30 results about "Negative selection algorithm" patented technology

The invention discloses a cyberspace security situation real-time detection method. The method comprises the following steps: original characteristic extraction that original network data packet characteristics are obtained from a network, multi-scale entropy calculations that sample entropy of an original data packet characteristic sequence is calculated at different time scales, detector training that a mature immunization detector is trained and generated by utilizing a sample entropy characteristic vector and a negative-selection algorithm at the different time scales, network threat security detection that a network sample is detected by utilizing the trained mature immunization detector at the different time scales, cyberspace security situation calculations that cyberspace security situations at the different time scales and different network layers, and situation visualization that the cyberspace security situations are expressed by different colors of curve charts at different time and the different network layers. The time scales considered in the method is relatively comprehensive, the fusion level is high, a situation assessment result is relatively accurate, a complex characteristics of a network behavior can be described, and the whole process of a network threat behavior can be carved in a fine-grained manner.

The invention discloses a vibration fault detection system and method for wind turbine generator units. Vibration data, including vibration data of front and rear bearings of a gearbox and vibration data of front and rear bearings of a generator, of all parts of the wind turbine generator units are collected through vibration collection nodes by setting up a wireless sensor network, routing nodes passing through all the units are transmitted to a network coordinator node in a multi-hopping mode and transmitted to a monitoring center in the distance through 3G, optical fibers and an etheric multifunctional network, and a negative selection algorithm based on mahalanobis distance is adopted for the monitoring center to achieve remote detection early warning of fault units and fault parts. The vibration fault detection system for the wind turbine generator units comprises the monitoring center, a detection terminal, a database server, the multifunctional network, the network coordinator node, the routing nodes and the vibration collection nodes. According to the system and method, efficiency of the algorithm is improved, the accuracy rate of fault diagnosis is improved, a large amount of time is saved, and the larger the data size is, the more apparent superiority of the algorithm is.

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 embodiment of the invention provides a method for predicting field operation and maintenance faults of electric pow communication, which comprises the following steps: judging whether the field operation and maintenance real-time data exist abnormality or not through a negative selection algorithm based on a matrix form, based on the field operation and maintenance real-time data and a presetdetector set; If the real-time operation and maintenance data are abnormal, the real-time operation and maintenance data are inputted to the fault prediction model, and the fault prediction result isoutputted, and the fault is checked based on the fault prediction result. The detector set is composed of several detectors which are selected by negative selection algorithm based on matrix and are based on normal sample data of field operation and dimension. The fault prediction model is based on the field operation and maintenance fault sample data and the field operation and maintenance faultsample data of the fault type training. The method provided by the embodiment of the invention solves the problem that the existing algorithm needs to process a large amount of data, reduces the performance requirements of the controller, and improves the prediction efficiency and prediction accuracy.

The invention belongs to the technical field of underwater robots, in particular relates to a method for diagnosing faults of the sensor of an underwater robot. The method comprises the steps: setting the number of detectors with the effective maximal circulation times; setting threshold values; judging whether the maximal circulation times are achieved or not; generating a detector; collecting and comparing the normal status signal of the detector; judging whether a faulted effective detector set is full or not; comparing the detector with a known fault set; and judging known fault memory effective detector set. According to the method, fault detection and diagnosis are performed on the fault diagnosing system of sensor of the underwater robot, real number coding is adopted, and the unsafe state of the sensor is calculated and judged by utilizing Euclidean distance, so that the defects that the conventional negative selection algorithm has high rate of missing report, abnormal faults can not be effectively recognized, and the detection accuracy and applicability of the sensor of the underwater robot are improved.

The invention discloses a directory controller test excitation generation method based on a genetic algorithm. The directory controller test excitation generation method comprises the steps of S1, performing symbol coding of the genetic algorithm for test characteristics of a directory controller; S2, creating a primary population of test excitation, and selecting random chromosomes to add into the population based on a negative selection algorithm; S3, performing mutation operation to generate new chromosomes, and adding the new chromosomes into the population based on the negative selectionalgorithm; S4, performing crossover operation to generate new chromosomes, and adding the new chromosomes into the population based on the negative selection algorithm; and S5, repeating the step S3S4until the maximum genetic algebra is reached or chromosomes with fitness values greater than or equal to a set threshold appear. The relationship between the coverage rate and excitation input can bemined, generation of random test excitation is guided, new chromosomes are supervised and selected to be added into the population according to a negative selection algorithm, the least redundant test excitation is achieved, different coverage rate function points are covered as soon as possible, the test time is shortened, and the verification efficiency is improved.

The invention discloses a quick software and hardware division method used for guaranteeing quality. The quick software and hardware division method retains the crossover operation and the mutation operation of a genetic algorithm, imports a negative selection process of a negative selection algorithm and a strategy that a new individual is generated on the basis of allele concentration, and a novel evolution method is adopted to quicken an evolution process and guarantee the quality of the individual so as to overcome the defect of long time consumption of a traditional genetic algorithm and the defects that the negative selection algorithm is high in result randomness and is likely to fall into local optimum.

The invention discloses an active defense system and method based on biological immune. The system comprises a terminal, wherein the terminal is equipped with a known behavior library which is trainedthrough utilization of a cloud and is used for carrying out local detection and real-time monitoring on behaviors through utilization of a quasi-biological immune mechanism, wherein the behaviors aregenerated based on internal and external data, and the terminal is also used for carrying out first-level active defense, and sending unidentified unknown behaviors to the cloud; and the cloud, wherein the cloud is equipped with the known behavior library which is trained through utilization of the cloud, and the cloud is used for collecting the unknown behaviors sent by the terminal, importing deep learning, carrying out cloud detection and behavior early warning, pushing new behaviors to the terminal in real time and carrying out second level-defense. According to the system and the method,on the basis of the quasi-biological immune mechanism and an improved NAS negative selection algorithm, unsecure computer behaviors can be actively identified, prevented, traced and checked, and integrated defense and active defense of a cloud-terminal cooperative computing environment is realized.

