A model for the representation of emergency cases
- 33 Downloads
An emergency case contains important information and knowledge for emergency management, such as the evolution law of incidents, the vulnerability of hazard-affected carriers and the practice of emergency response. To respond effectively, we should learn from these valuable kinds of information and knowledge and utilize them. Most models of emergency cases are established based on ontology methodology. Important emergency information is semantically expressed and then analyzed by the text mining or cluster analysis methods. This type of methodology is at a disadvantage for obtaining the knowledge contained in the cases. In addition, some emergency case representation models are established using the event tree method or state chart method. However, not all the important information for emergencies can be integrated into these diagrams. The knowledge elements are not expressed with good structure, which results in a disadvantage to case-based reasoning and knowledge mining. In this paper, a comprehensive model for the representation of emergency cases is established. The proposed model combines the advantages of several conventional methods, including event tree, Bayesian conditional probability and information structured expression. Hazard-affected carrier properties, incident evolution laws and emergency response experience can be integrated and represented, which provides a good basis to employ data mining technology. With the proposed model, the general laws and successful emergency response experience contained in massive emergency cases can be obtained. Furthermore, the case-based reasoning and knowledge mining models for risk assessment, emergency preparedness and prevention, and decision-making can be developed based on effectively represented emergency cases.
KeywordsEmergency case Case representation Incident evolution Vulnerability of hazard-affected carriers Emergency response experience
The authors deeply appreciate support for this paper by the National Natural Science Foundation of China (Grant No. 71673161), the Fundamental Research Funds for the Central Business Unit (Grant No. 512015Y-4002) and the Youth Talent Fund of Beijing (Grant No. 512016Z-4983).
- Chakraborty B, Ghosh D, Rrnjan R et al (2010) Knowledge management with case-based reasoning applied on fire emergency handling. In: 8th IEEE international conference on industrial informatics INDIN 2010, Osaka, Japan, pp 708–713Google Scholar
- Cheng Z, Jia X, Wang LC, Bai YS (2010) A Framework for the case-based and model-based RCM analysis. In: International conference on E-product E-service and E-entertainment, vol 11, pp 1–4Google Scholar
- Güdemann M, Ortmeier F (2010) A framework for qualitative and quantitative formal model-based safety analysis. In: IEEE, international symposium on high-assurance systems engineering. IEEE Computer Society, Washington, pp 132–141Google Scholar
- Heckerman D, Geiger D, Chickering DM (1995) Learning Bayesian networks: the combination of knowledge and statistical data. Mach Learn 20(3):197–243Google Scholar
- Huang C, Zhong SB, Li X, Zhang FS, Chen JG, Su GF, Huang QY, Yuan HY (2014) Foundations of intelligent systems. In: Advances in intelligent systems and computing, vol 277. Springer, Berlin, pp 911–919Google Scholar
- Liu YH (2009) A case learning model for ship collision avoidance based on automatic text analysis. In: Proceedings of the eighth international conference on machine learning and cybernetics, Baoding, 12–15 July, pp 2199–2204Google Scholar
- Liu JF, Zou P, Zhang PZ, Jia ZQ (2009) Task-oriented capability requirement analysis using an ontology-based case reasoning method. In: 2009 international conference on computational intelligence and software engineering, vol 12, pp 1–4Google Scholar
- Shaker HE, Mohammed E (2015) Case based reasoning: case representation methodologies. Int J Adv Comput Sci Appl 6(11):192–208Google Scholar
- Wang D, Xiang Y, Zou GB, Zhang B (2009) Research on ontology-based case indexing in CBR. In: 2009 international conference on artificial intelligence and computational intelligence, vol 11, pp 238–241Google Scholar