Large-Scale Experimental Evaluation of Cluster Representations for Multiobjective Evolutionary Clustering
Large-Scale Experimental Evaluation of Cluster Representations for Multiobjective Evolutionary Clustering
复制标题
DOI：
10.1109/tevc.2013.2281513
复制
发表时间：
2014-02
影响因子：
14.3
通讯作者：
A. Garcia-Piquer;A. Fornells;J. Bacardit;A. Orriols-Puig;E. Golobardes
中科院分区：
文献类型：
--
作者：
A. Garcia-Piquer;A. Fornells;J. Bacardit;A. Orriols-Puig;E. Golobardes
多目标进化聚类算法是基于多个目标函数的优化，这些目标函数引导搜索遵循基于进化算法的循环。他们的能力使他们能够找到更好的解决方案比传统的聚类算法，如果选择合适的个人表示。本文提供了一个详细的分析，三个最相关和最有用的表示原型为基础，标签为基础，图形为基础的，通过广泛的合成数据集。此外，他们也比较相关的传统聚类算法。实验表明，多目标进化聚类算法与其他聚类算法相比具有较强的竞争力。此外，还提出了每种表示的最佳方案。
Multiobjective evolutionary clustering algorithms are based on the optimization of several objective functions that guide the search following a cycle based on evolutionary algorithms. Their capabilities allow them to find better solutions than with conventional clustering algorithms if the suitable individual representation is selected. This paper provides a detailed analysis of the three most relevant and useful representations-prototype-based, label-based, and graph-based-through a wide set of synthetic data sets. Moreover, they are also compared to relevant conventional clustering algorithms. Experiments show that multiobjective evolutionary clustering is competitive with regard to other clustering algorithms. Furthermore, the best scenario for each representation is also presented.