Search

Forecasting accuracy is an important issue for successful intelligent traffic management, especially in the domain of traffic efficiency and congestion reduction. The dawning of the big data era brings opportunities to greatly improve prediction accuracy. In this paper, we propose a novel model, stacked autoencoder Levenberg-Marquardt model, which is a type of deep architecture of neural network approach aiming to improve forecasting accuracy. The proposed model is designed using the Taguchi method to develop an optimized structure and to learn traffic flow features through layer-by-layer feature granulation with a greedy layerwise unsupervised learning algorithm. It is applied to real-world data collected from the M6 freeway in the U.K. and is compared with three existing traffic predictors. To the best of our knowledge, this is the first time that an optimized structure of the traffic flow forecasting model with a deep learning approach is presented. The evaluation results demonstrate that the proposed model with an optimized structure has superior performance in traffic flow forecasting. [ABSTRACT FROM AUTHOR]

One of the basic parameters which describes road traffic is Annual Average Daily Traffic (AADT). Its accurate determination is possible only on the basis of data from the continuous measurement of traffic. However, such data for most road sections is unavailable, so AADT must be determined on the basis of short periods of random measurements. This article presents different methods of estimating AADT on the basis of daily traffic (VOL), and includes the traditional Factor Approach, developed Regression Models and Artificial Neural Network models. As explanatory variables, quantitative variables (VOL and the share of heavy vehicles) as well as qualitative variables (day of the week, month, level of AADT, the cross-section, road class, nature of the area, spatial linking, region of Poland and the nature of traffic patterns) were used. Based on comparisons of the presented methods, the Factor Approach was identified as the most useful. [ABSTRACT FROM AUTHOR]

TNMAide -- for use in the FHWA's Traffic Noise Model (TNM) -- is a spreadsheet tool that aids in the determination of the worst noise hour of the day, as required by 23 CFR 772. The U.S. Department ofTransportation recently designated 44 infrastructure projects around the country as Infrastructure for Rebuilding America (INFRA) Extra -- a designation that makes project sponsors eligible to apply for credit assistance for up to 49 percent of project costs. FHWA Releases Air Quality and Noise Analysis Tools In 2021, the Federal Highway Administration developed the Database for Air Quality and Noise Analysis (DANA) tool. [Extracted from the article]

• We introduce a machine learning nudging framework for reduced order models. • Our approach puts forth a realtime predictive tool for wake-vortex transport and decay systems. • We explore the effects of measurements noise and state estimate uncertainty on modeling performance. • We found that our method effectively handles different levels of temporal and spatial measurement sparsity. We put forth a long short-term memory (LSTM) nudging framework for the enhancement of reduced order models (ROMs) of fluid flows utilizing noisy measurements for air traffic improvements. Toward emerging applications of digital twins in aviation, the proposed approach allows for constructing a realtime predictive tool for wake-vortex transport and decay systems. We build on the fact that in realistic application, there are uncertainties in initial and boundary conditions, model parameters, as well as measurements. Moreover, conventional nonlinear ROMs based on Galerkin projection (GROMs) suffer from imperfection and solution instabilities, especially for advection-dominated flows with slow decay in the Kolmogorov n -width. In the presented LSTM nudging (LSTM-N) approach, we fuse forecasts from a combination of imperfect GROM and uncertain state estimates, with sparse Eulerian sensor measurements to provide more reliable predictions in a dynamical data assimilation framework. We illustrate our concept by solving the two-dimensional vorticity transport equation. We investigate the effects of measurements noise and state estimate uncertainty on the performance of the LSTM-N behavior. We also demonstrate that it can sufficiently handle different levels of temporal and spatial measurement sparsity, and offer a huge potential in developing next-generation digital twin technologies for aerospace applications. [ABSTRACT FROM AUTHOR]

The article discusses how math could fix traffic jams. During rush hour traffic congestion can be sometimes caused by a seemingly unknown reason. Topics include an overview of research by a mechanical engineer at the University of Alberta, who produced a model which shows how phantom traffic jams develop. The mathematical representation of traffic jams as alternating waves of automobile density and how improving data flow could ease traffic jams is also presented.

The article describes the Fudong Che global positioning system (GPS) program in Beijing, China. The program analyzes data collected from GPS sensors in all 66,000 of Beijing's taxis in order to build real-time models of automobile traffic in the city. Through this system, drivers will be able to learn the least congested route to a given destination.

Statistics about daily bicycle trips and motor vehicle trips in New York City from 2010 to 2015 are presented.

The article offers information on the views of a commission on New York Mayor Michael Bloomberg's traffic congestion pricing proposal for New York City. The commission is likely to overhaul the proposal by moving the northern boundary from 86th Street to 60th Street and simplifying enforcement. According to Marc Shaw, chairman of the commission, the overview plan is to find a way to reduce congestion and do it in a way that doesn't have a negative impact on the economy.