00743088

Component

https://doi.org/10.3141/1588-11

http://scholar.google.com...ddis&publication_year=1997

A method combining machine learning and regression analysis to automatically and intelligently update predictive models used in the Kansas Department of Transportation's (KDOT's) internal management system is presented. The predictive models used by KDOT consist of planning factors (mathematical functions) and base quantities (constants). The duration of a functional unit (defined as a subactivity) is determined by the product of a planning factor and its base quantity. The availability of a large data base on projects executed over the past decade provided the opportunity to develop an automated process updating predictive models based on extracting information from historical data through machine learning. To perform the entire task of updating the predictive models, the learning process consists of three stages. The first stage derives the numerical relationship between the duration of a functional unit and the project attributes recorded in the data base. The second stage finds the functional units with similar behavior--that is, identifies functional units that can be described by the same shared planning factor scaled in terms of their own base quantities. The third stage generates new planning factors and base quantities. A system called PFactor built on the basis of the three-stage learning process shows good performance in updating KDOT's predictive models.

This paper appears in Transportation Research Record No. 1588, Intelligent Transportation Systems and Artificial Intelligence.

English

p. 86-94

1997

Transportation Research Record

0309061628

Figures (5) ; References (17) ; Tables (2)

History; Machine learning; Management; Mathematical models; Modernization; Programming (Planning); Regression analysis; Scheduling; State departments of transportation; Time series

Management systems

Kansas

Administration and Management; Data and Information Technology; Highways; History; Planning and Forecasting; I72: Traffic and Transport Planning

TRIS, TRB, ATRI

Nov 5 1997 12:00AM

• AUTOMATIC VEHICLE IDENTIFICATION TECHNOLOGY APPLICATIONS TO TOLL COLLECTION SERVICES
• COST-BENEFIT ANALYSIS ON DEPLOYMENT OF AUTOMATED HIGHWAY SYSTEMS
• CRITICAL REVIEW OF EXPERT SYSTEM VALIDATION IN TRANSPORTATION
• DEVELOPING A MARKET-SENSITIVE INTELLIGENT TRANSPORTATION SYSTEMS EDUCATIONAL PROGRAM
• DYNAMIC TRAFFIC ASSIGNMENT: GENETIC ALGORITHMS APPROACH
• EVALUATING EFFECTIVENESS OF REAL-TIME ADVANCED TRAVELER INFORMATION SYSTEMS USING A SMALL TEST VEHICLE FLEET
• FRAMEWORK FOR DEVELOPING A REGIONAL SYSTEM ARCHITECTURE FOR INTELLIGENT TRANSPORTATION SYSTEMS
• GUIDELINES FOR FUNDING OPERATIONS AND MAINTENANCE OF INTELLIGENT TRANSPORTATION SYSTEMS/ADVANCED TRAFFIC MANAGEMENT SYSTEMS
• INTELLIGENT TRANSPORTATION SYSTEMS AND SUSTAINABLE COMMUNITIES: FINDINGS OF A NATIONAL STUDY
• MACROSCOPIC MODELING OF FREEWAY TRAFFIC USING AN ARTIFICIAL NEURAL NETWORK
• PERSPECTIVES ON DRIVER PREFERENCES FOR DYNAMIC ROUTE GUIDANCE SYSTEMS
• PLANITS: STRUCTURING AND SUPPORTING THE INTELLIGENT TRANSPORTATION SYSTEMS PLANNING PROCESS
• PROMOTING ADVANCED TRAVELER INFORMATION SYSTEMS AMONG CELLULAR AND LAND-LINE PHONE USERS: SMARTRAVELER EXPERIENCE IN BOSTON
• REAL-TIME MULTIPLE-OBJECTIVE PATH SEARCH FOR IN-VEHICLE ROUTE GUIDANCE SYSTEMS
• TECHNICAL AND ECONOMIC VIABILITY OF AUTOMATED HIGHWAY SYSTEMS: PRELIMINARY ANALYSIS
• TRAFFIC ANALYSIS FOR HIGHWAY-TO-HIGHWAY INTERCHANGES ON AUTOMATED HIGHWAY SYSTEMS: CONGESTION IN ABSENCE OF DEDICATED RAMPS
• WILLINGNESS TO PAY FOR ADVANCED TRAVELER INFORMATION SYSTEMS: SMARTRAVELER CASE STUDY