Detecção de Anomalias Frequentes no Transporte Rodoviário Urbano

Title: Detecção de Anomalias Frequentes no Transporte Rodoviário Urbano

Venue: SBBD 2018

Date: August / 2018

Location: Rio de Janeiro, RJ – Brasil

Abstract:

The growth of urban population and, consequently, the number of vehicles causes the increase of traffic jams and emission of polluting gases. In this context, we observe the intensification of papers that aim to identify bottlenecks and their causes. These papers propose methodologies that use trajectory data model and aim to explain systemic behaviors. This article proposes the identification and classification of anomalies in the urban road transport system from space-time aggregations to permanent objects. The methodology consists of pre-processing of data, identification of anomalies, identification, and classification of frequent patterns. Through it, we can identify the systemic and specific behaviors on the urban transit of Rio de Janeiro.

Presentation

About Eduardo Ogasawara
I am a Professor of the Computer Science Department of the Federal Center for Technological Education of Rio de Janeiro (CEFET / RJ) since 2010. I hold a PhD in Systems Engineering and Computer Science at COPPE / UFRJ. Between 2000 and 2007 I worked in the Information Technology (IT) field where I acquired extensive experience in workflows and project management. I have solid background in the Databases and my primary interest is Data Science. He currently studies space-time series, parallel and distributed processing, and data preprocessing methods. I am a member of the IEEE, ACM, INNS, and SBC. Throughout my career I have been presenting consistent number of published articles and projects approved by the funding agencies, such as CNPq and FAPERJ. I am also reviewer of several international journals, such as VLDB Journal, IEEE Transactions on Service Computing and The Journal of Systems and Software. Currently, I am heading the Post-Graduate Program in Computer Science (PPCIC) of CEFET / RJ.

Comments are closed.