Dimensionality Reduction in Data Cubes With Independent Slices
Zacharenia Kyrana, Emmanouil D. Pratsinakis, Nikolaos Papafilippou, Alexandra-Maria Michaelidou, Efstratios Kiranas, Georgios C. Menexes · 2025
Data cubes are p-dimensional data structures, where p ≥ 3. The application of different dimensionality reduction strategies based on PCA to data cubes was investigated. Some strategies focused on decomposing the total variability of the data cube into between-“slices” and within-“slices” variability. Other strategies either ignored the effect of “slices” or considered it on the overall data cube structure. The primary aim was to provide new insights into dimensionality reduction strategies on data cubes with independent “slices”. For the implementation and comparison of the proposed strategies, two three-dimensional data cubes with independent “slices” and differing structures in terms of the number of objects per “slice” were examined. The proposed strategies highlighted the importance of applying different analysis strategies for dimensionality reduction according to the research objectives.