00676574

Component

http://onlinepubs.trb.org...trr/1994/1453/1453-010.pdf

https://scholar.google.co...arko&publication_year=1994

Traffic control along an urban rail corridor with closely spaced stations can be considered a sequence of decision-making stages. A train on an urban rail corridor that connects two terminal points with a number of intermediate stations can follow various regimes of moving and stopping, which identify individual driving scenarios. The execution of these regimes may result in different values of attributes that describe driving scenarios, namely, travel time, energy consumption, passenger comfort, and others. An attempt is made to demonstrate how to develop decision rules for driving scenarios along an urban rail corridor that can optimize travel time, energy consumption, and passenger comfort, using the concept of machine learning. Machine learning is a science that deals with the development and implementation of computational models of learning processes. The concept of knowledge acquisition through inductive learning as an intelligent vehicle-highway system approach is explored to establish some initial decision rules. A computer model, REGIME, was developed for the estimation of values of evaluation criteria, such as travel time, energy consumption, and passenger comfort levels for a hypothetical rail corridor for various driving scenarios. Next, a commercial learning system, ROUGH, was used in conjunction with the examples created through REGIME to develop decision rules. The learning algorithm is based on the theory of rough sets. The feasibility of machine learning in automated knowledge acquisition to develop decision rules for complex engineering problems, such as urban rail corridor control, is demonstrated. Further research is needed to verify the rules developed before these can be applied.

This paper appears in Transportation Research Record No. 1453, Intelligent Transportation Systems: Evaluation, Driver Behavior, and Artificial Intelligence. Distribution, posting, or copying of this PDF is strictly prohibited without written permission of the Transportation Research Board of the National Academy of Sciences. Unless otherwise indicated, all materials in this PDF are copyrighted by the National Academy of Sciences. Copyright © National Academy of Sciences. All rights reserved

01401256

English

p. 91-97

1994

Transportation Research Record

0309060613

Figures (2) ; References (10) ; Tables (8)

Algorithms; Computer models; Decision making; Energy consumption; Intelligent transportation systems; Machine learning; Optimization; Passenger comfort; Railroad traffic control; Travel time

Railroad corridors

Energy; Highways; Operations and Traffic Management; Public Transportation; Railroads

TRIS, TRB

Apr 13 1995 12:00AM

• APPLICATIONS OF ARTIFICIAL NEURAL NETWORKS TO INTELLIGENT VEHICLE-HIGHWAY SYSTEMS
• CRITERIA AND METHODS FOR EVALUATING INTELLIGENT TRANSPORTATION SYSTEM PLANS AND OPERATIONAL TESTS
• EFFECT OF MODELING ASSUMPTIONS ON EVOLUTION OF QUEUES IN A SINGLE CORRIDOR
• FRAMEWORK FOR EVALUATING INTELLIGENT VEHICLE-HIGHWAY SYSTEMS
• IMPROVED FREEWAY INCIDENT DETECTION USING FUZZY SET THEORY
• INFLUENCE OF TRAFFIC INFORMATION ON DRIVERS' ROUTE CHOICE BEHAVIOR
• MODELS OF COMMUTERS' INFORMATION USE AND ROUTE CHOICE: INITIAL RESULTS BASED ON SOUTHERN CALIFORNIA COMMUTER ROUTE CHOICE SURVEY
• REGIONAL APPROACH TO STRATEGIC INTELLIGENT VEHICLE HIGHWAY SYSTEM PLANNING IN ORANGE COUNTY
• SHORT-TERM TRAFFIC FLOW PREDICTION: NEURAL NETWORK APPROACH
• USE OF SYSTEM CHARACTERISTICS TO DEFINE CONCEPTS FOR AUTOMATED HIGHWAY SYSTEMS