ABSTRACT
In order to improve the search ability, the convergence performance and algorithm results of genetic algorithm, we propose a population initialization method of genetic algorithm based on improved k-means algorithm. Firstly, the initial individuals walking evenly in the decision space are created by uniform design method, and then the initial individuals are processed by local search such as step-by-step search. Secondly, through the similarity degree between the individuals, several main search spaces are aggregated. Based on the search space, the individuals needed by the final initial population are clustered by K-means method.
- Poikolainen I, Neri F, Caraffini F. Cluster-based population initialization for differential evolutio frameworks[J]. Information Sciences, 2015, 297: 216--235.Google ScholarDigital Library
- Elsayed S, Sarker R, Coello C A. Sequence-based deterministic initialization for evolutionary algorithms[J]. IEEE Transactions on Cybernetics, 2017, 47 (9):2911--2923.Google ScholarCross Ref
- 马金萍,尹默,郑屹然.基于双重抽样框的均匀设计抽样调查方法研究[J/OL]. 统计与决策, 2021(04):50--52.Google Scholar
- (Ma J P, Yi M, Zheng Y R. Research on uniform design sampling survey method based on double sampling frame [J/OL]. Statistics and decision making, 2021 (04):50--52.)Google Scholar
- 陈再现,钟炜彭,李秦鸣.基于均匀设计的模型更新混合模拟试验方法[J].振动 与冲击, 2020, 39(21):9--16.Google Scholar
- (Chen Z X, Zhong W P, Li Q M. Hybrid simulation test method of model updating based on uniform design [J]. Vibration and shock, 2020, 39(21):9--16.)Google Scholar
- Kong Zhiwei, Zhang Yong, Wang Xudong, Sun Shuanzhu, Zhou Chunlei, Li Dou, Jin Baosheng. Error prediction and structure determination for CMAC neural network based on the uniform design method[J]. Expert Systems, 2020, 38(2).Google Scholar
- Tolga A, Egemen Y. Multiobjective Hooke-Jeeves algorithm with a stochastic Newton-Raphson-like step-size method[J]. Expert System with Application, 2019, 117(3): 166--175.Google Scholar
- Marco C, Aritz P, Jose A L. An efficient approximation to the K-means clustering for massive data[J]. Knowledge-Based Systems, 2017, 117(2): 56--69.Google Scholar
- Surya K, Tripti M, Vinay K J, et al. LeaderRank based k-means clustering initialization method for collaborative filtering[J]. Computers and Electrical Engineering, 2018, 69(6): 598--609.Google Scholar
- Jocelyn Z G, Ado A A, Abdelhak M G. Efficient K-means based clustering scheme for mobile networks cell sites management[J]. Computer and Information Sciences, 2018, 11: 1--8.Google Scholar
- Zhang G, Zhang C C, Zhang H Y. Improved K-means algorithm based on density Canopy[J]. Knowledge-Based Systems, 2018, 145(4): 289--297.Google ScholarDigital Library
Index Terms
- Initialization method of genetic algorithm based on improved clustering algorithm
Recommendations
Cluster center initialization algorithm for K-means clustering
Performance of iterative clustering algorithms which converges to numerous local minima depend highly on initial cluster centers. Generally initial cluster centers are selected randomly. In this paper we propose an algorithm to compute initial cluster ...
A quantum-inspired genetic algorithm for k-means clustering
The number of clusters has to be known in advance for the conventional k-means clustering algorithm and moreover the clustering result is sensitive to the selection of the initial cluster centroids. This sensitivity may make the algorithm converge to ...
Genetically Improved PSO Algorithm for Efficient Data Clustering
ICMLC '10: Proceedings of the 2010 Second International Conference on Machine Learning and ComputingClustering is an important research topic in data mining that appears in a wide range of unsupervised classification applications. Partitional clustering algorithms such as the k-means algorithm are the most popular for clustering large datasets. The ...
Comments