59 results about "Clonal selection algorithm" patented technology

The invention discloses a non-convex compressed sensing image reconstruction method based on a redundant dictionary and structure sparsity. A reconstruction process of the method includes: observing original image blocks; using a mutual neighboring technology for clustering observation vectors; using a genetic algorithm for finding optimal atom combinations in a dictionary direction for each class of observation vectors, and preserving species; after species expansion operation is executed on each image block, using a clonal selection algorithm for finding an optimal atom combination on scale and displacement in a determined direction for each image block; reconstructing each image block by the optimal atom combination; and piecing all the constructed image blocks in sequence to form an entire constructed image. Image structure sparsity prior and redundant dictionary direction features are fully utilized, the genetic algorithm is combined with the clonal selection algorithm, and the method is used as a nonlinear optimization reconstruction method to realize image reconstruction. The reconstructed image is good in visual effect, high in peak signal noise ratio and structural similarity, and the method can be used for non-convex compressed sensing reconstruction of image signals.

A method for detecting dynamic gridding instruction based on artificial immunity, is a method for detecting instruction facing to gridding which takes use the artificial immunity technique for reference. According to the dynamic and real time requirement of the instruction detection under gridding surroundings, the method takes the prior clonal selection algorithm as main body, combines negative selection, clonal selection, affinity maturation and memory detector gene bank method, so at to dynamic handle the instruction detection under gridding surroundings. The method includes a dynamic detector evolvement process and a gridding instruction detection process which are based on artificial immunity, which is characterized in by using the artificial immunity technique for reference, and combining the negative selection, clonal selection, affinity maturation and memory detector gene bank method; firstly obtaining an evolvement matured detector; and then dynamically handling the instruction detection problem in the gridding surroundings under the coordination of the artificial immunity mechanism, to complete the entire process of dynamic gridding instruction detection.

The invention discloses a compressed sensing image reconstructing method based on a prior model and 10 norms, mainly used for solving the defects of poor visual effect and long operation time existing in image reconstruction in the prior art. In the technical scheme of the invention, a compressed sensing image reconstruction frame with 10 norms is optimized by utilizing a prior model; and the positioning of sparsity coefficient and solution of the sparsity coefficient value are achieved through two effective steps: step 1, establishing the prior model, and carrying out low frequency coefficient inverse wavelet transform so as to obtain an image with a fuzzy edge, determining the position of the edge by edge detection, and searching the position of wavelet high frequency subband sparsity coefficient through an immunization genetic algorithm by using the prior model of which the wavelet coefficient has inter-scale aggregation; and step 2, solving a corresponding high frequency subband by using an improved clone selective algorithm, and then carrying out the inverse wavelet transform so as to obtain a reconstructed image. Compared with the prior art, the method has the advantages of good visual effect and low calculation complexity, and can be used in the fields of image processing and computer visual.

The invention discloses a compressed sensing image reconstruction method based on a principal component analysis (PCA) redundant dictionary and direction information. The compressed sensing image reconstruction method based on the PCA redundant dictionary and the direction information mainly solves the problem that in an existing compressed sensing reconstruction method OMP, a reconstructed image under a blocking compressed sensing framework has blocking effect and fuzzy texture. The compressed sensing image reconstruction method based on the PCA redundant dictionary and the direction information comprises the following steps: constructing the PCA redundant dictionary; receiving measurement matrixes and blocking measurement vector quantities, and judging category of an image block to be reconstructed according to each blocking measurement vector quantity; designing a species group initialization scheme and a sequencing cross operator based on the direction information on each image block to be reconstructed, and using a genetic algorithm and a clone selection algorithm to achieve reconstruction of each image block under the PCA redundant dictionary. Compared with an OMP method, the compressed sensing image reconstruction method based on the PCA redundant dictionary and the direction information has the advantages of being capable of seeking an optimum sparse representation of each image block from the overall situation under the PCA redundant dictionary, clear in texture and edge of the reconstructed image, and capable of being used for acquiring a high quality image in the process of reconstructing images under the blocking compressed sensing framework.

The present invention provides a method and a system for filtering spam, characterized in that the method includes the following steps: a usage pattern in training data is mined out by adopting a data mining method in spam detection to establish an autogenous pattern set and an alien pattern set and to define attributes in the pattern sets; then, digitalized representation is adopted to map phenotype into genotype, which is a coding process; then, a negative selection algorithm and a clonal selection algorithm are combined to produce new antibodies so as to perform detecting and filtering on the spam, thereby reducing cost of mail filtering and improving efficiency of an intrusion detection system.

