New York: Researchers have developed a new framework to predict future terrorist attacks by analysing the relationship between more than 140,000 such attacks that took place between 1970 and 2014. Developed by Salih Tutun and his colleagues from Binghamton University, the framework calculates the relationship between select features of terrorist attacks like attack time and weapon type. "They are learning, but they don't know they are learning. If we don't have social media or other technologies, we need to understand the patterns. Our framework works to define which metrics are important," Tutun said. "Based on this feature, we propose a new similarity (interaction) function. Then we use the similarity (interaction) function to understand the difference (how they interact with each other) between two attacks. For example, what is the relationship between the Paris and the 9/11 attacks? When we look at that, if there's a relationship, we're making a network," he added. Tutun presented his work recently at the 2016 Industrial and Systems Engineering Research Conference (ISERC) in California. Previous studies have focused on understanding the behaviour of individual terrorists (as people) rather than studying the different attacks by modelling their relationship with each other. Terrorist activity detection focuses on either individual incidents -- which does not take into account the dynamic interactions among them -- or network analysis -- which gives a general idea about networks but sets aside functional roles of individuals and their interactions. "Predicting terrorist events is a dream, but protecting some area by using patterns is a reality. If you know the patterns, you can reduce the risks. It's not about predicting, it's about understanding," Tutun said.