Object Cluster Hierarchies

对象集群层次数据集是由弗罗茨瓦夫科技大学计算智能系的研究人员开发，用于支持机器学习领域中的层次聚类分析方法的评估和改进。该数据集包含160个层次结构，涵盖了多种不同的层次特征，如深度、宽度和数据分布。数据集的创建过程涉及使用树结构棒打破过程生成合成层次数据，确保数据集能够模拟真实世界中的复杂层次结构。这些数据集适用于测试和比较不同的层次聚类算法，以及开发新的聚类质量评估方法。

The Object Cluster Hierarchical Dataset was developed by researchers from the Department of Computational Intelligence, Wrocław University of Science and Technology, to support the evaluation and refinement of hierarchical clustering analysis methods in the field of machine learning. This dataset comprises 160 hierarchical structures, encompassing a wide range of hierarchical characteristics such as depth, width, and data distribution. The dataset's development process utilizes the tree-stick breaking process to generate synthetic hierarchical data, ensuring that it can replicate complex hierarchical structures present in real-world scenarios. This dataset is suitable for testing and comparing different hierarchical clustering algorithms, as well as developing novel methods for clustering quality assessment.