This study considers the task of clustering for data characterized by peculiar quantitative features in that they express performance according to different indicators or criteria. Performance is supposed to be optimized in one way or the other, i.e. maximized or minimized. This peculiar type of data introduces a comparative context that is not generally taken into account in the field of pattern recognition, in general, and clustering, in particular. In the present study, we introduce different concepts and develop tools that facilitate the evaluation of data partitions in this comparative context leading to the consideration of asymmetric preference relationships between objects and between clusters. We show their usefulness on the basis of artificial data and also by analyzing the results produced on real data by means of clustering methods.

这项研究考虑了对具有特殊定量特征的数据进行聚类的任务，因为它们根据不同的指标或标准来表达绩效。应该以一种或另一种方式（即最大化或最小化）来优化性能。这种奇特的数据类型引入了比较上下文，通常在模式识别领域（尤其是聚类）中通常不会考虑这种比较上下文。在本研究中，我们介绍了不同的概念并开发了有助于在这种比较情况下评估数据分区的工具，从而导致了对象之间和群集之间的不对称偏好关系的考虑。我们在人工数据的基础上以及通过使用聚类方法分析在实际数据上产生的结果来显示其有用性。