58 results about "Immune network" patented technology

The invention discloses a mobile robot path planning method, which comprises the following steps of: A, determining a moving destination of a robot, and setting the number of sensors of the robot and the number of directions towards which the robot can move; B, detecting the environmental information of the surrounding by using the robot; C, defining a mapping relationship between the path planning method and an artificial immune network; and D, resolving the maximum concentration of the artificial immune network and determining an antibody corresponding to the maximum concentration as the moving direction of the robot. The mobile robot path planning method of the invention has the advantage of reaching a destination point under a complex obstacle environment with the local minimization problem, and is feasible and effective under the complex obstacle environment. Simulation results obtained under the U-shaped obstacle environment further show the high efficiency of planning results obtained by the method of the invention under the complex environment.

The invention provides a polyclone artificial immunity network algorithm for multirobot dynamic path planning, and relates to an improved polyclone artificial immunity network algorithm. According to the polyclone artificial immunity network algorithm, a polyclone artificial immunity network is applied to multiple mobile robot dynamic path planning, mutual influence among robots and influence on the robots of mobile barriers are considered, a computational formula of antibody concentration is defined, diversity of antibodies is increased through clonal operators, crossover operators, mutation operators and selection operators, and the problem of premature convergence of a traditional immune network is solved. Specific antibodies corresponding to antigens in a specific environment are stored, initial concentration of the specific antibodies is increased, response time is shortened, and multiple mobile robot dynamic path planning in an unknown environment is effectively achieved.

The invention is applicable to the field of internet information safety and provides an immunological network system. The system comprises a transparent firewall, an intelligent inspection device and an emergency device, wherein the transparent firewall is used for analyzing and extracting the scan features and preventing external network scanning; the intelligent inspection device is used for monitoring the flow which enters the network, extracting the attach fingerprint features according to the abnormal flow and storing the attach fingerprint features into an immunological feature library; and the emergency device provides an emergency channel for the damaged internal network nodes detected by the intelligent inspection device and prompts the user to reduce the damaged nodes to the safety state before attack after the operation of the user is finished. The network flow is monitored and audited, the good state of the network is maintained, the unknown intrusion behavior is analyzed and memorized, the network immunity is improved, the damage range can be effectively controlled after intrusion, the unimpeded network service can be normally provided, the system has the self-restoring and reducing capacity, and the stable operation of the network is comprehensively maintained.

The invention relates to a virus detection system and method for an immune network under a cloud computing environment, and belongs to the technical field of network security. The virus detection system comprises a cell bank consisting of different types of immune cells, a MapReduce-based immune network module and a virus detection module based on a MapReduce immune network, wherein according to a MapReduce model, construction and dynamic balance of the immune network are decomposed into millions of sub programs; the split sub programs are submitted to the cloud computing environment consisting of a plurality of servers for processing, so that a memory detector is formed; and the servers in the cloud environment parallelly detect viruses in the cloud environment according to distribution of the memory detectors. The virus detection system is combined with the high data processing capacity of a cloud computing platform and the advantages of the immune network; by the virus detection system and the virus detection method, the detection efficiency of the detector can be effectively improved, the redundancy of the detector is reduced, the virus detection rate of the whole cloud computing environment is increased, and the security of the cloud computing environment is improved.

The invention discloses eye drops with the function of relieving the symptom of xeroma, which are characterized by comprising a recombinant human keratinocyte growth factor-2, a protein protective agent, a thickening agent, an osmotic pressure regulator and a proper buffer system in a certain proportion; the invention also discloses a preparation method of the eye drops. Pharmacological experiments show that the eye drops can delay the rupture time of the lacrimal film, maintain the integrity of the ocular barrier, restore the ocular immunological network and relieve the symptom of the xeroma by restoring the corneal epithelium.

The invention discloses a double-jump-based single mode matching method. The method includes adopting an improved Sunday algorithm to complete matching of intrusion mode strings therein; if characters are unequal in the process of character matching, continuously jumping two steps and then matching. By the method, matching efficiency of an intrusion detection system is improved greatly, detection speed of the detection system is improved, and instantaneity of the detection system is improved indirectly. The double-jump-based single mode matching method is wide in application range and can be applied to aspects like self-adaptive immune network intrusion detection system and network content auditing.

