Presentation 2013-10-24
A New Machine Learning Based Data Mining Approach for the Network Big Data
Hongbo SHI, Kazuhiko IWASAKI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We propose a new method that impoves a neural network, the Growing Hierarchical Self-Organizing Map (GHSOM), to analyze the DNS query log files. Based on our proposal, the structure of the DNS query frequency, infected computers are easier to detect than our prior research. Our experiment shows the different DNS query structure between healthy and infected computers. Furthermore, the experiment results show that our proposal can detect the infected computers properly based on their simple classification structures.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) DNS / GHSOM / classification / query interval
Paper # DC2013-24
Date of Issue

Conference Information
Committee DC
Conference Date 2013/10/17(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Dependable Computing (DC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A New Machine Learning Based Data Mining Approach for the Network Big Data
Sub Title (in English)
Keyword(1) DNS
Keyword(2) GHSOM
Keyword(3) classification
Keyword(4) query interval
1st Author's Name Hongbo SHI
1st Author's Affiliation Library and Information Academic Center, Tokyo Metropolitan University()
2nd Author's Name Kazuhiko IWASAKI
2nd Author's Affiliation Library and Information Academic Center, Tokyo Metropolitan University
Date 2013-10-24
Paper # DC2013-24
Volume (vol) vol.113
Number (no) 270
Page pp.pp.-
#Pages 6
Date of Issue