A learning-based transportation oriented simulation system

This paper describes the conceptual development, operatonalization and empirical testing of : A Learning-based Transportation Oriented Simulation System. This activity-based model of activity-travel behavior is derived from theories of choice heuristics that consumers apply when making decisions in complex environments. The model, one of the most comprehensive of its kind, predicts which activities are conducted when, where, for how long, with whom, and the transport mode involved. In addition, various situational, temporal, spatial, spatial-temporal and institutional constraints are incorporated in the model. The decision tree is proposed as a formalism to represent an exhaustive set of mutually exclusive rules for each decision step in the model. A CHAID decision tree induction method is used to derive decision trees from activity diary data. The case study conducted to develop and test the model indicates that performance of the model is very satisfactory. We conclude therefore that the methodology proposed in this article is useful to develop computational process models of activity-travel choice behavior.

[1]  David A. Landgrebe,et al.  A survey of decision tree classifier methodology , 1991, IEEE Trans. Syst. Man Cybern..

[2]  G. V. Kass.  An Exploratory Technique for Investigating Large Quantities of Categorical Data , 1980 .

[3]  T. Garling.  Theoretical Foundations of Travel Choice Modeling , 1998 .

[4]  Tommy Gärling,et al.  Computational-Process Modelling of Household Activity Scheduling , 1993 .

[5]  T. Gärling.  The importance of routines for the performance of everyday activities , 1992 .

[6]  Richard S. Sutton,et al.  Reinforcement Learning: An Introduction , 2005, IEEE Transactions on Neural Networks.

[7]  Dick Ettema,et al.  A SIMULATION MODEL OF ACTIVITY SCHEDULING BEHAVIOUR , 1992 .

[8]  J. Ross Quinlan,et al.  C4.5: Programs for Machine Learning , 1992 .

[9]  Geert Wets,et al.  Identifying Decision Structures Underlying Activity Patterns: An Exploration of Data Mining Algorithms , 2000 .

[10]  Tommy Gärling,et al.  Computer Simulation of Household Activity Scheduling , 1998 .

[11]  Mei-Po Kwan,et al.  GISICAS: AN ACTIVITY-BASED TRAVEL DECISION SUPPORT SYSTEM USING A GIS-INTERFACED COMPUTATIONAL-PROCESS MODEL. , 1997 .

[12]  W.W. Recker,et al.  A MODEL OF COMPLEX TRAVEL BEHAVIOR: PART I. THEORETICAL DEVELOPMENT , 1985 .

[13]  Wilfred W. Recker,et al.  A model of complex travel behavior: Part II—An operational model , 1986 .

[14]  Tommy Gärling,et al.  COMPUTATIONAL PROCESS MODELING OF HOUSEHOLD TRAVEL DECISIONS USING A GEOGRAPHICAL INFORMATION SYSTEM , 2005 .

[15]  T Garling,et al.  HOUSEHOLD ACTIVITY SCHEDULING , 1989 .

[16]  Leo Breiman,et al.  Classification and Regression Trees , 1984 .

[17]  Frank S. Koppelman,et al.  TRANSFERABILITY ANALYSIS OF DISAGGREGATE CHOICE MODELS , 1982 .

[18]  Tommy Gärling,et al.  Behavioural Assumptions Overlooked in Travel-Choice Modelling , 1998 .

[19]  John R. Anderson.  The Architecture of Cognition , 1983 .

[20]  Tommy Gärling.  Determinants of everyday time allocation , 1992 .

[21]  Tommy Gärling,et al.  The role of anticipated time pressure in activity scheduling , 1999 .