A Systemic Approach for Early Warning in Crisis Prevention and Management
Given the importance of early warning in crisis prevention this paper discusses both knowledge-based and data-driven approaches. Traditional knowledge-based methods are often of limited suitability for use in crisis prevention and management, since they typically use a model which has been designed in advance. Novel data-driven Artificial Intelligence (AI) methods such as Deep Learning demonstrate promising skills to learn implicitly from data alone, but require significant computing capacities and a large amount of annotated, high-quality training data. This paper addresses research results on concepts and methods that may serve as building blocks for realizing a decision support tool based on hybrid AI methods, which combine knowledge-based and data-driven methods in a dynamic way and provide an adaptable solution to mitigate the downsides of each individual approach.
KeywordsEarly warning Expert knowledge models Deep Learning
Inputs to the paper from Marian Sorin Nistor are gratefully acknowledged.
- 2.Kuwertz, A., Mühlenberg, D., Sander, J., Müller, W.: Applying knowledge-based reasoning for information fusion in intelligence, surveillance, and reconnaissance. In: Multisensor Fusion and Integration in the Wake of Big Data, Deep Learning and Cyber Physical System, LNEE 501, pp. 119–139. Springer (2018)Google Scholar
- 6.Zsifkovits, M., Moll, M., Pham, T.S., Pickl, S.W.: A visual approach to data fusion in sensor networks. In: Proceedings of the International Conference on Security Management (2017)Google Scholar
- 7.Nagananthini, C., Yogameena, B.: Crowd Disaster Avoidance System (CDAS) by deep learning using eXtended Center Symmetric Local Binary Pattern (XCS-LBP) texture features. In: International Conference on Computer Vision and Image Processing, pp. 487–498 (2017)Google Scholar
- 8.Zhang, W., Fu, S., Diao, Y., Sheng, W., Jia, D.: A situation awareness and early warning method for voltage instability risk. In: China International Conference on Electricity Distribution, pp. 1010–1014 (2018)Google Scholar
- 9.Khediri, A.: Deep-belief network based prediction model for power outage in smart grid. In: 4th International Conference of Computing for Engineering and Sciences (2018)Google Scholar
- 10.Lohumi, K., Roy, S.: Automatic detection of flood severity level from flood videos using deep learning. In: 5th International Conference on Information and Communication Technologies for Disaster Management (2018)Google Scholar
- 12.Sihombing, F., Torbol, M.: Machine learning implementation for a rapid earthquake early warning system. In: 6th International Symposium on Life-Cycle Civil Engineering (2018)Google Scholar