Abstract
Mobile information systems agendas are increasingly becoming an essential part of human life and they play an important role in several daily activities. These have been developed for different contexts such as public facilities in smart cities, health care, traffic congestions, e-commerce, financial security, user-generated content, and crowdsourcing. In GIScience, problems related to routing systems have been deeply explored by using several techniques, but they are not focused on security or crime rates. In this paper, an approach to provide estimations defined by crime rates for generating safe routes in mobile devices is proposed. It consists of integrating crowd-sensed and official crime data with a mobile application. Thus, data are semantically processed by an ontology and classified by the Bayes algorithm. A geospatial repository was used to store tweets related to crime events of Mexico City and official reports that were geocoded for obtaining safe routes. A forecast related to crime events that can occur in a certain place with the collected information was performed. The novelty is a hybrid approach based on semantic processing to retrieve relevant data from unstructured data sources and a classifier algorithm to collect relevant crime data from official government reports with a mobile application.
Highlights
Nowadays, millions of citizens go through the streets of Mexico City, taking some specific routes that are planned by using either public or private transportation or even walking
We propose a hybrid approach embedded in a mobile application, which automatically combines social and official crime data, by using an ontology exploration method and the Bayes algorithm to classify crime activities, according to the Mexican penal code
The mobile application was implemented in Android 4.0, and the tests were performed in mobile devices
Summary
Millions of citizens go through the streets of Mexico City, taking some specific routes that are planned by using either public or private transportation or even walking. There are well-known routes that citizens most often take for their traveling, new routes (probably unsafe) might be experimented especially for newcomers. This generation is not an easy task; generally it is made by routing systems that search the shortest or fastest paths [1]. Many routing systems are based on processing linguistic techniques and treating with name of places to define the origin and destination. These works have faced well-known linguistic problems (e.g., polysemy). The novelty of our proposal is the use of two heterogeneous data sources: corpus of tweets and government official reports, which were integrated and processed by the Bayes algorithm for obtaining a risk level applied to routes in a mobile system
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