The invention discloses an equipment fault diagnosis method based on an improved negative selection algorithm of a particle swarm algorithm, and the method comprises the steps of constructing a hash value character string self-set P1 formed by a, b and c strings and a to-be-detected string D1 through the frequency change trend of m points of an equipment current amplitude; constructing a hash value character string self-set P2 and a to-be-detected string D2 formed by 0 and 1 strings according to the relationship between the standard deviation of the m-point data and the standard deviation of all the data, generating a detector A and a detector B by a particle swarm algorithm, and calculating the distance between the to-be-detected string D1 and each sub-string of the detector A and the distance between the to-be-detected string D2 and each sub-string of the detector B in a Hamming distance mode; and obtaining an optimal value by generating each round of iteration of a particle swarm algorithm constructed by different substrings so as to solve detector overlapping and cross vulnerabilities. According to the method, the problem of loss caused by sudden failure of equipment in enterprise production can be well solved, and the problem that valuable equipment has no abnormal data and can be compared and analyzed can be well solved, so that the production can be better served.

The invention relates to an email binary classification algorithm based on active learning and negative selection. The email binary classification algorithm is characterized in that user bidirectionalinterest sets are first established according to marked email sets; an email binary classification algorithm is constructed by using an abnormal detection mechanism in a negative selection algorithm,and to-be-classified email sets serve as self-sets to perform matching detection; finally email classification results are obtained by using matching results, and the user bidirectional interest setis updated; an active learning method and the negative selection algorithm are applied to spam filtering, the to-be-classified email sets serve as the self-sets, user positive and negative interest sets constructed from existing labeled email sets serve as detectors, all email key feature sets screened by a key feature selection algorithm serve as classified objects, and finally classification results of the email sets are obtained through an anomaly detection matching mechanism. The algorithm performs bidirectional binary matching detection on the email sets through positive and negative interest sets, and a new idea is provided for the spam filtering method.

The invention provides a neighborhood morphological space artificial immunodetector multi-source generation algorithm, and belongs to the technical field of artificial intelligence immune systems. Theneighborhood morphological space artificial immunodetector multi-source generation algorithm uses a neighborhood morphological space, improves a neighborhood negative selection algorithm, and introduces a chaos theory and a genetic algorithm to form the detector multi-source generation algorithm, thereby solving the problems of each algorithm of a detector in a real-value morphological space.

The invention provides a keystroke motion identification method based on cosine similarity, which relates to the field of network safety based on negative selection algorithm. Based on the keystroke dynamics, the biological immunization process can be simulated by means of the negative selection algorithm. Through the abstractness of immune cells, non-self detection can be completed by the detector, and the aim of distinguishing truth from falsehood can be achieved. The invention is advantageous in that the keystroke dynamics is applied, and with multiple attributes, the bottleneck of the negative selection algorithm in a high-dimensional space can be broken through; the high-dimensional negative selection algorithm has great advantage in the self recognition and non-self recognition in the complicated compound application scene.

The invention discloses a wireless sensor network fault diagnosis method based on an improved negative selection algorithm, and relates to the technical field of wireless sensors. The method comprises the following steps: step 1, analyzing and researching an NSA principle to find an improvement point of an algorithm; 2, researching a WSN fault node detection method; 3, researching a WSN fault classification method; 4, performing verification and comparative research on the algorithm by using simulation software. According to the method, the fault detection accuracy is improved, and the time and energy consumed in the detection process are reduced, time can be saved, and rapid detection is facilitated.

The invention discloses a data classification method based on a self-set density search and clustering detector-negative selection algorithm (DSC-NSA). The method comprises the following steps: 1), according to a density peak of a data set, calculating a cluster center and deleting noise; 2), according to a non-noise self-sample, generating a self-detector; 3), according to the self-detector, generating a non-self detector; and 4), determining whether a detection data sample is abnormal by simultaneous use of the self-detector and the non-self detector so as to realize data classification. The data classification method based on the self-set DSC-NSA, provided by the invention effectively eliminate influences of noise and is quite small in time cost and quite low in misjudgement rate.

The invention discloses a method for deploying component services for a data-intensive service cooperation system. By the method, the component services are optimally deployed by the aid of a multi-object optimization algorithm on the basis of negative selection. The method includes mapping the component service deployment on the basis of data-intensive service cooperation into a negative selection algorithm, mapping a single deployment scheme of each single component service into a gene, mapping a deployment scheme of all the component services as an antibody and creating all possible genes to form a gene library; sequentially iteratively matching antibodies on the basis of a negative selection process and circularly iteratively matching the antibodies repeatedly to finally obtain antigens, and using the deployment schemes corresponding to the certain antibodies as the optimal deployment schemes. The method has the advantages that in each iteration procedure, a certain quantity of antibodies are generated by means of gene recombination at first, antibody groups are formed, then low-quality antibodies in the antibody groups are eliminated by means of negative selection, and accordingly search space is reduced; a gene warehouse is updated according to an iteration result after each iteration procedure is completed, so that optimal antibodies can be assuredly generated by means of gene recombination in each follow-up iteration procedure.

The invention belongs to the technical field of image processing, and particularly relates to an infrared target detection and tracking integrated algorithm based on extension immunity. In the algorithm, a negative selection algorithm and a KCF tracking algorithm are improved by applying an extension theory, an infrared target detection module and a tracking module are redesigned, and target center position information of the detection module is sent to the tracking module, so that integration of infrared target detection and tracking is realized.