Urban analytics in the context of public safety

Abstract

Given a collection of geolocated activities, the goal of urban analytics in the context of public safety is to discover the underlying motives of people that affect their movement/activity patterns in space and time. Understanding the spatial patterns from urban mobility/activity datasets is an important task in public safety, city planning and sociology since these may reveal the underlying causes of crimes and safety issues, as well as behavior changes of individuals. Avoidance patterns are a type of behavioral change characterized by a lack of movement contrary to expectation. Avoidance pattern detection is a challenging task due to the lack of observations (e.g. lack of movement), defining the expected "normal" movement and large datasets (i.e. high number of GPS trajectories which are spread across the study area and large road network graphs). In addition, these challenges are exacerbated by the complicated and often hidden drivers of human activities and the complex relationships and dependencies between the spatially associated features. In this paper, we will provide a brief overview of the state-of-the-art spatial data science approaches in the context of avoidance patterns. First, we introduce the background from the domain (i.e. public safety) perspective, followed by an overview of the current state-of-the-art work. Then we will discuss possible future directions that may help shape future research on the topic.