El próximo 4 de febrero de 2016, el Prof. Dr. Jorge Mateu, (Catedrático de Estadística e Investigación Operativa, Departamento de Matemáticas, Campus Riu Sec, Universitat Jaume I), impartirá la conferencia: Inhomogeneous spatio-temporal log-Gaussian Cox processes. Application to criminal surveillance. La conferencia tendrá lugar en el Salón de Grados de la Facultad de Matemáticas de la Universidad de Santiago de Compostela a las 19:00h.

Bajo la dirección del Profesor Jorge Mateu, la Universidad Jaume I de Castellón ha desarrollado un modelo matemático, sustentando por Pred-Crime, un algoritmo para predecir y prevenir delitos, que tiene como objetivo adelantarse al futuro en base a los delitos ocurridos en el pasado. Se trata de un modelo de inteligencia policial que utiliza una inmensa base de datos procedente de los delitos cometidos, que alimenta una serie de modelos y algoritmos matemáticos para generar mapas de riesgo que ayudaran a prevenir y predecir delitos.

 

Crime, Gaussian random fields, Log-Gaussian Cox processes, Nonstationarity, Spatio-temporal point patterns, Surveillance

Surveillance systems have their origins in industrial applications, where the name refers to the routine collection and analysis of data for quality control purposes. More recently, the increasing need for early detection of disease outbreaks to inform prevention and control policies has given rise to an extensive literature on public health surveillance systems. Surveillance methods have been developed for other areas of application, for example, to detect acts of bioterrorism. Our motivation is from criminology, in particular prediction of crime events, and detection of emergent clusters in the spatio-temporal distribution of such crimes.
 
We propose a method for conducting likelihood-based inference for a class of nonstationary spatio-temporal log-Gaussian Cox processes. We derive an approximate conditional likelihood function for spatio-temporal log-Gaussian Cox processes. The method uses low-rank convolution-based models to capture the spatio-temporal correlation structure, to alleviate the computational burden involved in applying likelihood-based methods to full rank models.
 
We describe an application to a surveillance system to model the spatio-temporal  distribution of crime events with the aim of predicting and detecting emergent spatio-temporal clusters of crime events.
 

 

• MÁS INFORMACIÓN:

 ITMATI, Departamento de Estadística e Investigación Operativa, USC