The invention discloses an artificial immune network clustering based grayscale image segmentation method, mainly aiming at solving the problems that the existing image segmentation technology is high in computation complexity and low in segmentation speed. The artificial immune network clustering based grayscale image segmentation method mainly comprises the following steps: (1) inputting a grayscale image to be segmented; (2) extracting the characteristics of the grayscale image to be segmented; (3) acquiring clustered data; (4) generating an initial antibody population randomly to realize initialization; (5) training optimally; (6) checking whether all antigens enter the network; (7) repeating the steps 5 and 6 for 100 times and ending the optimization training; (8) clustering; (9) generating a clustering result; and (10) outputting a segmented image. According to the artificial immune network clustering based grayscale image segmentation method, a watershed and the immune network clustering method are adopted to realize grayscale image segmentation, more image detail information is acquired, accurate region homogeneity and good edge retentivity are acquired, the segmentation speed is high, the overall segmentation precision is improved and the method can be applied to the technical field of natural grayscale image segmentation.

The invention provides a self-adaptive learning system based on an artificial immunization network, provides a structural model and an immune adjustment algorithm of the artificial immunization network, and belongs to the field of numerical control system fault diagnosis, wherein the self-adaptive learning system based on the artificial immunization network is designed for a numerical control machine fault diagnosis system based on multi-agent technology. The structural model of the artificial immunization network is confirmed; antibodies in the immunization network is generated according to the immune adjustment algorithm of antigenic similarity, and a memory antibody set (Nab) is obtained; and according to the inverse ratio property between immunization and distance, comprehensive immune response ability of each antibody in the network is obtained. The self-adaptive learning system suitable for resolving of complex problems has the advantages of avoiding local minimum, getting rid of limitation of expert experience and being high in algorithm speed and accuracy.

The invention belongs to the technical field of network information processing. The invention discloses a microblog social circle mining method and system based on an artificial immune network, and the method comprises the steps: carrying out the calculation of the similarity between users through the analysis of social information and interest information between the users, measuring the relationship strength between the users through the similarity, and carrying out the comprehensive description of the relationship strength between the users; And on the basis, constructing a microblog undirected weighted network taking the users as nodes and the relationship strength as weights, and removing edges with relatively low relationship strength in the undirected weighted network to obtain a microblog user similarity network. According to the invention, an artificial immunization method with relatively high adaptability and self-adjustability is adopted; A principle and an action mechanismof a biological immune network are applied to similarity clustering of microblog users, users with high relationship strength are divided together, and one user is allowed to belong to a plurality ofsocial circles at the same time during division, so that mining of overlapped social circles is realized.

The invention discloses an improved immune network abnormal behavior detection method. The method comprises four stages of autologous library data extraction, antigen presentation, abnormal behavior detection and clonal selection, wherein a single-category autologous data generation model based on deep belief network is adopted in the autologous library data extraction and antigen presentation; the deep belief network is formed by stacking restricted Boltzmann machines RBM; the RBM is a neural network; a method combining congenital immunity and adaptive immunity is adopted in the abnormal behavior detection; and a clonal variation method based on a generation network is adopted in the clonal selection. According to the improved immune network abnormal behavior detection method disclosed bythe invention, the deep learning model and method are introduced into a computer immune network anomaly detection model to improve the quality and efficiency of the model training, no matter the detection efficiency and the accuracy are greatly improved, and meanwhile, the defect that the traditional method is random or a large number of invalid calculations caused by cross variation are overcomeat the same time.

The invention discloses a data mining method combined with a multi-agent technology and an artificial immunity network. The typical strategy of the multi-agent technology is integrated into the immunity network. Neighborhood clone selection is introduced to an algorithm, the operation process is executed from the local part to the whole, and a natural evolution model of the immunity network can be simulated more comprehensively. Meanwhile, the competition and collaboration operation between antibodies is increased in the network training process, and the dynamic analysis capacity of the network is improved. By the adoption of the algorithm, in the data mining process, data clustering accuracy can be improved, and data classification accuracy can be improved as well.

