Using Nonnegative Matrix Factorization and Concept Lattice Reduction to visualizing data

摘要

The large volume of data from the large-scale computing platforms for high-fidelity design and simulations, and instrumentation for gathering scientific as well as business data, and huge information in the web, give us some problems if we want to compute all concepts from huge incidence matrix. In some cases, we do not need to compute all concepts, but only some of them. In this paper, we proposed minimizing incidence matrix by using non-negative matrix factorization (NMF), because non-negative matrix factorization (NMF) is an emerging technique with a wide spectrum of potential applications in biomedical data analysis. Modified matrix has lower dimensions and acts as an input for some known algorithms for lattice construction.