Galactic swarm optimization (GSO) is a new global metaheuristic optimization algorithm. It manages multiple sub-populations to explore search space efficiently. Then superswarm is recruited from the best-found solutio...
详细信息
Galactic swarm optimization (GSO) is a new global metaheuristic optimization algorithm. It manages multiple sub-populations to explore search space efficiently. Then superswarm is recruited from the best-found solutions. Actually, GSO is a framework. In this framework, search method in both sub-population and superswarm can be selected differently. In the original work, particle swarm optimization is used as the search method in both phases. In this work, performance of the state of the art and well known methods are tested under GSO framework. Experiments show that performance of artificial bee colony algorithm under the GSO framework is the best among the other algorithms both under GSO framework and original algorithms.
A three-dimensional objective space (3DOS) optimization strategy using an enhanced multi-objective artificial bee colony (ABC) algorithm for the design optimization of layered radar absorbing material (LRAM) is presen...
详细信息
A three-dimensional objective space (3DOS) optimization strategy using an enhanced multi-objective artificial bee colony (ABC) algorithm for the design optimization of layered radar absorbing material (LRAM) is presented in this study. The multi-objective exploitation ability of ABC is improved with regard to the convergence and diversity by integrating a pioneer Pareto (PP) solution to the onlooker bee phase, which is selected from the Pareto optimal set. Initially, the performance of PP-ABC is successfully verified by a comparison with ABC and the well-known multi-objective counterparts like particle swarm optimization (PSO) and differential evolution (DE) algorithms. The comparison is carried out through five multi-objective benchmark functions with respect to three favorable and reliable multi-objective indicators such as hypervolume (HV), HV ratio and Pareto sets proximity (PSP). The employed three objective functions to be the dimensions of 3DOS are weighted bandwidth-based total reflection coefficient involving sub-reflection waves of a wide oblique incident angular range 0 degrees-75 degrees, the total thickness and the number of layers. By using PP-ABC, a 3D designed LRAM operating at a large frequency band of 2-18 GHz is then designed for synchronously minimizing the three objective vectors by finding out the design variables: thickness and material types. Meanwhile, the material types of the proposed LRAM are optimally picked up from a composite material database with 51 specimens from 9 previously reported studies (51 /9#database). In order to point out the effectiveness of the proposed 3DOS optimization strategy, three LRAMs are also compared with respective reported designs whose material type is selected from a database with 6 specimens (6/1#database). The results show that the proposed LRAMs are hence the global optimal designs in terms of all objective functions thanks to the proposed 3DOS optimization strategy based on PP-ABC. (C) 2020 Elsevier B.V
This study presents the cooperation of candidate solutions vortex search called CVS that has been used for solving numerical function optimization. The main inspiration of CVS is that there have been some drawbacks of...
详细信息
ISBN:
(纸本)9783319936925;9783319936918
This study presents the cooperation of candidate solutions vortex search called CVS that has been used for solving numerical function optimization. The main inspiration of CVS is that there have been some drawbacks of the Vortex Search (VS) algorithm. Although, the results from the proposal of VS are presented with a high ability but it could produce some drawbacks in updating the positions of vortex swarm. The VS used only single center generating the candidate solutions. The disadvantages happened when VS suffers from multi-modal problems that contain a number of local minima points. To overcome these drawbacks, the proposed CVS generated some cooperation of swarms which created from the diverse points. The experiments were conducted on 12 of benchmark functions. The capability of CVS was compared among the 5 algorithms: DE, GWO, MFO, VS and MVS. The results showed that CVS outperformed all of the comparisons of algorithms used.
In various studies, classification method and input features are two main factors that have significant effects on the results. In high dimensional non-linear problems, SVM was suggested as the superior classification...
详细信息
In various studies, classification method and input features are two main factors that have significant effects on the results. In high dimensional non-linear problems, SVM was suggested as the superior classification. In these cases, the kernel parameters are often determined by the trial-and-error approach, which leads to reduce reliability of the results and automation level. On the other hand, because of the similarity of pixel spectral behavior, the classification accuracy will be reduced using only spectral bands in complex urban areas. To overcome this limitation, using additional features (e.g., textural and elevational features) was suggested in many studies. However, due to high variety of textural features in terms of type and direction, the presence probability of dependent features will increase by using all the features, which results in classification inefficiency. In addition to relatively high automation, in this paper, metaheuristic optimization algorithms were used to optimize simultaneously SVM in feature selection (FS) and parameter determination (PD) process as a solution due to being independent of image type and scene. There are few comprehensive evaluations in this field in various studies. For this purpose, a comprehensive research of the most efficient optimizationalgorithms in SVM (i.e., ACOR, GA, ICA, and PSO) was carried out in different ways and by different input features. Moreover, the results were compared to random forest (RF) classification in terms of FS process and accuracy. The optimized SVMs were implemented on two different image scenes (i.e., simple suburban and complex urban areas) in order to show the robustness of the optimized methods in terms of image type and scene. The results were evaluated by five quantitative criteria and McNemar's test. Also, the approximate time calculations, the number of optimized features, and parameters were presented for each image scene. In comparison with using only spectral bands, the re
Prediction of solar power involves the knowledge of the sun, atmosphere and other parameters, and the scattering processes and the specifications of a solar energy plant that employs the sun's energy to generate s...