The invention relates to an industrial cloud data safety automatic production line based on the dynamic clonal selection algorithm, especially to an industrial automatic production line with industrial cloud data safety storage and high-efficient calculating framework based on dynamic clonal selection algorithm. Bulk production data acquired from an industrial site are packed and input to a cloud data center, and improved data safety protection based the dynamic clonal selection algorithm is applied in a memory block. When a calculating block extracts corresponding stored data according to a user's request, only the request is sent to a control node to extract corresponding data self sets which enter into the memory block to be matched. For external access, read and write of data are allowed after passing authentication if the obtained data self sets completely match with the self sets memorized in a memory block server. Memory detector matching is conducted if the previous matching process fails, data access is allowed if the memory detector matching succeeds, otherwise, a routine detector detection is started.

The invention relates to an artificial immunity intelligent optimization system facing the geographical space optimization, which comprises an immune operator library, a problem application library and an application platform module. The immune operator library is used for storing immune operator plugins; the problem application library is used for storing application plugins for solving the space optimization problem; the application platform module is used for calling the corresponding immune operator plugins from the immune operator library according to the selection of a user to determine a clonal selection algorithm and calling the corresponding application plugins from the problem application library to determine an antibody code and an affinity evaluation function of the specific space optimization problem to be solved of the user; and according to the determined antibody code and affinity evaluation function, the optimal solution of the specific space optimization problem to be solved of the user is acquired by the clonal selection algorithm. The artificial immunity intelligent optimization system provided by the invention can integrate the clonal selection algorithm which is currently and most widely used in the field of geoscience, and has universality, expandability and openness.

The invention provides a clonal-selection-based method for positioning a subpixel of a high spectrum remote sensing image. Subpixel positioning of the high spectrum remote sensing image is realized on the basis of a clonal theory and a subpixel positioning theory. By using a clonal selection optimizing algorithm, optimal calculation is performed on remote sensing image subpixel positioning without any future knowledge, and a result of subpixel positioning can be directly obtained according to an input image. Meanwhile, as the clonal selection algorithm has the advantages of self-learning and self-memorizing, the global optimal subpixel positioning result can be obtained.

The invention relates to a fuzzy job-shop scheduling method based on self-adaption inheritance and the clonal selection algorithm. The method includes the steps of determining the coding scheme of the fuzzy job-shop scheduling problem, generating the initial population N at random, defining a solution space, defining and calculating the adaptability function of an individual, conducting clone proliferation operation on the individual according to the size of the adaptability value near each generation of optimal solution, independently conducting self-adaption cross and mutation operation on individuals obtained through reproduction, conducting clonal selection operation on the individuals obtained through cross and mutation to generate the new population N*, ending the circulation if the ending condition is met, and returning to continue the next step if the ending condition is not met. By means of the method, resources can be more reasonably distributed, the completion time of job-shop scheduling fuzziness is shortened, the efficiency of job-shop fuzzy scheduling is improved, and the requirement of actual production scheduling is better met.

The invention relates to a method for grading land resource evaluation factors based on the clonal selection algorithm, which makes full use of the advantages of the clonal selection algorithm in optimization problem solving and introduces the clonal selection algorithm into evaluation factor grading problem. According to the characteristics of the evaluation factor grading problem, a clonal selection algorithm affinity function and constraint conditions are designed, and a clonal selection algorithm model suitable for evaluation factor grading is constructed. The method provided by the invention can provide scientific and accurate basis for factor impact analysis for land resource quality evaluation, and further provides technical support for rational utilization of land resources.

The invention relates to a power system load modeling parallel computing method based on an electric energy quality monitoring system. According to the method, the electric energy quality monitoring system acquires the disturbance data of a power grid, and an improved clone selection parallel computing algorithm is used for performing parallel computing identification processing on a model; and the fitting condition of the output power of the model with actually-measured load power is checked under different failure conditions, and a Mifare (MI) card and a fitting curve are output according to a Bonneville power administration (BPA) motor model. The electric energy quality monitoring system is used for acquiring the data, and the improved clone selection parallel computing algorithm is used for identifying load model parameters, so that the method has the characteristics of high identification accuracy, global convergence, high running speed and fitting real-time performance, and is applied to practical engineering application; high scalability and a high speed-up ratio are realized according to actual needs; the timeliness and usability of a load modeling process are improved; and the running efficiency of a software platform for load modeling operation under complex conditions is improved to a great extent.

