Case–Based Reasoning for Assessing Intelligent Transportation Systems Benefits

Abstract

Existing transportation planning modeling tools have critical limitations with respect to assessing the benefits of intelligent transportation systems (ITS) deployment. In this article, we present a novel framework for developing modeling tools for quantifying ITS deployments benefits. This approach is based on using case–based reasoning (CBR), an artificial intelligence paradigm, to capture and organize the insights gained from running a dynamic traffic assignment (DTA) model. To demonstrate the feasibility of the approach, the study develops a prototype system for evaluating the benefits of diverting traffic away from incident locations using variable message signs. A real–world network from the Hartford area in Connecticut is used in developing the system. The performance of the prototype is evaluated by comparing its predictions to those obtained using a detailed DTA model. The prototype system is shown to yield solutions comparable to those obtained from the DTA model, thus demonstrating the feasibility of the approach.