Generating Data on Individual Learning Paths for Classification Using Deep Learning Networks

DOI

10.2991/aisr.k.201029.069How to use a DOI?

Keywords

ontology, individual learning paths, deep learning networks, compiler generator, generation of model data

Abstract

The article considers information about individual learning paths as a set of observations with a large number of features. To reduce the amount of information, it is proposed to classify samples using deep learning networks. Selections are saved either in a relational database or as an ontology. To device training algorithms, a generation of model data instead of real ones, which is currently missing, is proposed. Data are converted from relational tables to ontology using the ANTLR compiler generator. Based on the generated data and qualimetric estimates, the integral characteristics are calculated using a method also proposed in the article. The final results will be a quality assessment of the classification based on deep learning networks. The methods and approaches proposed by the authors are universal and can be used in any higher educational institution to select an algorithm for their qualitative classification.

Copyright

© 2020, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Sofia Sosinskaya
AU  - Roman Dorofeev
AU  - Sofia Rogacheva
AU  - Andrey Dorofeev
PY  - 2020
DA  - 2020/11/10
TI  - Generating Data on Individual Learning Paths for Classification Using Deep Learning Networks
BT  - Proceedings of the 8th Scientific Conference on Information Technologies for Intelligent Decision Making Support (ITIDS 2020)
PB  - Atlantis Press
SP  - 369
EP  - 374
SN  - 1951-6851
UR  - https://doi.org/10.2991/aisr.k.201029.069
DO  - 10.2991/aisr.k.201029.069
ID  - Sosinskaya2020
ER  -