The invention relates to a network load on-line modeling method based on a PMU load characteristic, comprising the following steps of 1) carrying out identification on a load test point of a wide area control protection system and a parameter of modifying a clone selection algorithm; 2) determining the load test point and carrying out a dynamic simulation test on a PMU device, and perfecting an electric power simulation software system according to the parameter of modifying the clone selection algorithm; 3) carrying out an artificial scene disturbance test according to the load test point and the result of the dynamic simulation test, so that the load modeling identification source data in a practical system are obtained; and 4) obtaining a comprehensive load model through combining load dynamic and static models according to the load modeling identification source data, converting the comprehensive load model into a load model of the electric power simulation software system, and carrying out checking. Compared with the prior art, the method has the advantage that the simulation precision is improved.

The invention discloses an SQL injection attack detection method based on a dynamic clonal selection algorithm. The method comprises the steps of extracting SQL statements submitted by a client browser and submitting the SQL statements to a rule base detection module for SQLIAs (SQL Injection Attacks) rapid mode matching; submitting the statements with unsuccessful mode matching to a dynamic detection module for deeper detection, introducing a local outlier factor as a fitness function for optimization of the distance between detectors before the dynamic detection module is operated, and constructing efficient detectors to identify normal data and abnormal data; operating the dynamic detection module to carry out detection; calling a clonal selection algorithm to carry out learning and identification; and updating system modules according to a detection result. The problem that the detection performance of an existing WAF (Web Application Firewall) is reduced and unknown features and various deformation attacks cannot be identified is solved.

The invention relates to a line feature simplification method based on the clonal selection algorithm. The clonal selection algorithm is used for solving the line feature simplification problem by fully using the advantage of optimization-problem solving of the clonal selection algorithm; according to the characteristic of line feature simplification problem, the affinity function and the constraint condition of the clonal selection algorithm are designed, and a clonal selection algorithm model applied to the line feature simplification is constructed; the local search algorithm and the clonal selection algorithm are combined and the global search capacity of the clonal selection algorithm and the local optimization capacity of the local search algorithm are fully utilized so that the line feature simplification precision and algorithm are improved. The invention provides a new thinking direction for promoting the line feature simplification technique system to develop automatically and intelligently and enriches related research content and methods. The research results provide important theoretical guidance and technical support for the cartographic generalization of actual production.

The invention discloses an analogue circuit fault diagnosis method based on an improved type clone selection algorithm. The method includes the first step of canceling the decision rules that an original decision algorithm determines which diagnosis radiuses faults belong to based on experience, and adopting the minimum Euclidean distance as a diagnosis decision condition, the second step of modifying an affinity calculation formula and utilizing a formula f=1/(1+d) to replace an original formula f=1/d so as to prevent overflowing in calculation and standardize the affinity within a fixed range of (0,1], and the third step of modifying an overall affinity calculation mode and utilizing an average value expression method of the affinity of all individuals in a species group to replace a sum expression method of the affinity of all the individuals in the species group. Through the first step, failure switch-off can be eliminated, false switch-off and excessive switch-off can be reduced and the fault diagnosis rate can be improved. Through the second step, calculation is convenient and the comparability of the affinity is higher. The improved type clone selection algorithm is applied to analogue circuit fault diagnosis and has superior performance.

The invention discloses an industrial product surface defect detection method based on FCN+FC-WXGBoost. The method comprises the following steps: 1) performing size standardization and normalization operation on a picture; 2) carrying out online enhancement and batching on the picture; 3) sending the picture to a network combining a full convolution network (FCN) and a full connection network (FC)for training; 4) taking the input of an output layer of the full connection network as a feature vector, training a WXGBoost classification model, using a clone selection algorithm to carry out automatic parameter adjustment, replacing an output layer of a full connection layer with WXGBoost, and combining with a full convolution network FCN to obtain an FCN+FC-WXGBoost network model; 5) during detection, inputting the picture into the FCN+FC-WXGBoost network to obtain the position and category information of the defect. According to the method, the influence of conditions such as illumination, exposure and displacement on defect detection is effectively reduced, the defect detection stability is improved, the influence of defect category imbalance on the detection precision is reduced, and the detection precision is improved.

The invention discloses a steel production energy consumption immune prediction control model. The energy consumption immune prediction control model basing on rough set-immune prediction control is built, a rolling optimal method is achieved by utilizing a clonal selection algorithm, and an equation and an inverse matrix for solving Diophantine are avoided. A nonlinear autoregressive moving average model is adopted directly in a prediction model. The nonlinear autoregressive moving average model is adopted according to controlled members by basing on an immune feedback adjustment principle, feedback errors are controlled to be optimal performance indicators, the rolling optimal method is achieved by utilizing evolutionary computation based on immune clone, a prediction controller based on immune parameter identification is designed, the equation and the inverse matrix for solving the Diophantine are avoided, relative gain parameters and lag time parameters are optimized on line, and the influences of model errors to system control are reduced.

