DATA CLUSTER ANALYSIS BASED ON OBJECT RELATIONS BY LOCAL OBJECTS
Received: 2026-07-15 10:39:01
Published: 2026-04-18
Abstract
In data analysis and machine learning tasks, the structure of the training dataset plays an important role. Large datasets may contain redundant or duplicated objects, which increases computational complexity and may reduce the efficiency of classification algorithms.In this paper, the stability of datasets obtained using an object selection algorithm is analyzed. To evaluate the structural properties of the data, a new nominal feature is introduced based on the composition of the k-nearest neighbors. The stability of this feature is evaluated using a specific indicator.For different levels of selection, a stability matrix is constructed, after which a correlation analysis between the datasets is performed. In addition, Principal Component Analysis (PCA) is applied for the visual analysis of structural differences between the datasets.
Keywords
List of references
About the Authors
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
How to Cite