To provide a new method for autonomously controlling the behavior of a control target device based on a stimulating action and a suppressing action among antibodies in an immune network, an operating unit 3 calculates an antibody concentration ai(t) serving as an index for selecting an antibody module ABi, while plural antibody modules ABi different in stimulating conditions are set as processing targets. A convergence judging unit 4 judges whether the antibody concentration ai(t) is converged to a predetermined target value ri. When a judgment of non-convergence is made, a convergence controlling unit 5 calculates a correction parameter ul(t) for correcting the antibody concentration so that the antibody concentration ai(t) approaches to the target value ri. When a judgment of convergence is made, an antibody estimating unit 7 calculates an estimation value Pi, and selects some antibody module ABi based on the estimation values Pi calculated for the plural antibody modules. The behavior of the control target device is controlled in accordance with a control content defined by the selected antibody module ABi.

The invention discloses a virus detection method based on a collaborative immune network evolutionary algorithm, and belongs to the technical field of network security. According to the method, detectors in the immune network are optimized continually through the mutual collaboration among various immune cells. The method introducing a non-self set in the evolutionary process, and performing clonal selection on mature detectors based on the detector fitness to the non-self set; simultaneously, updating mutation methods with mutation step size self-adaptation and capable of changing mature detectors through an evolutionary algebra through the evolutionary algebra, and raising a network inhibition strategy based on concentration partition, thus, the network cell diversity is improved, and the redundancy rate of detectors is reduced simultaneously. According to the virus detection method based on the collaborative immune network evolutionary algorithm, advantages of the evolutionary algorithm and the artificial immune technology are combined and fully used, and the network virus detection efficiency is improved.

The invention belongs to the Internet field and provides an immune network system. The immune network system comprises a transparent firewall, an intelligent tour-inspection device and an emergency device, wherein the transparent firewall is used for analyzing the present network scanning technology, extracting universal scanning features and taking the universal scanning features as filtering rules for filtering; the intelligent tour-inspection device is used for auditing and monitoring flow entering the network, offering abnormal flow treatment proposals, communicating with a host computer generating abnormal flow, extracting features of attack fingerprints and saving the attack fingerprints in an immune feature library; the emergency device is used for providing an emergency channel for detected damaged intranet nodes and reminding a user of restoring the damaged nodes to the safe state before attacking after the user completes work. According to the invention, the network flow is monitored and audited to keep the network in a good state, unknown invasion actions are analyzed and memorized to improve the network immunocompetence, the hazard range can be effectively controlled after invasion to guarantee network connection and normal service providing, and the system has an autonomous remediation and restoration capacities and can comprehensively maintain stable network operation.

The invention discloses organic rice flour capable of enhancing immunity of infants. A formula comprises organic rice, glucose, hawthorn, salt-processed fructus alpiniae oxyphyllae, medlar, pine nut, composite vitamins and composite minerals. The organic rice flour disclosed by the invention has the advantages that a biological enzymolysis technology is utilized for improving the degree of gelatinization of rice starch, the problems of shortage of enteral amylase of the infants and indigestion caused by intake of non-gelatinized starch can be effectively solved, and the digestive absorption index can be obviously improved in comparison with a traditional rice flour processing technology. An extract of the medlar contains lycium barbarum polysaccharides, has the effect of promoting humoral immunity, cellular immunity and erythrocyte immunity, and can promote the function exertion of mononuclear macrophages, NK (natural killer) cells, plaque forming cells, dendritic cells and cell factors and play a positive role in receptor expression, signal conduction and a nerve-endocrine-immune network.

The invention discloses a method for optimizing an integrated circuit of an analog operational amplifier. The method has the advantages that according to the principle and requirement of an analog integrated circuit to be designed, the method can automatically design technical parameters and circuit parameters free from design parameters and the number of optimized targets by applying an intelligent optimized searching method of a Q-deviant immune network, can automatically search and find the optimal technical parameters and circuit parameters meeting the requirements of analog circuit performance indexes in a range of set values, namely meeting the requirements of high direct current gain, unit gain bandwidth, conversion velocity and low power consumption, and provides good foundation and accordance for high-performance analog integrated circuit technological design. Furthermore, the method is applicable to various analog circuit designs, is easy for transplanting, and has wide applicability and high universality.

