Home > Archive > 2018 > Volume 8 Number 5 (Oct. 2018) >
IJMLC 2018 Vol.8(5): 447-453 ISSN: 2010-3700
DOI: 10.18178/ijmlc.2018.8.5.727

Solving 3-D Puzzles Using Tensor Decomposition and Application to Education of Multidimensional Data Analysis

Akio Ishida, Naoki Yamamoto, Jun Murakami, and Nobuhiro Oishi

Abstract—We have been conducting research on multi-dimensional data analysis. Because it is difficult to teach students of our laboratory the concept of multidimensional data processing, we are developing teaching materials to make them easier to understand that. In this paper, we described a method to solve 3-d puzzles using HOSVD, which is one of the methods of tensor decomposition, and proposed utilizing it to education. Specifically, we took up several kinds of 3-d puzzles and showed their solutions and scripts of R language.

Index Terms—Multidimensional data processing, tensor decomposition, HOSVD, 3-d puzzles, understanding support.

A. Ishida is with the Faculty of Liberal Studies, Kumamoto College, National Institute of Technology, Koshi, 861-1102 Japan (e-mail: ishida@kumamoto-nct.ac.jp).
N. Yamamoto and J. Murakami is with the Department of Human-Oriented Information Systems Engineering, Kumamoto College, National Institute of Technology, Koshi, 861-1102 Japan.
N. Oishi is with the Department of Information, Communication and Electronic Engineering, Kumamoto College, National Institute of Technology, Koshi, 861-1102 Japan.

[PDF]

Cite: Akio Ishida, Naoki Yamamoto, Jun Murakami, and Nobuhiro Oishi, "Solving 3-D Puzzles Using Tensor Decomposition and Application to Education of Multidimensional Data Analysis," International Journal of Machine Learning and Computing vol. 8, no. 5, pp. 447-453, 2018.

General Information

  • E-ISSN: 2972-368X
  • Abbreviated Title: Int. J. Mach. Learn.
  • Frequency: Quaterly
  • DOI: 10.18178/IJML
  • Editor-in-Chief: Dr. Lin Huang
  • Executive Editor:  Ms. Cherry L. Chen
  • Abstracing/Indexing: Inspec (IET), Google Scholar, Crossref, ProQuest, Electronic Journals LibraryCNKI.
  • E-mail: ijml@ejournal.net


Article Metrics in Dimensions