Creative activity modeling for handling surprises in asymmetric attacks

Asymmetric warfare today has become a mean for less militarily advanced troops to battle against the more militarily advanced ones. This may also be extended onto civilian grounds, and many of these attacks have led to priceless loss of life and social well-being. One of the common characteristics of many of these attacks is the element of surprise. Those who carry out the attacks normally try their best to ensure that no one knows what or where the attack is to take place in order to ensure the highest degree of damage. In this work, we propose a framework for developing a decision support tool for defence personnel in dealing with this kind of threats. The framework integrates three well-known machine learning concepts resulting from research in artificial intelligence and machine learning. By reasoning based on the historical attack patterns, the use of the proposed framework allows one to realise what may happen given a set of previous acts and a set of factors currently observed.