Towards detection of faulty traffic sensors in real-time

Nikolas Zygouras, Nikolaos Panagiotou, Ioannis Katakis, Dimitrios Gunopulos, Nikos Zacheilas, Ioannis Boutsis, Vana Kalogeraki

Research output: Contribution to journalConference articlepeer-review

Abstract

Detecting traffic events using the sensor network infrastructure is an important service in urban environments that enables the authorities to handle traffic incidents. However, irregular measurements in such settings can derive either from faulty sensors or from unpredictable events. In this paper, we propose an efficient solution to resolve in real-time the source of such irregular readings by examining the correlation and the consistency among neighbor sensors and exploiting the wisdom of the crowd. Our experimental evaluation illustrates the efficiency and practicality of our approach.

Original languageEnglish
Pages (from-to)53-62
Number of pages10
JournalCEUR Workshop Proceedings
Volume1392
Issue numberJanuary
Publication statusPublished - 1 Jan 2015
Event2nd International Workshop on Mining Urban Data, MUD 2015 - co-located with 32nd International Conference on Machine Learning, ICML 2015 - Lille, France
Duration: 11 Jul 2015 → …

Fingerprint

Dive into the research topics of 'Towards detection of faulty traffic sensors in real-time'. Together they form a unique fingerprint.

Cite this