Abstract
Sensor network infrastructures are widely used in smart cities to monitor and analyze urban traffic flow. Starting from punctual information coming from traffic sensor data, traffic simulation tools are used to create the digital twin” mobility data model that helps local authorities to better understand urban mobility. However, sensors can be faulty and errors in sensor data can be propagated to the traffic simulations, leading to erroneous analysis of the traffic scenarios. Providing real-time anomaly detection for time series data streams is highly valuable since it enables to automatically recognize and discard or repair sensor faults in time-sensitive processes. In this paper, we implement a data cleaning process that detects and classifies traffic anomalies distinguishing between sensor faults and unusual traffic conditions, and removes sensor faults from the input of the traffic simulation model, improving its performance. Experiments conducted on a real scenario for 30 days have demonstrated that anomaly detection coupled with anomaly classification boosts the performance of the traffic model in emulating real urban traffic.
Highlights
Investigation is an important element in many application domains such as fault detection, privacy and cybersecurity, communication networks, and social media
In the smart city context, through deploying Internet of Things (IoT) technologies, many aspects of the urban environment can be monitored in real-time such as mobility, pollution, parking, waste, lighting
Since observations coming from traffic sensors are often used as input of customized traffic models that simulate urban traffic flows in real-time, this paper examines and discusses the improvement provided by the anomaly detection and classification method by comparing the traffic model outputs, considering or excluding sensor faults
Summary
Investigation is an important element in many application domains such as fault detection, privacy and cybersecurity, communication networks, and social media. Analysis of traffic data is an essential component of intelligent transportation system applications crucial for smart cities. Traffic data collected through sensors such as induction loop detectors often contain anomalies, e.g. due to malfunctioning detectors or anomalous traffic conditions. Such anomalies can heavily affect the results of the subsequent analysis like traffic flow analysis, monitoring, and prediction. Traffic models are essential tools for road traffic analysis and simulation of urban mobility and the deployment of intelligent transportation system applications. Real-time simulations can be performed using as input the traffic sensors data to emulate the traffic flow in the entire urban context. The detection of anomalies in the input has to be done in a short time
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
