and initial belted layer parameters, conducting belted layer end parametric modeling on the basis of a standardized tire geometric model, constructing a durability finite element analysis model to obtain a stress-strain distribution field, conducting multi-parameter sensitivity analysis to determine a key influence factor weight matrix, and obtaining a stress-strain distribution field. And optimally designing a belted layer end structure based on the matrix, and finally performing durability verification and evaluation. According to the method, through accurate geometric expression, flexible parametric modeling, accurate performance analysis and multi-objective optimization design, belted layer end stress distribution uniformization and structural rigidity optimization are achieved.
Owner:中策橡胶(天津)有限公司

Processing temperature optimization control method and system applied to plastic pipe fitting

The invention relates to a processing temperature optimization control method and system applied to a plastic pipe fitting, and the method comprises the steps: M1, collecting the change data information of historical temperatures of different sections of a charging barrel of an extruder in the processing process of the plastic pipe fitting in the extruder, the data information of the temperature of each section of a charging barrel of the extruder, the data information of the rotating speed of a screw rod and the data information of the pressure of a machine head are collected in real time; and M2, based on the change data information of the historical temperatures of the different sections of the extruder charging barrel, predicting the temperature of each section of the extruder charging barrel by adopting a BP neural network regression prediction algorithm based on random walk matrix optimization to obtain predicted data information of the temperature of each section of the extruder charging barrel. According to the invention, the temperature of each section of the extruder cylinder can be accurately controlled and adjusted, so that the energy consumption is reduced, and self-adaptive adjustment can be carried out according to different application scenes in the control process, so that the robustness of the system is improved.
Owner:HUBEI HUIFENG PLASTIC PIPE

High-speed rail station building comprehensive energy efficiency analysis and judgment system based on digital twinning

The invention relates to the technical field of data processing, in particular to a digital twinning-based comprehensive energy efficiency analysis and judgment system for a high-speed rail station building, and the system comprises a multi-dimensional perception acquisition module which outputs an environment tensor, an equipment vector and a people flow matrix which are synchronous in time; the dynamic coupling modeling module generates an equipment coupling characteristic impedance coefficient matrix; the optimization algorithm knowledge base module dynamically activates a multi-target genetic algorithm, a particle swarm optimization algorithm and a model prediction control or reinforcement learning algorithm according to the passenger flow growth rate and temperature rise rate characteristic indexes, and outputs an optimization parameter set to the four-dimensional parallel simulation module; the simulation module generates an equipment state parameter combination and an energy efficiency index; the energy efficiency collaborative evaluation module generates a global energy efficiency evaluation report through Pareto frontier analysis and Markov decision; the energy efficiency report generation module outputs a visual chart and equipment maintenance suggestions, and the energy efficiency and state double-closed-loop module triggers model correction based on pipe network pressure difference, temperature uniformity and energy efficiency ratio deviation.
Owner:INST OF COMPUTING TECH CHINA ACAD OF RAILWAY SCI +2

Intelligent reflector-assisted NOMA uplink transmission method based on energy efficiency

The invention discloses an intelligent reflector assisted NOMA uplink transmission method based on energy efficiency. The method comprises the following steps: firstly, establishing an IRS-assisted NOMA uplink system; and designing a joint optimization problem of transmitting power control at the user and phase shift matrix optimization at the IRS, wherein the joint optimization problem is used for maximizing the energy efficiency of the uplink system. Then decoupling optimization variables in the joint optimization problem by adopting a block coordinate descent method, and optimizing each variable, namely dividing the joint optimization problem into two sub-problems of user power control and IRS phase shift matrix optimization; and finally, the two sub-problems are solved in sequence until the solved precision difference reaches the preset precision or the number of iterations reaches a certain number of times. According to the invention, the bit number of data transmitted per Hertz under unit energy can be increased to the greatest extent, and is measured through energy efficiency.
Owner:HANGZHOU DIANZI UNIV

