Immune response-based algorithm for optimization of dynamic environments

A novel immune algorithm suitable for dynamic environments (GIDE) is proposed based on a biological immune mechanism. GIDE models the dynamic process of artificial immune response with gradient-based diversity operators. Unlike traditional artificial immune algorithms, which require that randomly generated cells be added to the current population to explore its fitness landscape, GIDE uses a gradient-based diversity operator to speed up optimization in dynamic environments. Other immune algorithms are compared to GIDE by using Moving Peaks Benchmarks. Preliminary experiments showed that GIDE can maintain high population diversity during the search process, while simultaneously speeding up optimization. Thus, GIDE is useful for optimization of dynamic environments.

The article combines Fruit Fly optimization algorithm with Immune Optimization Algorithm into Fruit Fly-Immune algorithm to solve the multi-distribution center location problem with a NP-hard nature. Using MATLAB simulation technology and comparing to the simulation results of traditional Immune Optimization Algorithm shows that the use of Fruit Fly-Immune algorithm to solve multi-distribution center location problem can get better convergence results and weaken faster.

Intelligent control algorithms in dynamic multi-obstacle scenarios are prone to the problem of poor stability and reliability of their own motion. In order to solve the above core problems, firstly, the fuzzy set theory is used to adjust the three control parameters of PID control to realize the adaptive adjustment of the system when facing uncertain changes. Secondly, for the defects of fuzzy control summary time is too long, the immunity algorithm with excellent feedback is combined with fuzzy control to realize more accurate control of the controlled object with less summary time, which improves the efficiency and stability of the control system. Based on the generalized Routh criterion, the theoretical determination steps of the stability and convergence of the intelligent controller in this paper are given to provide a guarantee for the safe operation of the intelligent control system. The output trajectory oscillation range of the controller based on fuzzy immune PID algorithm designed in this paper is within -5~1, which is smaller than that of the traditional controller output trajectory. And the optimization algorithm in this paper has a very small error in tracking maximum power in a variety of local shading environments, and the oscillation range in dynamic environment is within 0.4W, which are smaller than the oscillation interval under the fuzzy control algorithm and immune algorithm alone. It shows that the optimized hybrid algorithm in this paper has important research significance for the development of intelligent control systems.

With the rapid development of science and technology, ultrasound has been paid more and more attention by people, and it is widely used in engineering, diagnosis, and detection. In this paper, an ultrasonic image recognition method based on immune algorithm is proposed for ultrasonic images, and its method is applied to medical ultrasound liver image recognition. Firstly, this paper grays out the ultrasound liver image and selects the region of interest of the image. Secondly, it extracts the feature based on spatial gray matrix independent matrix, spatial frequency decomposition, and fractal features. Then, the immune algorithm is used to classify and identify the normal liver, liver cirrhosis, and liver cancer ultrasound images. Finally, based on the deficiency of the immune algorithm, it is combined with the support vector machine to form an optimized immune algorithm, which improves the performance of ultrasonic liver image classification and recognition. The simulation shows that this paper can effectively classify the normal liver, liver cirrhosis, and liver cancer ultrasound images. Compared with the traditional immune algorithm, this paper combines the immune algorithm with the support vector machine, and the optimized immune algorithm can effectively improve the performance of ultrasonic liver image classification and recognition.

A novel immune algorithm is suggested for finding Pareto-optimal solutions to multiobjective optimization problems based on opt-aiNET, the artificial immune system algorithm for multi-modal optimization. In the proposed algorithm, a randomly weighted sum of multiple objectives is used as a fitness function, and a local search algorithm is incorporated to facilitate the exploitation of the search space. Specifically, a new truncation algorithm with similar individuals (TASI) is proposed to preserve the diversity of the population. Also, a new selection operator is presented to create the new population based on TASI. Simulation results on seven standard problems (ZDT2, ZDT6, DEB, VNT, BNH, OSY and KIT) show that the proposed algorithm is able to find a much better spread of solutions and better convergence near the true Pareto-optimal front compared to the vector immune algorithm and the elitist non-dominated sorting genetic system.

Based on the biological immune system, the authors propose a new immune population network algorithm which combines population immune algorithm and network immune algorithm in this paper. This algorithm could execute multi-point parallel search from local to global searching field, increasing the diversity of antigen population and the ability of searching maximum. At last, we apply this algorithm to the fault diagnosis system and simulation results indicate that the algorithm could recognize the fault correctly.

Customized bus is a kind of new type of public transport service which is tailor-made for the people whose travel has a similar location, time, destination and so on. In 2013, it has appeared in China and landed in various cities successively. But the development around the situation is different, the study about this problem is few. Based on the immune optimization algorithm and particle swarm optimization algorithm, combined with the advantages of genetic algorithm, the paper forms a hybrid immune optimization algorithm and hybrid particle swarm algorithm. Considering the custom bus station settings, line planning and other aspects, we take custom bus in Wuhan City, Hubei Province as an example, and try to give a scientific and practical guidance to the development of customized public transport nowadays, so that it can get a further theoretical and practical basis on mathematics in its development and operation.

