The design method of adaptive infinite impulse response (IIR) filter is a challenging problem. Its design principle is to determine the filter parameters by the iteration process of the adaptive algorithm, which is to...
详细信息
The design method of adaptive infinite impulse response (IIR) filter is a challenging problem. Its design principle is to determine the filter parameters by the iteration process of the adaptive algorithm, which is to obtain an optimal model for unknown plant based on minimizing mean square error (MSE). However, many adaptive algorithms cannot adjust the parameters of IIR filter to the minimum MSE. Therefore, a more efficient adaptive optimizationalgorithm is required to adjust the parameters of IIR filter. In this paper, we propose a selfish herd optimization algorithm based on chaotic strategy (CSHO) and apply it to solving IIR system identification problem. In CSHO, we add a chaotic search strategy, which is a better local optimization strategy. Its function is to search for better candidate solutions around the global optimal solution, which makes the local search of the algorithm more precise and finds out potential global optimal solutions. We use solving IIR system identification problem to verify the effectiveness of CSHO. Ten typical IIR filter models with the same order and reduced order are selected for experiments. The experimental results of CSHO compare with those of bat algorithm (BA), cellular particle swarm optimization and differential evolution (CPSO-DE), firefly algorithm (FFA), hybrid particle swarm optimization and gravitational search algorithm (HPSO-GSA), improved particle swarm optimization (IPSO) and opposition-based harmony search algorithm (OHS), respectively. The experimental results show that CSHO has better optimization accuracy, convergence speed and stability in solving most of the IIR system identification problems. At the same time, it also obtains better optimization parameters and achieves smaller difference between actual output and expected output in test samples.
Clustering analysis is a popular data analysis technology that has been successfully applied in many fields, such as pattern recognition, machine learning, image processing, data mining, computer vision and fuzzy cont...
详细信息
Clustering analysis is a popular data analysis technology that has been successfully applied in many fields, such as pattern recognition, machine learning, image processing, data mining, computer vision and fuzzy control. Clustering analysis has made great progress in these fields. The purpose of clustering analysis is to classify data according to their intrinsic attributes such that data that have the same characteristics are in the same class and data that differ are in different classes. Currently, the k-means clustering algorithm is one of the most commonly used clustering methods because it is simple and easy to implement. However, its performance largely depends on the initial solution, and it easily falls into locally optimal solutions during the execution of the algorithm. To overcome the shortcomings of k-means clustering, many scholars have used meta-heuristic optimizationalgorithms to solve data clustering problems and have obtained satisfactory results. Therefore, in this paper, a selfish herd optimization algorithm based on the simplex method (SMSHO) is proposed. In SMSHO, the simplex method replaces mating operations to generate new prey individuals. The incorporation of the simplex method increases the population diversity of algorithm, thereby improving the global searching ability of algorithm. Twelve clustering datasets are selected to verify the performance of SMSHO in solving clustering problems. The SMSHO is compared with ABC, BPFPA, DE, k-means, PSO, SMSSO and SHO. The experimental results show that SMSHO has faster convergence speed, higher accuracy and higher stability than the other algorithms.
selfish herd optimization algorithm is a novel meta-heuristic optimizationalgorithm, which simulates the group behavior of herds when attacked by predators in nature. With the further research of algorithm, it is fou...
详细信息
selfish herd optimization algorithm is a novel meta-heuristic optimizationalgorithm, which simulates the group behavior of herds when attacked by predators in nature. With the further research of algorithm, it is found that the algorithm cannot get a better global optimal solution in solving some problems. In order to improve the optimization ability of the algorithm, we propose a selfish herd optimization algorithm with orthogonal design and information update (OISHO) in this paper. Through using orthogonal design method, a more competitive candidate solution can be generated. If the candidate solution is better than the global optimal solution, it will replace the global optimal solution. At the same time, at the end of each iteration, we update the population information of the algorithm. The purpose is to increase the diversity of the population, so that the algorithm expands its search space to find better solutions. In order to verify the effectiveness of the proposed algorithm, it is used to train multi-layer perceptron (MLP) neural network. For training multi-layer perceptron neural network, this is a challenging task to present a satisfactory and effective training algorithm. We chose twenty different datasets from UCI machine learning repository as training dataset, and the experimental results are compared with SSA, GG-GSA, GSO, GOA, WOA and SOS, respectively. Experimental results show that the proposed algorithm has better optimization accuracy, convergence speed and stability compared with other algorithms for training multi-layer perceptron neural network.
暂无评论