Skip to Main Content
Smart cities combine technology and human resources to improve the quality of life and reduce expenditures. Ensuring the safety of city residents remains one of the open problems, as standard budgetary investments fail to decrease crime levels. This work takes steps toward implementing smart, safe cities, by combining the use of personal mobile devices and social networks to make users aware of the safety of their surroundings. We propose novel metrics to define location and user based safety values. We evaluate the ability of forecasting techniques including autoregressive integrated moving average (ARIMA) and artificial neural networks (ANN) to predict future safety values. We devise iSafe, a privacy preserving algorithm for computing safety snapshots of co-located mobile device users and integrate our approach into an Android application for visualizing safety levels. We further investigate relationships between location dependent social network activity and crime levels. We evaluate our contributions using data we collected from Yelp as well as crime and census data.