Home // BUSTECH 2018, The Eighth International Conference on Business Intelligence and Technology // View article

Detecting Adverse Events in an Active Theater of War Using Data Mining Techniques

Authors:
Jozef Zurada
Donghui Shi
Waldemar Karwowski
Jian Guan
Erman Cakit

Keywords: Adverse events, Active war theater, Prediction, Classification, Data mining

Abstract:
This study investigates the effectiveness of data mining techniques in detecting adverse events based on infrastructure development spending, the number of project types, and other variables in an active theater of war in Afghanistan using data sets provided by the Human Social Culture Behavior program management (2002-2010) of the U.S. Department of Defense. The study first applies feature reduction techniques to identify significant variables, then uses five cost-sensitive classification methods and reports the resulting classification accuracy rates and areas under the receiver operating characteristics charts for adverse events for each method for the entire country and its seven regions. The results show that when analysis is performed for the entire country, there is little correlation between adverse events and project types and the number of projects. However, the same type of analysis performed for each of its seven regions shows a connection between adverse events and the infrastructure budget and the number of projects allocated for the specific regions and time periods. Among the five classifiers, the C4.5 decision tree and k-nearest neighbor provided the best global performance.

Pages: 43 to 44

Copyright: Copyright (c) IARIA, 2018

Publication date: February 18, 2018

Published in: conference

ISSN: 2308-4391

ISBN: 978-1-61208-614-9

Location: Barcelona, Spain

Dates: from February 18, 2018 to February 22, 2018