article · IEEE Transactions on Intelligent Transportation Systems
Deploying physical sensors across every road link in a network is impractical, and sensors do not directly capture origin-destination travel demand. To resolve these challenges, a combined deep learning architecture and global sensitivity analysis tool simultaneously tackles traffic demand estimation and optimal sensor placement. The deep learning model utilises a stacked sparse autoencoder to reconstruct network-wide origin-destination flows from observed link flows, effectively reversing the traditional traffic assignment problem by linking flow data with network topology. The architecture is trained using synthetic link flow data generated from historical demand. Global sensitivity analysis then ranks the relative importance of each link to pinpoint where sensors should be installed. Across validation tests on two networks of different sizes, the approach demonstrated low root-mean-square error while decreasing the volume of link flow measurements needed.
Managing modern traffic networks requires understanding how people move from start to finish, but monitoring every street is prohibitively expensive. By identifying the critical points where sensors deliver the most useful data and using machine learning to reconstruct full traffic patterns from partial observations, authorities can monitor and manage congestion far more efficiently with fewer physical devices.
This technique could be adopted by municipal transport agencies, urban planning consultants, and intelligent transportation systems developers to cut hardware installation costs. Because the system has been tested only on two network models using synthetic training data, it remains at the stage of applied experimental research, requiring real-world field validation before commercial integration into operational traffic management platforms.
AI-generated from the published abstract. Always read the original work before citing.
Traffic control and management applications require the full realization of traffic flow data. Frequently, such data are acquired by traffic sensors with two issues: it is not practicable or even possible to place traffic sensors on every link in a network; sensors do not provide direct information about origin–destination (O–D) demand flows. Therefore, it is imperative to locate the best places to deploy traffic sensors and then augment the knowledge obtained from this link flow sample to predict the entire traffic flow of the network. This article provides a resilient deep learning (DL) architecture combined with a global sensitivity analysis tool to solve O–D estimation and sensor location problems simultaneously. The proposed DL architecture is based on the stacked sparse autoencoder (SAE) model for accurately estimating the entire O–D flows of the network using link flows, thus reversing the conventional traffic assignment problem. The SAE model extracts traffic flow characteristics and derives a meaningful relationship between traffic flow data and network topology. To train the proposed DL architecture, synthetic link flow data were created randomly from the historical demand data of the network. Finally, a global sensitivity analysis was implemented to prioritize the importance of each link in the O–D estimation step to solve the sensor location problem. Two networks of different sizes were used to validate the performance of the model. The efficiency of the proposed method for solving the combination of traffic flow estimation and sensor location problems was confirmed from a low root-mean-square error with a reduction in the number of link flows required.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1109/tits.2023.3344533
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
