Multilayer Artificial Neural Networks for Level-of-Service Analysis of Signalized Intersections

Saito, Mitsuru; Fan, Jianzhong

doi:10.3141/1678-26

Cited by 2 publications

(3 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…LOSANN is a computer-simulated artificial neural network that consists of linear combination functions and activation functions. 2,6 The output of LOSANN is on the right, and the inputs, shown as variables in the braces, are on the left, as Equation (1) shows. During the training process, the output and the input are given, but the weights in LOSANN are not fixed; that is, they need to be adjusted.…”

Section: Traffic Information Geometric Condition Signalization Conditionmentioning

confidence: 99%

“…Detailed descriptions of LOSANN can be found elsewhere. 2,6 For detailed discussions on types of artificial neural network structures, the reader is referred to Haykin. 3 The input interface of the trained LOSANN receives two kinds of information: the traffic environment data and the range of cycle length that will be analyzed for optimal signal timing.…”

Section: Introductionmentioning

confidence: 99%

“…In the present artificial neural network model structure, LOSANN considers almost all the signal-timing factors used by the HCM method. 2,6 This article briefly discusses the relation between LOSANN and OTSTM and then focuses on the development of an optimal solution search algorithm called direction search for determining optimal cycle length and green-time split, theoretical comparison of computational time between the enumeration method and the direction method, and their numerical examples. This article demonstrates that an artificial neural network-based signal optimization system may be feasible once the artificial neural network is trained properly.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Artificial Neural Network–Based Heuristic Optimal Traffic Signal Timing

Saito

Fan²

2000

Computer aided Civil Eng

Self Cite

View full text Add to dashboard Cite

A software called Optimal Traffic Signal Control System (OTSCS) was developed by us for testing the feasibility of dynamically controlling a traffic signal by finding optimal signal timing to minimize delay at signalized intersections. It also was designed as a research tool to study the learning behavior of artificial neural networks and the properties of heuristic search methods. It consists of a level-of-service evaluation model that is based on an artificial neural network and a heuristic optimization model that interacts with the level-of-service evaluation model. This article discusses the latter model, named the Optimal Traffic Signal Timing Model (OTSTM). The OTSTM was applied to determine optimal signal timing of twophase traffic signals to evaluate the model's performance. Two search methods were employed: a depth-first search method (an enumeration method) and a direction-search method that we developed. It was found that the OTSTM with the direction search resulted in "optimal" signal timings similar to the depth-first search, which would always produce a global optimal timing. Yet the cost of the direction search, as measured by the CPU time of the computer used for analysis, was found to be much less than the cost of obtaining an optimal solution by the depth-first search cases-more than 10 times less. The study showed that once

show abstract

Section: Traffic Information Geometric Condition Signalization Conditionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Artificial Neural Network–Based Heuristic Optimal Traffic Signal Timing

Saito

Fan²

2000

Computer aided Civil Eng

Self Cite

View full text Add to dashboard Cite

show abstract

Real-Time Inductive-Signature-Based Level of Service for Signalized Intersections

Ritchie

2002

Transportation Research Record: Journal of the Transportation R

View full text Add to dashboard Cite

The Highway Capacity Manual (HCM) presents a procedure for estimating signalized intersection control delay, which is used to determine level of service (LOS) and to evaluate intersection performance. The HCM is used extensively by traffic engineers. However, it is intended as an offline decision support tool for planning and design. To meet user requirements of advanced traffic management and information systems, new LOS criteria are required for real-time intersection analysis. The objective of this research was to demonstrate a technique for development of such LOS criteria. The study used a new measure of effectiveness, called reidentification delay (RD), derived from analysis of vehicle inductive signatures and reidentification of vehicles traveling through a major signalized intersection in the city of Irvine, California. Two main issues regarding real-time LOS criteria were tackled. The first was how to determine the threshold values partitioning the LOS categories. To provide reliable real-time traffic information, the threshold values should be decided on so that RDs within the same LOS category would represent similar traffic conditions as much as possible. RDs in different LOS categories should also represent dissimilar traffic conditions. The second issue concerned the aggregation interval to use for RD in deriving LOS categories. An investigation of both fixed and cycle-based aggregation intervals was conducted. Several clustering techniques were then employed to derive LOS categories, including k-means, fuzzy, and self-organizing map approaches. The resulting real-time LOS criteria were then determined. The procedures used in this study are readily transferable to other signalized intersections for the derivation of real-time LOS.

show abstract

Multilayer Artificial Neural Networks for Level-of-Service Analysis of Signalized Intersections

Cited by 2 publications

References 1 publication

Artificial Neural Network–Based Heuristic Optimal Traffic Signal Timing

Artificial Neural Network–Based Heuristic Optimal Traffic Signal Timing

Real-Time Inductive-Signature-Based Level of Service for Signalized Intersections

Contact Info

Product

Resources

About