Using Singular Value Decomposition to Reduce Dimensionality of Initial Data Set

2020 61st International Scientific Conference on Information Technology and Management Science of Riga Technical University (ITMS 2020): Proceedings 2020
Oļegs Užga-Rebrovs, Gaļina Kuļešova

The purpose of any data analysis is to extract essential information implicitly present in the data. To do this, it often seems necessary to transform the initial data into a form that allows one to identify and interpret the essential features of their structure. One of the most important tasks of data analysis is to reduce the dimension of the original data. The paper considers an approach to solving this problem based on singular value decomposition (SVD).

Keywords
Left eigenvectors, matrix rank, right eigenvectors, singular value decomposition, singular value matrix
DOI
10.1109/ITMS51158.2020.9259304
Hyperlink
https://ieeexplore.ieee.org/document/9259304

Užga-Rebrovs, O., Kuļešova, G. Using Singular Value Decomposition to Reduce Dimensionality of Initial Data Set. In: 2020 61st International Scientific Conference on Information Technology and Management Science of Riga Technical University (ITMS 2020): Proceedings, Latvia, Riga, 15-16 October, 2020. Piscataway: IEEE, 2020, pp.1-4. ISBN 978-1-7281-9106-5. e-ISBN 978-1-7281-9105-8. Available from: doi:10.1109/ITMS51158.2020.9259304

Publication language
English (en)