Q-Net is a state-space Kalman filter augmented with neural networks that learns time-varying gains to integrate loop detector counts and segment-wise average speeds for real-time queue length estimation at signalized intersections.
Examining queue-jumping phenomenon in heterogeneous traffic stream at signalized intersection using uav-based data
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Q-Net: Queue Length Estimation via Kalman-based Neural Networks
Q-Net is a state-space Kalman filter augmented with neural networks that learns time-varying gains to integrate loop detector counts and segment-wise average speeds for real-time queue length estimation at signalized intersections.