PREDICTING THE NATURE OF TERRORIST ATTACKS IN NIGERIA USING BAYESIAN NEURAL NETWORK MODEL
Keywords: Terrorism, Weapons, Bayesian Neural Network, Activation function, Accuracy
Abstract: Terrorist attacks is one of the major problems Nigeria is facing presently. Seeking for techniques to understand the different factors involved in terrorism and how to deal with those factors in order to completely eradicate or reduce terrorist activities is the topmost priority of the government in any country. This study focuses on using a Bayesian Neural Network (BNN) model for predicting the nature of attacks of terrorists in Nigeria . The developed model was considered under different activation functions and training sets. The results showed that hyperbolic tangent activation function outperformed the other activation functions better in predicting the important variables in terrorist attacks in Nigeria.
Submission Category: Machine learning algorithms
Submission Number: 3
Loading