Attribute Selection Using Information Gain and Naïve Bayes for Traffic Classification

Oklilas, Ahmad Fali and tasmi, tasmi and Siswanti, Sri Desy and Afrina, Mira and Setiawan, Herri (2019) Attribute Selection Using Information Gain and Naïve Bayes for Traffic Classification. International Conference on Information System, Computer Science and Engineering (ICONISCSE), 1196 (1). pp. 1-6. ISSN 012021

Text tasmipaper1.pdf Restricted to Registered users only Download (734kB)

Abstract

This paper presents the value of good attributes in carrying out the package classification process Furthermore, attribute selection results can be of value in determining one type of data packet traffic. In obtaining the results (data) this study uses several stages of Data Capture, Feature Extraction and Feature Selection, but in this study only focuses on the process of feature selection using the gain and Entropy Information and Naïve Bayes algorithm. The testing process by dividing raw data into parts is 70 per cent for Training data and 30 per cent for testing data. The total data used is 6632, so for the training data obtained is 4642, while the data for testing is 1990. The results obtained are for the https data package type is 9 attributes, while for the HTTP data is 10 attributes. For further research can be added using another classification method as a comparison of data

Item Type:	Article
Subjects:	Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions:	Faculty of Computer Science > Department of Computer Engineering
Depositing User:	Mr Tasmi Salim
Date Deposited:	07 May 2019 04:01
Last Modified:	07 May 2019 04:01
URI:	http://eprints.uigm.ac.id/id/eprint/99

Actions (login required)

View Item