Large model training method based on second-order matrix optimization

The invention discloses a large model training method based on second-order matrix optimization, and belongs to the field of deep learning model training technology optimization, and the large model training method based on second-order matrix optimization comprises the following steps: S1, decomposing a second-order matrix into row and column vectors, and carrying out sliding average and distributed block reduction storage; s2, generating a statistical row vector by combining row gradient aggregation with a historical attenuation factor; s3, carrying out block distributed statistics in the column direction and synchronously generating column vectors across equipment; s4, a low-rank matrix is constructed through outer products of row and column vectors, and estimation precision is improved through noise suppression; s5, performing dynamic sparse sampling, performing initial high-density focusing, and stabilizing the sampling rate of a key layer; s6, the sampling points execute time sequence attenuation updating, and asynchronous calculation is carried out to improve the resource utilization rate; s7, performing Gaussian kernel smoothing on a neighborhood value compensation coverage gap in an unsampled region; s8, fusing low-rank estimation and sparse data, and balancing global precision by self-adaptive weight; the method has the beneficial effects of reducing video memory occupation, and improving distributed computing efficiency and balance training precision and speed.
Owner:BEIJING DIGITAL FUTURE TECHNOLOGY CO LTD

Coding method and system based on matrix optimization and storage and calculation integrated accelerator, and medium

The invention discloses a coding method and system based on matrix optimization and a storage and calculation integrated accelerator and a medium, and relates to the technical field of communication, and the method comprises the steps: constructing the storage and calculation integrated accelerator which comprises an input buffer area, a dynamic reconstruction storage and calculation array and a result processing module; m * n sub-matrixes obtained by splitting the check matrix H are respectively stored in corresponding storage and calculation integrated cores of the dynamic reconstruction storage and calculation array; the total code c is divided into n segments through an input buffer area and then multiply-accumulate with the corresponding column of sub-matrixes, a calculation result of the dynamic reconstruction storage array is input into a result processing module for result processing, and a final coding result is obtained; according to the coding method, the coding system and the medium, the dynamic adaptability and the calculation efficiency are broken through, and a high-reliability and low-delay LDPC coding solution is provided for tape storage.
Owner:HANGZHOU INTERNATIONAL INNOVATION INSTITUTE OF BEIHANG UNIVERSITY

Transform-based unsupervised cell segmentation method

The invention relates to an unsupervised cell segmentation method based on Transform, and the method is characterized in that a multi-modal text image alignment module aims at effectively fusing text and image data, and achieves the high alignment of multi-modal information through a Transform architecture; the mutual relevance of the data is enhanced through a low-rank attention mechanism, so that the multi-modal features can be extracted and aligned more accurately in an unsupervised environment. The matching matrix feature optimization module further processes the aligned feature data. According to the method, a unique matching matrix optimization algorithm is utilized, the precision of feature matching is remarkably improved, parameters of segmented cells are extracted and adjusted through the optimized matching matrix, and a more accurate initial prompt is provided for the subsequent segmentation process. The optimized features are input to an SAM segmentation module. And the SAM realizes high-precision cell segmentation by utilizing the strong segmentation capability of the SAM. The module gives full play to the advantages of a low-rank attention mechanism and matching matrix optimization, and ensures the accuracy and robustness of a segmentation result.
Owner:HANGZHOU DIANZI UNIV

Phase-only array wide main lobe transmitting power directional diagram synthesis method based on rank-one matrix optimization

The invention discloses a phase-only array wide main lobe transmitting power pattern synthesis method based on rank-one matrix optimization, which comprises the following steps of: constructing a wide beam power pattern synthesis problem model of minimum power gain in a maximum main lobe region, an objective function in the wide-beam power pattern synthesis problem model is a maximum and minimum fraction objective function; introducing a first auxiliary variable, and converting a maximum and minimum fraction objective function form into a maximum and minimum integer objective function form by using generalized fraction programming; and introducing a second auxiliary variable to equivalently represent the problem of maximization and minimization as a minimization form, and solving by using an equivalent rank-one method, a continuous convex approximation method and a penalty method to obtain an optimal phase-only emission weight.
Owner:NANJING UNIV OF SCI & TECH

Automobile radiator finished product performance prediction method based on machine learning

The invention belongs to the technical field of automobile radiator production processes, and particularly relates to an automobile radiator finished product performance prediction method based on machine learning. The method comprises the following steps: firstly, acquiring radiator manufacturing data including material components, process parameters, environmental conditions and performance test data; secondly, a meta-learning algorithm is used for constructing a model for preliminary training, and the steps of task division, adaptive learning rate adjustment, Hessian matrix optimization and the like are included; then introducing physical knowledge constraints, and fusing heat conduction and heat convection equations into a loss function in a soft target mode; and finally, evaluating the model by adopting an increment verification mode, including continuous monitoring and collection of new data, batch increment evaluation and the like. The method solves the problems that an existing method is poor in adaptability, not combined with physical knowledge, reduced in long-term performance and the like, prediction accuracy and model adaptability are improved, and it is ensured that model output conforms to the physical law.
Owner:CHIPING LUHUAN AUTOMOBILE RADIATOR CO LTD