The invention belongs to the technical field of an intelligent power grid, and discloses a power distribution network fault positioning method based on a hybrid immune algorithm. The method comprisesthe steps of screening fault source candidate nodes by means of an immune network method; if an obtained fault source candidate solution only comprises one node, outputting the fault source; and if aplurality of fault source candidate solutions are obtained, performing further diagnosis on the preliminarily determined fault subset by means of an immune algorithm, and determining the fault node. The power distribution network fault positioning method settles problems of relatively low accuracy and relatively low speed in power distribution network fault positioning in prior art and realizes atechnical effect of improving fault positioning speed and efficiency.

To provide a new method for autonomously controlling the behavior of a control target device based on a stimulating action and a suppressing action among antibodies in an immune network, an operating unit 3 calculates an antibody concentration ai(t) serving as an index for selecting an antibody module ABi, while plural antibody modules ABi different in stimulating conditions are set as processing targets. A convergence judging unit 4 judges whether the antibody concentration ai(t) is converged to a predetermined target value ri. When a judgment of non-convergence is made, a convergence controlling unit 5 calculates a correction parameter ul(t) for correcting the antibody concentration so that the antibody concentration ai(t) approaches to the target value ri. When a judgment of convergence is made, an antibody estimating unit 7 calculates an estimation value Pi, and selects some antibody module ABi based on the estimation values Pi calculated for the plural antibody modules. The behavior of the control target device is controlled in accordance with a control content defined by the selected antibody module ABi.

The invention relates to a mechanical fault diagnosis technology, in particular to a mechanical fault diagnosis method based on a collaborative mechanism immune particle swarm network. The problems that according to an existing mechanical fault diagnosis technology, requirements for the number of fault samples are high, and the diagnosis accurate rate is low are solved. The mechanical fault diagnosis method based on the collaborative mechanism immune particle swarm network includes the following steps that (1) mechanical fault samples collected by a sensor are taken as antigens; (2) appetencies between the antigens and antibodies of the immune network are calculated; (3) low-frequency variation and antibody recombination are performed on subgroup bodies A with large appetencies, particle swarm optimization and antibody recombination are performed on subgroup bodies B with small appetencies, and therefore a new antibody group is obtained; (4) the new antibody group is adjusted through the immune network; (5) the step (2), the step (3) and the step (4) are executed circularly; (6) the mechanical fault samples collected by the sensor are input into the new immune network. The mechanical fault diagnosis method is suitable for mechanical fault diagnosis.

The invention relates to a synergistic immunity detection method for a steam leakage of a steam trap of a tire vulcanizing machine based on a computer artificial system. The synergistic immunity detection method comprises the following steps: A: initialization of a computer host system is carried out; to be specific, (1) by establishing a dynamic baseline regression model between the steam level at the workshop level and the equipment level, a dynamic hazard baseline is generated, and a hazard threshold is set; (2) the state parameters of vulcanizing machine and the state parameters of steam pipe are used and the detector of leakage vulcanizing machine is generated by artificial immune network clustering; B: Synergistic immune detection method of computers running at each time is that the dynamic baseline regression model and the detector are performed synergistic immunity detection. The synergistic immunity detection method can accurately detect whether or not the steam leakage event exists in the steam trap of the vulcanizing machine; the omission rate and the error detection rate are respectively controlled at 2.62% and 5.26%, compared with the traditional device level state parameter detection methods, the omission rate rate and the error detection rate are reduced by 6.67% and 14.28% respectively.

The invention discloses a computer network fault diagnosis method, which is based on an artificial immune algorithm, and comprises the following steps of: defining category information for describingantigens and antibodies, and dividing collected network fault samples into a training antigen set and a test antigen set; normalizing the proportion of the training antigen set to obtain a non-memoryantibody, selecting a certain number of antigens as memory antibodies, and purifying the memory antibodies; calculating the affinity between the training antigen set and the memory antibody and the affinity between the training antigen set and the non-memory antibody; selecting a plurality of antibodies with the highest affinity for cloning to obtain a selection set, and mutating the cloned antibodies to obtain an antibody set; obtaining a total memory antibody set according to the training antigen set and the mutated antibody set; circularly selecting a next antigen; inhibiting the memory antibody; and detecting the category of the antigen. The advantages of self-learning and self-memorizing of the artificial immune network are utilized, the fault sample antigen is trained, the obtained memory antibody set has fault category information, and the accuracy of the algorithm is improved.

