Open AccessClassification with incomplete training information using a cluster ensemble and low-rank matrix decomposition
Author(s) -
B. A. TULEGENOVA,
E. N. AMIRGALIYEV,
Lyailya Cherikbayeva,
Vladimir Berikov
Publication year - 2020
Publication title -
vestnik nacionalʹnoj inženernoj akademii respubliki kazahstan
Language(s) - English
Resource type - Journals
eISSN - 2709-4707
pISSN - 2709-4693
DOI - 10.47533/2020.1606-146x.32
Subject(s) - computer science , laplacian matrix , pattern recognition (psychology) , regularization (linguistics) , cluster analysis , matrix decomposition , hyperspectral imaging , spectral clustering , artificial intelligence , rank (graph theory) , graph , computation , similarity (geometry) , matrix (chemical analysis) , data mining , algorithm , mathematics , image (mathematics) , theoretical computer science , eigenvalues and eigenvectors , physics , quantum mechanics , combinatorics , materials science , composite material
The paper is devoted to solve the pattern recognition problem with incomplete learning data. The solution method, which combines similarity graph with Laplacian Regularization and collective clustering is proposed. The low-rank decomposition of co-association matrix for cluster ensemble is used, which allows to speed up the computations and keep memory. Experimental results on test tasks and on real hyperspectral image demonstrate the effectiveness of proposed method, including with noisy data.