Abstract
Accurate traffic sensor data is essential for traffic operation management systems and acquisition of real-time traffic surveillance data depends heavily on the reliability of the traffic sensors (e.g., wide range detector, automatic traffic recorder). Therefore, detecting the health status of the sensors in a traffic sensor network is critical for the departments of transportation as well as other public and private entities, especially in the circumstances where real-time decision is required. With the purpose of efficiently determining the sensor health status and identifying the failed sensor(s) in a timely manner, this paper proposes a graphical modeling approach called spatiotemporal pattern network (STPN). Traffic speed and volume measurement sensors are used in this paper to formulate and analyze the proposed sensor health monitoring system and historical time-series data from a network of traffic sensors on the Interstate 35 (I-35) within the state of Iowa is used for validation. Based on the validation results, we demonstrate that the proposed approach can: (i) extract spatiotemporal dependencies among the different sensors which leads to an efficient graphical representation of the sensor network in the information space, and (ii) distinguish and quantify a sensor issue by leveraging the extracted spatiotemporal relationship of the candidate sensor(s) to the other sensors in the network.
Highlights
Due to the increasing dependencies on relatively cheaper sensors for condition monitoring, diagnostics, and decision mak-ing in large infrastructure systems (Wenjie, Lifeng, Zhanglong, & Shiliang, 2005) (Wang, Zhang, Sun, Gong, & Cui, 2011), the reliability of the sensors themselves is critical in terms of collecting accurate information from the system of interest
According to the U.S Department of Transportation, the sensors are typically installed about every 2 miles and facilitating sensor redundancy is not feasible due to the sheer length of roadways that requires monitoring in each state and the cost of sensors deployed (e.g., microwave radar sensor that covers multiple lanes costs at least $6200 without the installation fee based on the costs database of the U.S DOT in 2002 (Klein et al, 2006))
Researchers have proposed different approaches according to different objective functions, such as uniform partitioning (UP), maximum entropy partitioning (MEP), statistically similar discretization (SSD) (Sarkar & Srivastav, 2016), and maximally bijective discretization (MBD)(Sarkar, Srivastav, & Shashanka, 2013)
Summary
Due to the increasing dependencies on relatively cheaper sensors for condition monitoring, diagnostics, and decision mak-. Most of the previous studies tend to use sensor redundancy approaches by considering one data source as the ground truth to validate another data source (Sallans, Bruckner, & Russ, 2005) Such systems typically have multiple collocated sensors to monitor the critical points (Jeong, Kim, Lee, & Dornfeld, 2006) (Harris et al, 1995), which may be reasonable for expensive, safety-critical systems or small systems where only limited monitoring points are needed (Bhuiyan, Wang, & Wu, 2009). Discovering the relationships among the sensors during operation with respect to the (historical) nominal conditions can provide us indications whether a sensor is healthy or not In this context, this work applies a recently proposed spatiotemporal graphical modeling approach, called the spatiotemporal pattern network (STPN, built on the concepts of symbolic dynamics filtering, SDF) (Sarkar, Sarkar, Virani, Ray, & Yasar, 2014; Liu, Ghosal, Jiang, & Sarkar, 2017; Jiang & Sarkar, 2015), to build a novel sensor health monitoring framework for traffic sensors. The results obtained with the three different methods are described in Section 4 and the paper is summarized in Section 5 along with the directions of future research
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
