How to Understand Better “Smart Vehicle”? Knowledge Extraction for the Automotive Sector Using Web of Things

Abstract

How to understand better the knowledge provided by Google results to build future “smart vehicle-centric” applications? What is the knowledge expertise required to build a smart vehicle application (e.g., driver assistance system)? Automotive companies (e.g., Toyota, BMW, Renault) are employing Internet of Things (IoT) and Semantic Web technologies to model the automotive sector. We aggregate this “common sense knowledge” in a automotive dataset which comprises 42 semantics-based projects between 2005 and 2019. The knowledge is already encoded with knowledge representation languages (e.g., RDF, RDFS, and OWL) and supported by the World Wide Web Consortium (W3C). However, only a subset of those projects share their expertise by publishing their ontologies online. For this reason, at the current time or writing, only 16 ontologies are processable. Our innovative Knowledge Extraction for the Automotive Sector (KEAS) methodology analyzes what are the most popular terms required to build a smart car, it provides: (1) a set of keyphrase that are synonyms to smart cars to find domain-specific knowledge, (2) synonyms are used to build a corpus of scientific publications to train the k-means machine learning algorithm, (3) a dataset of smart car ontologies that we collected, is analyzed by the k-means algorithm, and (4) the extraction of the most common terms from the ontology dataset for the automotive sector. Our KEAS findings can be used as a starting point for further domain-specific investigations (e.g., Volvo willing to integrate semantic web) and for future information extraction from structured knowledge.