Amin Ghafouri, Aron Laszka, Abhishek Dubey, Xenofon D. Koutsoukos
Proceedings of the 2nd International Workshop on Science of Smart City Operations and Platforms Engineering, SCOPE@CPSWeek 2017, Pittsburgh, PA, USA, April 21, 2017 2017
Faulty traffic sensors degrade performance of route planning systems and can cause suboptimal routing decisions. Existing detection methods often assume fixed thresholds without optimization. This work is innovative because it formulates sensor fault detection as an optimization problem that minimizes overall losses from sensor failures.
This paper presents methods for detecting faulty traffic sensors using prediction models and Gaussian processes, with application to route planning optimization. The authors develop algorithms to identify optimal detection thresholds that minimize losses caused by false positives and false negatives. The work applies the methodology to real traffic data from downtown Los Angeles.
The paper demonstrates that using Gaussian process-based prediction models enables effective detection of faulty traffic sensors. Results show optimal detection thresholds minimize total losses from both false positives and false negatives in route planning applications.
@inproceedings{Ghafouri2017,
author = {Ghafouri, Amin and Laszka, Aron and Dubey, Abhishek and Koutsoukos, Xenofon D.},
booktitle = {Proceedings of the 2nd International Workshop on Science of Smart City Operations and Platforms Engineering, SCOPE@CPSWeek 2017, Pittsburgh, PA, USA, April 21, 2017},
title = {Optimal detection of faulty traffic sensors used in route planning},
year = {2017},
pages = {1--6},
abstract = {In a smart city, real-time traffic sensors may be deployed for various applications, such as route planning. Unfortunately, sensors are prone to failures, which result in erroneous traffic data. Erroneous data can adversely affect applications such as route planning, and can cause increased travel time. To minimize the impact of sensor failures, we must detect them promptly and accurately. However, typical detection algorithms may lead to a large number of false positives (i.e., false alarms) and false negatives (i.e., missed detections), which can result in suboptimal route planning. In this paper, we devise an effective detector for identifying faulty traffic sensors using a prediction model based on Gaussian Processes. Further, we present an approach for computing the optimal parameters of the detector which minimize losses due to false-positive and false-negative errors. We also characterize critical sensors, whose failure can have high impact on the route planning application. Finally, we implement our method and evaluate it numerically using a real- world dataset and the route planning platform OpenTripPlanner.},
bibsource = {dblp computer science bibliography, https://dblp.org},
biburl = {https://dblp.org/rec/bib/conf/cpsweek/GhafouriLDK17},
category = {workshop},
contribution = {colab},
doi = {10.1145/3063386.3063767},
file = {:Ghafouri2017-Optimal_detection_of_faulty_traffic_sensors_used_in_route_planning.pdf:PDF},
keywords = {fault detection, traffic sensors, Gaussian processes, route planning, anomaly detection},
project = {cps-reliability,smart-transit,smart-cities},
tag = {ai4cps,platform,incident,transit},
timestamp = {Tue, 06 Nov 2018 16:59:05 +0100},
url = {https://doi.org/10.1145/3063386.3063767}
}