Decision Support System to Guide Use-Centric Cooperative, Connected and Automated Mobility Deployments: The SINFONICA Knowledge Map Explorer

Antonakopoulou, Anna; Fokeas, Konstantinos; Tsougiannis, Evangelos; Krikochoriti, Maria; Amditis, Angelos · 2025 · Crossref

DOI: 10.54941/ahfe1006533

archive: archived pipeline: cataloged verified

Get this paper ↗ (DOI — opens at the source; we link to it, we don't host it)

Summary

This paper presents the design, architecture, and implementation of the SINFONICA Knowledge Map Explorer (KME), a decision-support system intended to facilitate the inclusive deployment of Cooperative, Connected, and Automated Mobility (CCAM) solutions. Motivated by the need to engage diverse stakeholders—including vulnerable road users, transport operators, and public authorities—the KME aims to synthesize user needs, preferences, and concerns into actionable insights. The tool is designed to guide CCAM designers and policymakers by providing tailored recommendations that ensure equity and sustainability, without directly operating CCAM systems or processing personal data. The KME utilizes a dual-system architecture combining a Semantic-Based System and a Rule-Based System. The semantic component is built on an ontology developed using the Protégé editor and the Web Ontology Language (OWL). This ontology captures interactions within the CCAM domain through four main classes: Data Concept, Domain Concept, General Concept, and Recommendations. The knowledge map was populated with data derived from interviews, focus groups, and workshops conducted across four European contexts. Structured data from spreadsheets was transformed into the ontology using the Cellfie plugin, which maps spreadsheet attributes to ontology classes and properties. The rule-based component employs Semantic Web Rule Language (SWRL) to define "if-then" logic for generating recommendations. The Pellet reasoner executes these rules to infer new knowledge, which is stored in an Apache Fuseki server. The system’s backend integrates these components to deliver real-time recommendations. When a user interacts with the frontend interface to select specific demographic or contextual criteria, the backend generates a SPARQL query. This query is executed against the Fuseki server, which contains precomputed inferences from the Pellet reasoner. The results are parsed and returned to the user as tailored guidelines. For instance, the system can recommend specific inclusivity guidelines for elderly citizens in urban areas of Greece based on predefined rules linking user profiles to recommendation types. The architecture ensures scalability, performance, and extensibility, allowing for easy updates to rules and ontologies. The significance of the KME lies in its ability to harmonize explicit and inferred knowledge to support evidence-based decision-making in CCAM deployments. By providing accessible, domain-specific insights, the tool helps stakeholders address unique user traits and contextual factors, fostering more equitable technology adoption. The paper concludes by noting that usability evaluations have informed system refinements. Future work will focus on expanding the system’s capabilities through dynamic ontology updates and semantically enriched machine learning, aiming to combine symbolic reasoning with data-driven models to enhance inference accuracy and adaptability to new real-world insights.

Provenance

The full processing record for this entry. Every stage of this paper's journey through the pipeline is logged — what ran, with which tool and model, how many attempts it took, and when it last completed.

Summary generated by qwen3.6-27b-prismaquant on 2026-06-26; verification: verified.

Topics

Ranked by relevance to this paper. Hover a topic for its definition.

• odd communication