CASE-BASED REASONING - A PLANNING TOOL FOR INTELLIGENT TRANSPORTATIONSYSTEMS

This paper develops a Case-Based Reasoning (CBR) methodology for PLANi TS (Planning and Analysis Integration for Intelligent Transportation S ystems). To address a current transportation planning situation, CBR p resents similar historical cases. Specifically, it estimates the impac ts of proposed transportation improvement actions, including Intellige nt Transportation Systems, based on previous experiences with similar actions. In this paper, a hierarchical structure for representing hist orical cases is developed. All historical cases consist of transportat ion improvement actions, performance measures and environments defined in terms of their spatial, temporal and user/traveler dimensions. In addition, cases contain information about lessons learnt such as infer ences regarding their success or failure, prescriptions and case quali ty. Information about historical cases can be synthesized. Specificall y, the reasoner contains mechanisms for (a) matching at various levels of stringency, (b) ranking with alternative distance and weight measu res and (c) analyzing similar past cases with statistical operations. Also discussed are the limitations of CBR applications to transportati on planning. Overall, the structure for the CBR is flexible and incorp orates different stakeholder preferences for alternative transportatio n improvement actions and evaluation criteria. Further, the applicatio n of CBR to transportation planning, discussed in this paper, formaliz es the use of case knowledge in transportation. This can lead to impro ving the transportation planning process. Copyright (C) 1996 Elsevier Science Ltd