I. Kivrakidis, E. Rigas, N. Bassiliades, “EVO: An Ontology for the Field of Electric Vehicles”, 20th International Conference on Artificial Intelligence Applications and Innovations (AIAI 2024), 27 - 30 June 2024, Ionian University, Corfu, Greece, In: Maglogiannis, I., Iliadis, L., Macintyre, J., Avlonitis, M., Papaleonidas, A. (eds), Artificial Intelligence Applications and Innovations, AIAI 2024, IFIP Advances in Information and Communication Technology, vol 714, Springer, Cham.
The global automotive industry, a thriving economic powerhouse and epicenter of research and development, is increasingly focused on advancing safety for both vehicle occupants and pedestrians. While the rising number of vehicles offers unprecedented mobility and convenience, it has also led to alarming urban air pollution levels. To combat this, many countries are actively promoting the adoption of Electric Vehicles (EVs). EVs are hailed for their remarkable efficiency in reducing oil consumption and gas emissions, positioning them as a promising solution for future road transportation. However, the EV landscape is marred by substantial diversity among manufacturers, particularly concerning battery capacities and types, range of vehicles and charger types. This lack of standardization has created a pressing need for advanced data and knowledge management methods. In response, this paper focuses on the development of an ontology tailored specifically to the domain of EVs. This ontology aims to enhance reusability and interoperability, fostering seamless information, integration and collaboration across various EV-related applications and systems. By doing so, it propels the EV industry toward greater improvement in the years ahead. The framework that was utilized for the development of the EV Ontology (EVO) was Protege, employing the Web Ontology Language (OWL) for standardized knowledge representation. The competence of the EVO is evaluated through SPARQL queries. Furthermore, the ontology is enriched by a Python script that scrapes data from web-based EV databases. Finally, a user interaction Python script is implemented that lets users interact with the ontology with personalized SPARQL queries.
