Abstract | ||
---|---|---|
There are often problems of search effectiveness and maintaining the diversity of population in solving single objective optimization problems by evolutionary algorithm. In order to improve search efficiency, the algorithm in this paper regards the current optimal individual as a search starting point, and designs efficient crossover and mutation operator with simulated annealing to search optimal solutions. A sorted race-based selection mechanism is taken to update current population to overcome premature and maintaining the diversity of population. The selection compares the similar individuals to select the best one to keep the population diversity. At last, we test a large number of single-objective test functions to compare and analyze the numerical results with existing algorithms. The results show that our algorithm is very effective. |
Year | DOI | Venue |
---|---|---|
2010 | 10.1109/ICMLC.2010.5580810 | ICMLC |
Keywords | Field | DocType |
crossover operator,evolutionary algorithm,evolutionary computation,sorted race-based selection mechanism,global optimization,sorted race mechanism,estimation,single objective optimization,simulated annealing,mutation operator,optimization problem,optimization | Simulated annealing,Population,Mathematical optimization,Crossover,Evolutionary algorithm,Global optimization,Computer science,Evolutionary computation,Artificial intelligence,Optimization problem,Machine learning,Mutation operator | Conference |
Volume | ISBN | Citations |
3 | 978-1-4244-6526-2 | 0 |
PageRank | References | Authors |
0.34 | 8 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Xueqiang Li | 1 | 47 | 4.54 |
Zhifeng Hao | 2 | 653 | 78.36 |
Han Huang | 3 | 159 | 30.23 |