期刊
INFORMATION SCIENCES
卷 554, 期 -, 页码 99-119出版社
ELSEVIER SCIENCE INC
DOI: 10.1016/j.ins.2020.12.020
关键词
Artificial Data; Benchmark Data; Benchmark Data Generator; Hierarchical Clustering; Object Cluster Hierarchy; Tree-Structured Stick Breaking Process; Clustering Evaluation; Cluster Analysis
This paper introduces a generator for benchmarking Object Cluster Hierarchy generation methods and provides a thorough empirical and theoretical analysis. The experiments show that the generator is capable of producing datasets with different structures.
A new variant of Hierarchical Cluster Analysis is gaining interest in the field of Machine Learning, called Object Cluster Hierarchy. Being still at an early stage of development, the lack of tools for systematic analysis of Object Cluster Hierarchies inhibits further improvement of this concept. In this paper we address this issue by proposing a generator of synthetic hierarchical data that can be used for benchmarking Object Cluster Hierarchy generation methods. The article presents a thorough empirical and theoretical analysis of the generator and provides guidance on how to control its parameters. The conducted experiments show the usefulness of the data generator capable of producing a wide range of differently structured data. Furthermore, datasets that represent the most common types of hierarchies are generated and made available to the public for benchmarking, along with the developed generator (http://kio.pwr.edu.pl/?page_id=396) (C) 2020 Elsevier Inc. All rights reserved.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据