Predictive analysis of terrorist activities in Thailand's Southern provinces: a deep learning approach
Journal article
Authors/Editors
Strategic Research Themes
Publication Details
Author list: Ganokratanaa, Thittaporn; Ketcham, Mahasak
Publication year: 2024
Journal acronym: IJECE
Volume number: 14
Issue number: 2
Start page: 1797
End page: 1808
Number of pages: 12
ISSN: 2088-8708
Languages: English-Great Britain (EN-GB)
Abstract
Terrorist activities have been on the rise globally, with Thailand experiencing significant challenges, particularly in its three southern border provinces. This study offers a comprehensive analysis aiming to predict forthcoming terrorist events in these provinces. We employed historical data, categorized into nine groups based on military expert recommendations, to train our prediction model. This research tested the prediction capabilities of various methodologies, including decision trees, naïve Bayesian learning techniques, and deep learning artificial neural networks. Notably, the deep neural network emerged as the superior predictive tool, achieving an impressive accuracy of 98.21% and a root mean square error (RMSE) of 0.59%. The primary anticipated events include bombings, shootings, assaults, and acts of vandalism. Our findings also revealed that Pattani Province was the most affected, accounting for 45% of incidents. Specific districts, such as Panare and Yarang, exhibited high crime rates of 40% and 36.84%, respectively. Yala Province, particularly Bannang Sata District, was identified as the hotspot for shooting incidents, with a rate of 34%. © 2024 Institute of Advanced Engineering and Science. All rights reserved.
Keywords
Data-driven analysis framework, Event categorization and forecasting, Terrorist events prediction, Thailand's Southern border provinces
Contact Information