How to Understand Better “Smart Vehicle”? Knowledge Extraction …
313
built a “common sense knowledge” dataset for the automotive sector comprising 42
projects between 2005 and 2019. However, only 16 ontologies are processable and
published online with knowledge representation standards. Our innovative Knowledge Extraction for the Automotive Sector (KEAS) methodology aims to analyze the
most popular knowledge required to build smart vehicle applications by applying the
k-means machine learning algorithm to a dataset of 16 ontologies that we collected.
This work highly encourages researchers to share their reproduceable experiments
by publishing online their smart vehicle ontologies. As a future work, we would like to
re-generate an ontology to aggregate and unify the knowledge from existing ontologies. Furthermore, we would like to automatically recognize the sensors mentioned
within ontologies and scientific publications to maintain our IoT dictionnary, and
reasoning mechanisms used to detect abnormal sensor data and execute actions.
Acknowledgements This work has partially received funding from the European Union’s Horizon
2020 research and innovation programme under grant agreement No. 857237 (Interconnect). The
opinions expressed are those of the authors and do not reflect those of the sponsors.
7 Appendix
7.1 Clustering Results
See Figs. 3, 4, 5, 6, 7, 8 and 9
313
built a “common sense knowledge” dataset for the automotive sector comprising 42
projects between 2005 and 2019. However, only 16 ontologies are processable and
published online with knowledge representation standards. Our innovative Knowledge Extraction for the Automotive Sector (KEAS) methodology aims to analyze the
most popular knowledge required to build smart vehicle applications by applying the
k-means machine learning algorithm to a dataset of 16 ontologies that we collected.
This work highly encourages researchers to share their reproduceable experiments
by publishing online their smart vehicle ontologies. As a future work, we would like to
re-generate an ontology to aggregate and unify the knowledge from existing ontologies. Furthermore, we would like to automatically recognize the sensors mentioned
within ontologies and scientific publications to maintain our IoT dictionnary, and
reasoning mechanisms used to detect abnormal sensor data and execute actions.
Acknowledgements This work has partially received funding from the European Union’s Horizon
2020 research and innovation programme under grant agreement No. 857237 (Interconnect). The
opinions expressed are those of the authors and do not reflect those of the sponsors.
7 Appendix
7.1 Clustering Results
See Figs. 3, 4, 5, 6, 7, 8 and 9