期刊名称：Journal of Theoretical and Applied Information Technology
印刷版ISSN：1992-8645
电子版ISSN：1817-3195
出版年度：2017
卷号：95
期号：23
页码：6369
出版社：Journal of Theoretical and Applied
摘要：In this paper, we present a new data classification approach in an unsupervised context, which is based on both numeric discretization and mathematical pretopology. The pretopologicals tool, specially the adherency application are used in the modes extraction process. The first part of the proposed algorithm consists to a presentation of the set of the multidimensional observations as a mathematical numeric discrete set; the second part of the algorithm consists in detecting clusters as separated subsets by means of pretopological transformations.
