Evaluating software clustering using multiple simulated authoritative decompositions
Evaluating software clustering using multiple simulated authoritative decompositions
复制标题
使用多个模拟权威分解评估软件集群
DOI：
--
复制
发表时间：
2011
期刊：
影响因子：
--
通讯作者：
Vassilios Tzerpos
中科院分区：
文献类型：
--
作者：
Mark Shtern;Vassilios Tzerpos
对软件聚类算法的评估，通常是将聚类结果与系统专家手工编制的权威分解进行比较。这种方法的一个众所周知的缺点是，有许多同样有效的方法来分解软件系统，因为不同的聚类目标会产生不同的分解结果。根据单一权威分解评估所有聚类算法可能会导致有偏差的结果。在本文中，我们介绍了 LimSim，这是一种利用多个模拟权威分解进行软件聚类评估的新方法。我们还介绍了应用这种新方法评估各种软件聚类算法的实验结果。这些结果证明了 LimSim 的实用性。
Evaluation of software clustering algorithms is typically done by comparing the clustering results to an authoritative decomposition prepared manually by a system expert. A well-known drawback of this approach is the fact that there are many, equally valid ways to decompose a software system, since different clustering objectives create different decompositions. Evaluating all clustering algorithms against a single authoritative decomposition can lead to biased results. In this paper, we introduce LimSim, a novel approach for software clustering evaluation that utilizes multiple simulated authoritative decompositions. We also present experimental results of applying the new approach to evaluate various software clustering algorithms. The results demonstrate the usefulness of LimSim.