Welcome to the InfoSci Platform
Winning the War on Terror: Using “Top-K” Algorithm and CNN to Assess the Risk of Terrorists

Winning the War on Terror: Using “Top-K” Algorithm and CNN to Assess the Risk of Terrorists

Yaojie Wang, Xiaolong Cui, Peiyong He
Copyright: © 2022 |Volume: 17 |Issue: 1 |Pages: 15
ISSN: 1554-1045|EISSN: 1554-1053|EISBN13: 9781799894001|DOI: 10.4018/IJITWE.288038
Cite Article Cite Article

MLA

Wang, Yaojie, et al. "Winning the War on Terror: Using “Top-K” Algorithm and CNN to Assess the Risk of Terrorists." IJITWE vol.17, no.1 2022: pp.1-15. http://doi.org/10.4018/IJITWE.288038

APA

Wang, Y., Cui, X., & He, P. (2022). Winning the War on Terror: Using “Top-K” Algorithm and CNN to Assess the Risk of Terrorists. International Journal of Information Technology and Web Engineering (IJITWE), 17(1), 1-15. http://doi.org/10.4018/IJITWE.288038

Chicago

Wang, Yaojie, Xiaolong Cui, and Peiyong He. "Winning the War on Terror: Using “Top-K” Algorithm and CNN to Assess the Risk of Terrorists," International Journal of Information Technology and Web Engineering (IJITWE) 17, no.1: 1-15. http://doi.org/10.4018/IJITWE.288038

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

From the perspective of counter-terrorism strategies, terrorist risk assessment has become an important approach for counter-terrorism early warning research. Combining with the characteristics of known terrorists, a quantitative analysis method of active risk assessment method with terrorists as the research object is proposed. This assessment method introduces deep learning algorithms into social computing problems on the basis of information coding technology. We design a special "Top-k" algorithm to screen the terrorism related features, and optimize the evaluation model through convolution neural network, so as to determine the risk level of terrorist suspects. This study provides important research ideas for counter-terrorism assessment, and verifies the feasibility and accuracy of the proposed scheme through a number of experiments, which greatly improves the efficiency of counter-terrorism early warning.