Information source coding matrix data processing method based on modified conjugate gradient algorithm

The invention relates to the technical field of computers, and discloses an information source coding matrix data processing method based on a modified conjugate gradient algorithm. According to the method, sparsity constraint and a fixed-point quantization mechanism are fused in iterative optimization, and a sparse fixed-point coding matrix meeting hardware deployment requirements is directly generated through gradient shielding, correction conjugate parameter calculation and Armijo criterion line search and synchronous execution of hard threshold sparseness and fixed-point quantization after each update. According to the method, the sparsity constraint and the fixed-point quantization mechanism are embedded in the iteration process of the modified conjugate gradient algorithm, so that end-to-end alignment of coding matrix optimization and hardware deployment requirements is realized.
Owner:FUZHOU STRAIT VOCATIONAL & TECH COLLEGE

Multi-domain power grid data collaborative modeling method and system based on tensor game diagram

The invention provides a multi-domain power grid data collaborative modeling method and system based on a tensor game diagram, and the method comprises the following steps: firstly constructing a six-dimensional enhanced tensor model, constructing a six-order tensor based on the number of nodes, timestamps and other six dimensions, and obtaining a kernel tensor and a factor matrix through CPD-Tucker mixed decomposition; a joint optimization objective function containing reconstruction errors, game equilibrium and privacy risks is constructed, and an optimization kernel tensor and factor matrix is solved; and finally, inputting an optimization result into the MGGCN, processing double targets through a leader branch (a physical topology adjacency matrix guarantees reliability) and a follower branch (a market transaction incidence matrix optimizes economic cost), and generating a collaborative decision result through multi-head attention fusion. According to the method, the problems of low multi-source heterogeneous data fusion efficiency and difficulty in considering cross-domain collaborative privacy security and dynamic optimization are solved, the new energy output prediction error can be reduced, and the data utility loss caused by global encryption is reduced.
Owner:HUBEI CENT CHINA TECH DEV OF ELECTRIC POWER +1

Matrix controllable switch fault self-detection and life prediction system and working method

The invention discloses a matrix controllable switch fault self-inspection and life prediction system and a working method, and belongs to the field of matrix switch non-intrusive testing, and the matrix controllable switch fault self-inspection and life prediction system comprises a test module composed of a matrix switch unit, a to-be-tested circuit assembly and a function test unit, a non-intrusive matrix self-inspection module and a life prediction and data recording module. Wherein the matrix switch unit comprises # imgabs0 # matrix switches, # imgabs1 # is the total number of test points of a circuit assembly to be tested, # imgabs2 # is the total number of test points accessed by the function test unit, and # imgabs3 # is the number of common column lines; the matrix switch unit is connected with the non-intrusive matrix self-checking module; and the non-intrusive matrix self-checking module is connected with the life prediction and data recording module. By adopting the matrix controllable switch fault self-inspection and life prediction system and the working method, high efficiency, safety and intelligence of circuit assembly testing are realized through non-intrusive self-inspection, matrix optimization, an intelligent prediction model and accurate fault positioning.
Owner:杭州君谋科技有限公司

Method for accelerating point cloud registration based on 3DSC and improved ICP algorithm

The invention discloses a method for accelerating point cloud registration based on 3DSC and an improved ICP algorithm, and the method comprises the following steps: S1, reducing the data volume of a point cloud through the combination of voxel filtering and Gaussian sampling, guaranteeing the integrity of a point cloud structure, and improving the processing speed of the point cloud; and S2, performing feature descriptor extraction and feature descriptor matching by using a 3DSC algorithm. And S3, optimizing parameters such as neighbor search radius and point cloud density according to point cloud characteristics to obtain better matrix estimation. And S4, transmitting the coarse registration matrix estimation to an NICP algorithm, initializing an initial homogeneous transformation matrix of the NICP algorithm, and improving the registration precision. And S5, in the NICP algorithm, using the KD-Tree to accelerate the nearest neighbor search and point cloud matching process, and reducing the calculation time. And S6, matrix optimization is carried out in combination with an ICP improved algorithm, namely an NICP fine registration algorithm.
Owner:滨沅国科(秦皇岛)智能科技股份有限公司