Digital library of construction informatics
and information technology in civil engineering and construction


Paper lc3-2017-256:
Taiwan High-Speed Trains Emergency Dispatching Using Ontology-Based, Multi-Agent Model

Facilitated by the SciX project

Chuen-Chyi Hsieh, Te-Che Chen, Ting-Wu Ho and Chien-Cheng Chou

Taiwan High-Speed Trains Emergency Dispatching Using Ontology-Based, Multi-Agent Model

Abstract: High-speed rail (HSR) systems have played a more and more important role for todayÕs traveling public. To guarantee punctual, reliable and safe services, modern HSR systems are equipped with sophisticated computerized subsystems for daily operations. However, when a natural or man-made disaster occurs, currently extensive human interventions are needed and, consequently, extended delays and possible injuries may occur if HSR emergency dispatching plans utilized do not accommodate all the conflicts raised. Previous literature shows that multi-agent system (MAS) technology can be utilized to provide decision-making assistance in a distributed and dynamic environment and is often combined with ontology and semantic rules to enhance the reasoning capability. Hence, this research aimed at developing an ontology-driven MAS model for HSR emergency dispatching, and intelligent agents were constructed using JADE (Java Agent DEvelopment framework) and Protˇgˇ with SWRL (Semantic Web Rule Language). The proposed model was validated with three real HSR emergency dispatching cases, plus 50 hypothetical cases. Experts from Taiwan HSR company were asked to assess the model performance. The assessment results showed that the HSR emergency dispatching plans generated were similar to those designed by experienced dispatchers, and the time required to develop a plan using the proposed model was significantly less than the time needed in the manual approach. The model is expected to help young dispatchers handle emergency dispatching cases under stress, as well as to strengthen the safety aspect of HSR services. Delays or casualties associated with a train disaster could be reduced if the proposed model is adequately utilized.

Keywords: Multi-Agent System, Ontology, High-Speed Rail, Disaster Response Phase, Emergency Dispatching

DOI: https://doi.org/10.24928/JC3-2017/0256

Full text: content.pdf (1,410,670 bytes) (available to registered users only)

Series: jc3:2017 (browse)
Similar papers:
Sound: N/A.


hosted by University of Ljubljana



© itc.scix.net 2003
FIRST PREVIOUS NEXT LAST Home page of this database login Powered by SciX Open Publishing Services 1.002 February 16, 2003