The invention relates to a behavior-based multi-UUV self-organizing coordination control method. The method comprises the following steps: 1, constructing a mapping relationship between an immune network and a multi-UUV system, and defining related parameters; 2, proposing a coordination control kinetic model based on basic behavior actions, and realizing fractional Brownian motion modeling of operation environment errors; and 3, giving immune network-based multi-UUV self-organizing coordination control in a discrete state to meet cooperative control for multi-UUV system under the distributedstructure and realize the entrapping operation on enemy targets. The method has the characteristics of strong self-organization, fault tolerance, real-time performance and the like, and is convenientfor engineering realization of the underwater unmanned system.

The invention discloses an orthogonal wavelet norm blind equalization method based on an artificial immune network, which includes the following steps: initialization: designing the initial antibody population; calculating the fitness value; cloning and variation: cloning and variation for each antibody; calculating Fitness value: For each clone, select the individual with the largest fitness value to form a new antibody population, and calculate the average fitness value of the population; compare the average fitness value of the population: if the average fitness value of this time is the same as the above If the value of the second iteration is different, go back to calculating the fitness value and perform the following operations; otherwise, continue to the next step; antibody suppression: calculate the affinity between antibodies, and compare the fitness of antibodies whose affinity is lower than the inhibition threshold, and eliminate the adaptation Antibodies with low density, the retained antibodies are used as memory cells of the network; diversity is introduced: if the iteration termination condition is not met, that is, the number of generations is cut off, antibodies are randomly generated and added to the original antibodies until the iteration is terminated.

The invention discloses a traditional Chinese medicinal acne removing composition used for being pasted on the navel. The composition is composed of the following components in parts by weight: 10-30 parts of kudzu vine roots, 8-15 parts of scutellaria baicalensis, 2-8 parts of coptis chinensis, 2-6 parts of cortex phellodendri, 1-2 parts of Chinese pulsatilla roots, 1-2 parts of rhizoma atractylodis and 3-6 parts of ash bark. The navel serves as one important part of the human body and has a good pharmaceutical effect absorption function. Local stimulation is realized on a navel position through compounding in a certain dose, various nerve endings on umbilicus skin can be in an active state, and a nerve-body fluid-internal secretion-immune network is regulated through nerve reflex, so that the effect of removing acnes can be achieved without directly smearing the composition on the face.

The invention provides a traditional Chinese medicine composition for treating the acute exacerbation of bronchial asthma. The traditional Chinese medicine composition is subjected to prescription according to monarch, minister, adjuvant and conductant, wherein achyranthes root and earthworm together serve as monarch drugs, cicada slough, ossa draconis, oyster, turtle shell and white peony root together serve as ministerial drugs, thunberbg fritillary bulb, amethyst, figwort root, radix asparagi, rhizoma anemarrhenae, turtle shell, white peony root, toosendan fruit and raw malt serve as adjuvant drugs, and licorice serves as a conductant drug. The traditional Chinese medicine composition fully prepared according to the prescription has the efficacies of endopathic wind calming, asthma relieving and wheeze stopping. Shown by modern medicine, the bronchial asthma is a typical psychosomatic disease, and the liver occupies an important position in the psychosomatic medicine of the traditional Chinese medicine and plays a crucial role in a nerve-endocrine-immune network, so that the treatment for the bronchial asthma from liver not only is in accordance with the theory of traditional Chinese medicine, but also has the scientific basis of the modern medicine, and is one of the important methods for treating the asthma. The traditional Chinese medicine composition provided by the invention has the advantages that the excessive and contrary liver Yang can be excellently calmed, the strong and contrary liver wind can be relieved, and the acute contraction of a lung tube is slowly spread, so that the acute exacerbation of the asthma is quickly eased, and no adverse reaction occurs; and the effective percentage is 80%.

