594 – Recent Advances in Statistical Process Control and Monitoring Research
Detecting Changes in Resilience And/or Level of Coordination in Terrorist Groups
Vasanthan Raghavan
Qualcomm Flarion Technologies
Activity profiles of terrorist groups show frequent spurts and downfalls corresponding to changes in organizational dynamics, e.g., changes in tactics/strategies, capabilities/resources, etc. The goal of this work is the quick detection of such patterns and in general, prediction of macroscopic trends in group dynamics. Prior work in this area are either based on time-series analysis techniques, self-exciting hurdle models, or hidden Markov models. While these approaches detect spurts and downfalls reasonably accurately, they are all based on model learning -- a task that is difficult in practice because of the "rare" nature of terrorist attacks from a model learning perspective. In this talk, we pursue a non-parametric majorization theory-based framework for spurt detection in activity profiles. In addition to being computationally simple, this approach can also clearly delineate spurts as those arising due to changes in resilience and/or level of coordination in the group.