CaSPR Lab


iSafe: Context Aware Public Safety for Smart Cities


Recent technological advances, in particular mobile devices and online social networks, have paved the way toward a smarter management of resources in today’s cities. As population density grows and natural disasters and man-made incidents (e.g., hurricanes, earthquakes, riots) impact increasing number of people, maintaining the safety of citizens, an essential smart city component, becomes a problem of paramount significance and difficulty.

We envision a system where users are seamlessly made aware of their safety in a personalized manner, through quotidian experiences such as navigation, mobile authentication, choosing a restaurant or finding a place to live. We propose to achieve this vision through a framework for defining public safety. Intuitively, public safety aims to answer the question “Will location L present any danger for user A when she visits L at a future time T ”?

In this project we investigate the combination of space and time indexed crime datasets, with mobile technologies and online social networks to provide personalized and context aware safety recommendations for mobile and social network users. Specifically, we first define location centric, static crime and safety labels, based on recorded crime events. The figure on the right maps crime levels in the Miami-Dade county.

We take advantage of observed crime behavior periodicities, to conjecture the fact that location safety values are predictable. To verify this hypothesis, we investigate the ability of timeseries forecasting tools to predict future location crime and safety index values based on recorded crime events. For example, the figure to the left compares the predictions of monthly robberies in Miami-Dade of time series forecasting algorithms including ARIMA, LES and ANN, with actual, observed data. The algorithms are trained on the previous 1 year of crime data collected by and made public by police departments in the county.

Moreover, we use mobile device and geosocial network technologies to record the trajectory trace of a user: the set of (location, time) pairs where the user has been present. When insufficient crime information exists at a given location, we propose to augment the ``context'' of the location with data collected from co-located mobile devices and geosocial networks like Yelp.

One question we need to answer is whether there exists a relation between the rating of a venue and the safety of its location. For this, we first mapped each venue in the Miami- Dade county to its corresponding census block, then computed Crime Index values for each block using the crime events of 2011. The figure on the right shows the corresponding mosaic plot, displaying the relationship between ratings and CI values: the areas of the rectangles are proportional to the probabilities of the user ratings and to the conditional probabilities of the CI levels. It shows that the bulk of the Yelp venues (even low rated ones) are in places where crime levels are low.

We implemented iSafe, a preliminary solution as a (i) web server, (ii) a browser plugin running in the user’s browser and (iii) a mobile application. We have implemented the location centric static safety labeling component of iSafe for a mobile application using Android. The mobile iSafe represents safety using five color labels ranging from green (safe) to red (unsafe). The figure on the left shows a snapshot of the mobile iSafe app. iSafe has a separate background service that displays in the status bar of the device, the safety color label of the user’s current location.

People

Publications

  • [IEEE TPDS] "Towards Safe Cities: A Mobile and Social Networking Approach"
    Jaime Ballestores, Bogdan Carbunar, Mahmudur Rahman, Naphtali Rishe, S.S. Iyengar.
    IEEE Transactions on Parallel and Distributed Systems (TPDS), Volume 25, Issue 9, 2014. [pdf] [supplemental material]

  • [IEEE LCN] Safe Cities. A Participatory Sensing Approach.
    Jaime Ballersteros, Mahmudur Rahman, Bogdan Carbunar, Naphtali Rishe.
    To appear in the 37th IEEE Conference on Local Computer Networks (LCN) [acceptance rate=29%], Orlando, October 2012 [pdf]