Neural Network Models for Traffic Control and Congestion Prediction

Estimating road traffic congestion from cellular handoff information using cell-based neural networks and K-means clustering

“…Several research efforts applied neural network techniques for road traffic estimation [7][8][9][10] using traffic volume, speed, and density data gathered from various kinds of sensors. In our previous work [6], we also used a neural network to predict the degrees of congestion from CDT data.…”

How to Provide Accurate and Robust Traffic Forecasts Practically?

“…Over the past decade, another nonparametric technique, artificial neural networks (ANNs) have been applied in traffic forecasting because of their strong ability to capture the indeterministic and complex nonlinearity of time series (Smith & Demetsky, 1994Chang & Su, 1995;Dougherty & Cobbet, 1997;Lam & Xu, 2000;Park et al, 1999;Dharia & Adeli, 2003;Wei et al, 2009;Wei & Lee 2007;Lee, 2009). Motivated by the universal approximation property, neural network models ranging from purely static to highly dynamic structures include the multilayer perceptrons (MLPs) (Clark et al, 1993;Vythoulkas, 1993;Lee & Fambro, 1999;Gilmore & Abe, 1995;Ledoux, 1997;Innamaa, 2000;Florio & Mussone, 1996;Yun et al, 1998;Zhang, 2000;Chen et al, 2001), the radial basis function (RBF) ANNs (Lyons et al, 1996;Park & Rilett, 1998;Chen et al, 2001), the time-delayed ANNs (Lingras et al, 2000;Lingras & Mountford, 2001;Yun et al, 1998;Yasdi 1999;Abdulhai et al, 1999;Dia, 2001;Ishak & Alecsandru, 2003), the recurrent ANNs (Dia, 2001;Van Lint et al, 2002, and the hybrid ANNs (Abdulhai et al, 1999;Chen et al, 2001;Lingras & Mountford, 2001;Park, 2002;Yin et al, 2002;Vlahogianni ...…”

Towards Developing a Travel Time Forecasting Model for Location-Based Services: A Review

“…Their learning capabilities make themselves a suitable approach for solving complicated problems like estimating current travel times from traffic flow patterns (Palacharla and Nelson, 1995). Recently, neural networks have gained a significant attention for transportation applications such as traffic flow modeling, traffic signal control, and transportation planning (Gilmore and Abe, 1995;Smith and Demetsky, 1997;Dochy et al, 1995). Among a number of neural network paradigms, backpropagation, a multi-layer learning regime, has been often applied to forecast traffic flow and congestion because of its ability to model relationships among continuously valued variables Dougherty et al, 1993).…”

“…Traffic simulation models have been developed much earlier than their applications in travel time forecasting, but the massive computation in simulating traffic behaviors has hindered their applications in travel time forecasting for many years. -Dochy et al, 1995-Gilmore and Abe, 1995-Palacharla and Nelson, 1995 As a result, some formulations in simulating traffic behaviors have adopted parallel computing technologies (Bush, 1999;Nagel et al, 1998;Berkbigler et al, 1997). Neural network models became popular in travel time forecasting during the 1990s, and the recent development of neural network models have a strong influence in forecasting travel time.…”

“…To apply DTA models in forecasting travel time, it is necessary to estimate dynamic travel demand, and hence obtaining dynamic origin-destination (OD) tables is a major issue for a successful DTA model. To improve existing DTA models, which are mostly based on static user equilibrium and system optimal traffic assignment models, several models have adopted genetic algorithms and eural networks (Sadek et al, 1997;Gilmore and Abe, 1995).…”