原文传递
ROUTE CHOICE MODEL WITH INDUCTIVE LEARNING.
| 题名： | ROUTE CHOICE MODEL WITH INDUCTIVE LEARNING. |
| 作者： | Nakayama-S; Kitamura-R |
| 关键词： | Caprice-; Cognitive-psychology; Delusions-; Genetic-algorithms; Habits-; Inductive-learning; Mathematical-models; Monte-Carlo-method; Perception-; Route-choice; Simulation-; Travel-behavior; Travel-time |
| 摘要： | In this study drivers are assumed to reason and learn inductively based on the theory of cognitive psychology. The model system is basically a production system, a compilation of if-then rules in which the rules are revised by applying genetic algorithms. The behavior of drivers and network flow through Monte Carlo simulation using the model system is examined. The intention of this research is to shed light on the behavior of a driver-network system from a new standpoint, one different from that of equilibrium analysis. This research views drivers' behaviors as psychological and heterogeneous rather than economical and homogeneous. The results of the numerical experiments can be summarized as follows: (1) network flow does not necessarily converge to the user equilibrium; (2) drivers form a delusion, an extremely biased perception of travel time as a result of experiencing excessive travel times on early parts of the simulation in which little experience had been gained; (3) the delusion is dissolved by switching routes capriciously; and (4) without caprice drivers continue to travel on the same route because of their delusions and develop the habit of choosing the same route, thus freezing their behaviors. These results indicate that system behavior is much more complex and dynamic than implied by equilibrium analysis. |
| 总页数： | Transportation Research Record. 2000. (1725) pp63-70 (5 Fig., 1 Tab., 18 Ref.) |
| 报告类型： | 科技报告 |
相关文献
- MODELING ROUTE CHOICE BEHAVIOR WITH STOCHASTIC LEARNING AUTOMATA.
- MODELING LEARNING AND EVOLUTIONARY ADAPTATION PROCESSES IN ACTIVITY SETTINGS: THEORY AND NUMERICAL SIMULATIONS.
- APPLICATION OF STOCHASTIC LEARNING AUTOMATA FOR MODELING DEPARTURE TIME AND ROUTE CHOICE BEHAVIOR.
- URBAN RAIL CORRIDOR CONTROL THROUGH MACHINE LEARNING: AN INTELLIGENT VEHICLE-HIGHWAY SYSTEM APPROACH.
- Analysis of Factors Affecting the Frequency and Type of Activity Schedule Modification.
- Development, Deployment, and Assessment of Activity-Based Transportation Courses.
检索历史
应用推荐