The invention provides a novel torque motor structure parameter optimization method, and belongs to the field of motor intelligent optimization design. A finite element analysis system is used for conducting modeling and torque analysis on introduced structural parameters to replace traditional motor mathematical model analysis and calculation, so that errors of calculating results are small, and the accuracy is high. A weight value changing immune clonal selection algorithm is provided, after a weight value changing mechanism is used, the weight between single objective functions can be continuously adjusted along with operation of the algorithm, wherein the weights of the single objective functions close to the design demand can be changed to be small, and the weights of the single objective functions deviating from the design demand can be continuously increased. Accordingly, the convergence rate of the algorithm is increased, a large amount of unnecessary optimizing time is saved, and the optimization result is obtained more quickly. In addition, the algorithm can effectively keep the diversity of a population, global searching and local searching can be achieved simultaneously, early-maturing of evolution and falling into local minimal values of searching can be prevented, and complex non-linear problems can be solved.

The invention relates to an image compression method based on wavelet transform and clonal selection algorithm. The image compression method based on the wavelet transform and the clonal selection algorithm comprises the following steps of: 1) an image data acquisition module collects external image information and sends the external image information to a LVDS (low voltage differential signaling) to TTL (transistor-transistor logic) module; 2) the LVDS to TTL module carries out signal transformation to the collected image information; 3) a synchronous FIFO (first in first out) module stores an image signal converted by the LVDS to TTL module to a SDRAM (synchronous dynamic random access memory) image cache module; 4) an FPGA (field programmable gate array) image data compression module carries out compressed encoding processing to pre-processed image information in the SDRAM image cache module; and 5) an image display module displays image information which is coded and compressed again in the FPGA image data compression module. According to the image compression method based on the wavelet transform and the clonal selection algorithm, which is disclosed by the invention, the image compression efficiency is improved, and the coding quality is high.

The invention relates to a load model parameter identification method based on a clone selection algorithm. According to the load model parameter identification method based on the clone selection algorithm, parameters to be identified serve as an antigen, an objective function of the parameters serves as an antibody, the maximum affinity between the antibody and the antigen serves as the objective, and a set of optimal load model parameters are obtained. Compared with the prior art, the load model parameter identification method based on the clone selection algorithm is good in optimal performance and robustness, and has good parallelism and operability; due to the fact that searching is carried out in a whole solution space to find more optimal individuals, the phenomenon that due to the fact that individuals with high fitness are in mass propagation in the later period of evolution, and fill the whole solution space, optimization stops on a local optimal solution is avoided.

The invention discloses a method for obtaining harmonic parameters on the basis of a clonal selection algorithm and improved fast S transformation. The method comprises the following steps that signals are subjected to improved fast S transformation; the number, the frequency, the amplitude value and the phase parameter of harmonic ingredients in the tested signals can be obtained according to a result matrix of the improved fast S transformation; the result matrix of the improved fast S transformation is subjected to linear decomposition; the reverse fast S transformation is used for rebuilding a time domain waveform of each harmonic ingredient; the detected frequency value of each harmonic ingredient is modified; a time domain model of each harmonic ingredient in the tested signals is built according to the detection information; the detected amplitude value and the phase information of the harmonic ingredients are corrected by using the clonal selection algorithm. The clonal selection algorithm and the improved fast S transformation algorithm are adopted, the advantages of high detection precision, high convergence rate, high searching capability and the like are realized, and various parameters in the harmonic ingredients can be extracted from complicated distortion signals.

The invention discloses an image retrieval method based on memetic algorithm, and relates to shape-based image retrieval. The image retrieval method comprises setting parameters; generating an initial population; calculating antibody affinity; cloning; executing clonal variation based on probability; performing clonal selection; recombining; subjecting the antibody to local search operator optimization based on simulated annealing algorithm; optimizing superior antibodies by using a local search operator (1) and a local search operator (2); and repeating the operations to realize rapid and effective image retrieval. By combining the clonal selection algorithm with the local search operators, the image retrieval method provided by the invention has high global search capacity, high convergence rate and high image retrieval efficiency. The local search operators with high local search capacity can further improve the retrieval result of the clonal selection algorithm so as to improve the accuracy of the image retrieval results. In addition, the method can overcome the difficulty in determining the number of classes by using a coding method based on class marks. Based on the advantages of high efficiency and high accuracy, the image retrieval method provided by the invention can be used for retrieving and classifying network pictures.