To solve the real-time path planning of multi-robots in complex environments, a new immune planning algorithm incorporating a specific immune mechanism is presented. In the immune planning algorithm incorporating a specific immune mechanism, a new coding format for an antibody is first defined according to the impact of the obstacle distribution on the obstacle avoidance behaviors of multi-robots. Then, a new robot immune dynamic model for antibody selection is designed in terms of different impacts of obstacles and targets on robot behaviors. Finally, aiming at the local minimum problem in complex environments and inspired by the specific immune mechanism, a series of appropriate avoidance behaviors are selected through the calculation of a specific immune mechanism to help robots walk out of local minima. In addition, to solve deadlock situations, a learning strategy for the antibody concentration is presented. Compared with four related immune planning algorithms—an improved artificial potential field, a rapidly exploring random tree algorithm, a D* algorithm and a A* algorithm—the simulation results in four static environments show that the paths planned by immune planning algorithm incorporating a specific immune mechanism are the shortest and the path smoothness is generally the highest, which shows its strong planning capability in multi-obstacle environments. The simulation result in a dynamic environment with local minima shows that the immune planning algorithm incorporating a specific immune mechanism has strong planning ability in dynamic obstacle avoidance and in escaping from local minima. Additionally, an experiment in a multi-robot environment shows that two robots can not only avoid static obstacles but also avoid dynamic obstacles, which further supports the validity of the proposed immune planning algorithm incorporating a specific immune mechanism for multi-robots in real environments.

Using state assignment to reduce area and power dissipation is important for the design of sequential circuits. In this paper, a new approach of state assignment using immune algorithm (IA)is proposed. The goal of the proposed IA is to find the optimal state assignment with low area and power dissipation. The proposed IA hybrid the immune operator and local search. Local search is adopt to prevent the premature convergence and remain the diversity of the whole population. The traditional crossover and mutation operator has been modified. Compared with published research, the proposed IA obtains a better state assignment that saves area and power dissipation.

Aiming at affecting of the parameter selection method of support vector machine(SVM) on its application in blind equalization algorithm, a SVM constant modulus blind equalization algorithm based on immune clone selection algorithm(CSA-SVM-CMA) is proposed. In this proposed algorithm, the immune clone algorithm is used to optimize the parameters of the SVM on the basis advantages of its preventing evolutionary precocious, avoiding local optimum, and fast convergence. The proposed algorithm can improve the parameter selection efficiency of SVM constant modulus blind equalization algorithm(SVM-CMA) and overcome the defect of the artificial setting parameters. Accordingly, the CSA-SVM-CMA has faster convergence rate and smaller mean square error than the SVM-CMA. Computer simulations in underwater acoustic channels have proved the validity of the algorithm.

Both empty and heavy car flows should be taken into consideration in the study of the Optimization Model of Car Flow Organization, in the Loading End of Heavy Haul Railway. Firstly, through the analysis of empty and heavy car flow organization in the semi-closed heavy haul railway loading end, comprehensive optimization model based on ability of station and railway can be established in order to obtain car flow organization scheme with minimum residence time of both empty and heavy cars in the loading end. Secondly, immune clone algorithm is applied to solve the model in which the objective function is regarded as antibody and the constrained condition is considered as antigen to calculate the affinity, further to conduct the mutation, based on information entropy. Mutation is conducted according to the affinity. In the solving process, reproduction can be realized with the use of immune clone selection algorithm. Besides, premature convergence can be prevented by using the antibody concentration which can control the population size. Finally, simulation results show that the average search time of the proposed algorithm is reduced by 36 and 51% respectively compared with the GA and PSO.

A prediction method based on Extreme Learning Machines(ELM) is proposed. The parameters of ELM are optimized by immune optimization algorithm. The proposed model is used to predict the fiber quality of the melt spinning process. According to the limited samples, the spinning speed, the spinning temperature, the blowing speed and the blowing temperature of the melt spinning process are four key parameters that affect the fiber quality. The four indexes of polyester fiber are 1.5 times rate of elongation(EYS1.5), elongation inequality rate(EYSCV), breaking strength(DT) and elongation capacity(DE). We collect actual data samples in the factory and establish the ELM prediction model. The ELM model optimized by immune optimization algorithm (ELM-IA) is compared with PSO optimized ELM (ELM-PSO), ELM model and BP neural network. The experimental results show that the ELM-IA model is better than the ELM-PSO model, the ELM model and BP neural network in prediction. The ELM-IA model has a good generalization ability. It can play a guiding role in the actual fiber production process.

This paper presents an immune PI control that consists of immune optimization algorithm and PI control. Traditional PI control can’t quickly match variation of motor variables or load disturbance in permanent magnet synchronous motor since control parameters are discrete and off-line adjusted. Therefore, by designing target function, antigen affinity, antibodies affinity and mutation, the immune algorithm optimizes parameters and memory cells. The tests and the simulation with time-based Parameters demonstrate immune algorithm makes control strategy and has global optimization ability and strong robustness. Based on DSP technology and SVPWM algorithm, the system shows that immune PI control system can obtain stable situation in 50ms, have much improvement in dynamic and static performance.

We present an immune recognition algorithm for improving the performance of promoter regions prediction in this paper. We focus on generation of immune detectors by using negative selection operator and clone selection operator. Subsequently, the detectors are evolved. The results of testing on large genomic sequences by comparisons show that our algorithm is efficient with higher sensitivity and specificity in predicting promoter regions.

Inspiring by biological immune principles, many immune detection algorithms in the area of Artificial Immune System are introduced. In this paper, such problems as immune memory, immune match and niching strategy in the algorithms are discussed. The idea of scheme match and Complement Operator are proposed. The experiments that are in the area of virus detection and intrusion detection are made. Shown by experiments, the algorithm joined scheme match and Complement operator improves the problem of hole and keeps variety of antibodies. And its detecting efficiency is increased obviously.