Research on Distributed TBL Support Vector Machine Based on MapReduce

DOI

10.2991/amcce-15.2015.168How to use a DOI?

Keywords

MapReduce frame; TBL method; Cluster model; M-tree; Internal medicine

Abstract

In the research process of internal medicine learning method, chunk cognitive processing is not easy to explore because of the complexity of having overall cognitive understanding and structure semantic understanding. Through the attempt of TBL method, this paper carries out chunk cognitive evaluation under the MapReduce framework, the method is validated by using clustering mathematical model, and then using cluster graph visualization function carries out analysis each cluster for the chunk cognitive process. Under the continuously increasing of the number of learning cognitive clusters, the method can display the individual chunk cognitive level of data set, finally using M- tree node overflow can get the contribution subtree model of the TBL method for the chunk perception. Based on the TBL method and the control group experiment, we discover that the contribution of TBL method is larger for the chunk perception, which can effectively improve the chunk cognitive performance, but also provide a new computer method for the inquiry of internal medicine learning method.

Copyright

© 2015, 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  - Jianwei Hu
AU  - Aiping Sheng
AU  - Huixiang Zhuge
PY  - 2015/04
DA  - 2015/04
TI  - Research on Distributed TBL Support Vector Machine Based on MapReduce
BT  - Proceedings of the 2015 International Conference on Automation, Mechanical Control and Computational Engineering
PB  - Atlantis Press
SP  - 845
EP  - 850
SN  - 1951-6851
UR  - https://doi.org/10.2991/amcce-15.2015.168
DO  - 10.2991/amcce-15.2015.168
ID  - Hu2015/04
ER  -