详细信息
Prediction of solar power involves the knowledge of the sun, atmosphere and other parameters, and the scattering processes and the specifications of a solar energy plant that employs the sun's energy to generate solar power. This prediction result is essential for an efficient use of the solar power plant, the management of the electricity grid, and solar energy trading. However, because of nonlinear and nonstationary behavior of solar power time series, an efficient forecasting model is needed to predict it. Accordingly, in this paper, we propose a new forecast approach based on combination of a neural network with a metaheuristicalgorithm as the hybrid forecasting engine. The metaheuristicalgorithm optimizes the free parameters of the neural network. This approach also includes a 2-stage feature selection filter based on the information-theoretic criteria of mutual information and interaction gain, which filters out the ineffective input features. To demonstrate the effectiveness of the proposed forecast approach, it is implemented on a real-world engineering test case. Obtained results illustrate the superiority of the proposed approach in comparison with other prediction methods.
In case of complex parts machining or multi-directional machining in multi-part fixtures the error compensation in multi-dimensional decision space poses a difficult problem. The article focuses on the limitation of d...
详细信息
In case of complex parts machining or multi-directional machining in multi-part fixtures the error compensation in multi-dimensional decision space poses a difficult problem. The article focuses on the limitation of defective products by means of systematic increase of the remaining error budget due to correction of the setup data. A vectorial equation for machine tool space description is presented. The development of geometric dimensioning and tolerancing scheme to the levels connected with the setup data is proposed. The optimizationalgorithm used here is based on the paradigm particle swarm optimization (PSO), but it includes a few significant modifications inspired by the growth of the coral reef thus the name of the method-coral reefs inspired particle swarm optimization (CRIPSO). CRIPSO has been compared with three other popular metaheuristics: classic PSO, genetic algorithm, and cuckoo optimizationalgorithm. There is a practical example in this article.
Flower pollination algorithm (FPA) is a novel metaheuristic optimization algorithm with quick convergence, but its population diversity and convergence precision can be limited in some applications. In order to enhanc...
详细信息
Flower pollination algorithm (FPA) is a novel metaheuristic optimization algorithm with quick convergence, but its population diversity and convergence precision can be limited in some applications. In order to enhance its exploitation and exploration abilities, in this paper, an elite opposition-based flower pollination algorithm (EOFPA) has been applied to functions optimization and structure engineering design problems. The improvement involves two major optimization strategies. Global elite opposition-based learning enhances the diversity of the population, and the local self-adaptive greedy strategy enhances its exploitation ability. An elite opposition-based flower pollination algorithm is validated by 18 benchmark functions and two structure engineering design problems. The results show that the proposed algorithm is able to obtained accurate solution, and it also has a fast convergence speed and a high degree of stability. (C) 2015 Elsevier B.V. All rights reserved.
Distributed generation (DG) has been utilized in some electric power networks. Power loss reduction, environmental friendliness, voltage improvement, postponement of system upgrading, and increasing reliability are so...
详细信息
Distributed generation (DG) has been utilized in some electric power networks. Power loss reduction, environmental friendliness, voltage improvement, postponement of system upgrading, and increasing reliability are some advantages of DG-unit application. This paper presents a new optimization approach that employs an artificial bee colony (ABC) algorithm to determine the optimal DG-unit's size, power factor, and location in order to minimize the total system real power loss. The ABC algorithm is a new metaheuristic, population-based optimization technique inspired by the intelligent foraging behavior of the honeybee swarm. To reveal the validity of the ABC algorithm, sample radial distribution feeder systems are examined with different test cases. Furthermore, the results obtained by the proposed ABC algorithm are compared with those attained via other methods. The outcomes verify that the ABC algorithm is efficient, robust, and capable of handling mixed integer nonlinear optimization problems. The ABC algorithm has only two parameters to be tuned. Therefore, the updating of the two parameters towards the most effective values has a higher likelihood of success than in other competing metaheuristic methods.
暂无评论