The invention discloses a target identification method of a remote sensing image of an artificial immune network based on a self-adaptive PSO(Particle Swarm Optimization), mainly overcoming the disadvantages of low target identification precision and low convergence speed in the traditional method. The identification method comprises the following steps of: firstly, extracting 7 invariant moment characteristics of an image target and carrying out normalization treatment on the characteristic data; secondly, setting running parameters, selecting a training sample and initializing an immune network and immune cells; thirdly, calculating the affinity degree of the immune cells and cloning the immune cells; fourthly, executing hyper-mutation operation based on the self-adaptive PSO; fifthly, selecting an immune cell with highest affinity degree and adding the immune cell into the immune network; sixthly, carrying out network inhibition operation; seventhly, judging a stop condition, turning to the eighth step eight if the condition is satisfied, and otherwise, and otherwise jumping to the third step; and eighthly, inputting characteristic values of the remote sensing images which are not used as training samples into the immune network, and judging a category attribute value of each image by the immune network. The method has the advantages of high target identification accuracy and stable target identification performance and can be used for solving the problem of target identification of a remote sensing image set.

The invention provides a traditional Chinese medicine composition for treating the acute exacerbation of bronchial asthma. The traditional Chinese medicine composition is subjected to prescription according to monarch, minister, adjuvant and conductant, wherein achyranthes root and earthworm together serve as monarch drugs, cicada slough, ossa draconis, oyster, turtle shell and white peony root together serve as ministerial drugs, thunberbg fritillary bulb, amethyst, figwort root, radix asparagi, rhizoma anemarrhenae, turtle shell, white peony root, toosendan fruit and raw malt serve as adjuvant drugs, and licorice serves as a conductant drug. The traditional Chinese medicine composition fully prepared according to the prescription has the efficacies of endopathic wind calming, asthma relieving and wheeze stopping. Shown by modern medicine, the bronchial asthma is a typical psychosomatic disease, and the liver occupies an important position in the psychosomatic medicine of the traditional Chinese medicine and plays a crucial role in a nerve-endocrine-immune network, so that the treatment for the bronchial asthma from liver not only is in accordance with the theory of traditional Chinese medicine, but also has the scientific basis of the modern medicine, and is one of the important methods for treating the asthma. The traditional Chinese medicine composition provided by the invention has the advantages that the excessive and contrary liver Yang can be excellently calmed, the strong and contrary liver wind can be relieved, and the acute contraction of a lung tube is slowly spread, so that the acute exacerbation of the asthma is quickly eased, and no adverse reaction occurs; and the effective percentage is 80%.

The invention is applicable to the field of internet information safety and provides an immunological network system. The system comprises a transparent firewall, an intelligent inspection device and an emergency device, wherein the transparent firewall is used for analyzing and extracting the scan features and preventing external network scanning; the intelligent inspection device is used for monitoring the flow which enters the network, extracting the attach fingerprint features according to the abnormal flow and storing the attach fingerprint features into an immunological feature library; and the emergency device provides an emergency channel for the damaged internal network nodes detected by the intelligent inspection device and prompts the user to reduce the damaged nodes to the safety state before attack after the operation of the user is finished. The network flow is monitored and audited, the good state of the network is maintained, the unknown intrusion behavior is analyzed and memorized, the network immunity is improved, the damage range can be effectively controlled after intrusion, the unimpeded network service can be normally provided, the system has the self-restoring and reducing capacity, and the stable operation of the network is comprehensively maintained.

The invention discloses an improved immune network abnormal behavior detection method, including four stages of autologous database data extraction, antigen presentation, abnormal behavior detection and clone selection, characterized in that: the autologous database data extraction, antigen presentation Both adopt a single-category self-data generation model based on a deep belief network; the deep belief network is stacked by a restricted Boltzmann machine (RBM for short); the RBM is a neural network; the abnormal behavior detection A method based on the combination of innate immunity and adaptive immunity is adopted; the clonal selection adopts a method of clonal variation based on generative network. The present invention introduces the model and method of deep learning into the computer immune network anomaly detection model, improves the quality and efficiency of model training, greatly improves both detection efficiency and accuracy, and overcomes the randomness of traditional methods. Or the defect that cross-mutation leads to a large number of invalid calculations.