Terrorists have become more careful when using the power of social media and telecommunication systems in planning for their attacks, which is why governments can’t always rely on these tools to discover their intentions.
But a team of researchers from Binghamton University and State University of New York proposed a new framework called Networked Pattern Recognition (NEPAR) that can understand terrorist behaviors in the future through recognizing the patterns in past terrorist attacks.
Salih Tutun, a PhD student at Binghamton, developed the framework with the use of data on over 150,000 terrorist attacks gathered between 1970 and 2015.
With NEPAR, describing the useful patterns of terrorist attacks is possible to be able to comprehend behaviors, examine connections and patterns in activity, predict future moves, as well as identify and avert possible terrorist attacks.
It examines the relationships of terrorist attacks, such as weapon type and attack time, and senses terrorist behaviors through such connections.
NEPAR has two main phases: building networks by finding connections between events; and using unified detection approach that combines proposed network topology and pattern recognition approaches.
The framework first distinguishes the characteristics of potential terrorist attacks by studying the relationship between previous attacks.
A comparison of the results with existing information demonstrates that such method successfully and accurately predicted most characteristics of the attacks by over 90%.
Afterward, the researchers recommend a unified detection approach applying pattern classification to setup the features and topology of incidents in detecting terrorist attacks with high accuracy as well as to recognize the extension of attacks (90% accuracy), terrorist goals (92% accuracy), and multiple attacks (96% accuracy).
Such framework provides government the ability to control behaviors of terrorists so as to minimize the risk of possible activities.
Tutun said these results could allow law enforcement agencies to suggest reactive strategies.
“Terrorists are learning, but they don’t know they are learning. If we can’t monitor them through social media or other technologies, we need to understand the patterns. Our framework works to define which metrics are important,” he said in a statement. “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. Maybe one attack in the past and another attack have a big relationship, but nobody knows. We tried to extract this information.”
Tutun thinks policymakers can make use of such approaches for time-sensitive detection and understanding of terrorist activities, enabling protection to prevent future attacks.
“When you solve the problem in Baghdad, you solve the problem in Iraq. When you solve the problem in Iraq, you solve the problem in the Middle East. When you solve the problem in the Middle East, you solve the problem in the world,” he said. “Because when we look at Iraq, these patterns are happening in the USA, too.”
Assisting and advising Tutun in his research was Mohammad Khasawneh, who is a professor and department head of Binghamton’s Systems Science and Industrial Engineering.
Expert Systems with Applications journal published the said research, “New framework that uses patterns and relations to understand terrorist behaviors.”