An ontology-based CBR approach for personalized itinerary search systems for sustainable urban freight transport

• Novel information retrieval system for personalized itinerary search in urban freight transport.
• Integration of CBR, Choquet integral and ontology for personalized retrieval mechanism.
• User-oriented ontologies to extract knowledge from the overwhelming urban traffic information.
• Introduction of a new similarity measures method in the retrieval step of the CBR.
• Considers textual and numerical features for improved quality of information retrieval.

This paper presents a novel information retrieval approach for personalized itinerary search in urban freight transport systems. The proposed approach is based on the integration of three techniques: Case Base Reasoning, Choquet integral and ontology. It has the following advanced features: (1) user-oriented ontology is used as source of knowledge to extract pertinent information about stakeholder’s preferences and needs; (2) semantic web rule language is considered to provide the system with enhanced semantic capabilities and support personalized case representation; (3) a CBR-personalized retrieval mechanism is designed to provide a user with an optimum itinerary that meets his personal needs and preferences. The above features lead to a personalized and optimum itinerary search that meets the user’s needs as specified in their queries such as fuel consumption, environmental impact, optimum route, time management etc. This has the potential to effectively manage fright movement according to stakeholder’s needs and alleviate congestion problems in urban areas. The proposed intelligent decision support system (Onto-CBR) is implemented to an itinerary search problem for freight transportation users in urban areas. Its performance is further compared to an itineraries search system that was proposed by the authors in an earlier publication. Both approaches are compared in terms of their ability to meet user’s personal preferences and achieve accuracy in case retrieval. The experimental results showed the ability of the proposed system to improve the accuracy of case retrieval and reduce retrieval time prominently. The ability of the proposed system tailor the search to stakeholders needs, improve the accuracy of case retrieval and facilitate the search process are among the main positive features of the proposed intelligent decision support system.