| |
Benjamin Betting, Emilien Varea, & Beatrice Patte-Rouland. (2017). Smoke dynamics in compartment fires: large scale experiments and numerical simulations. In eds Aurélie Montarnal Matthieu Lauras Chihab Hanachi F. B. Tina Comes (Ed.), Proceedings of the 14th International Conference on Information Systems for Crisis Response And Management (pp. 879–889). Albi, France.
Abstract: Today, during compartments fire, the decision-making of the rescue teams is mainly based on human decisions, which are the results of gathered experiences. However, a perfect knowledge of the situation, its evolution over time and the dangers that may appear is impossible. The transition between a localized fire and a generalized fire can take several forms. One of the most important vectors in the propagation of combustion for compartment fires is smoke due to its high temperature and the large amounts of energy it contains. Despite its extreme danger, smoke remains important to study because it convey valuable information, especially on the appearance of thermal phenomena feared by firemen. To carry out this study, a large scale experimental cell is used. A burner fueled with propane produces hot fumes in a so-called “real fire” configuration. All the measurements carried out are compared with LES (Large Eddy Simulation) simulations of the experiment using FDS. The numerical component allows defining scenarios (fire fully developed, fire under ventilated ...), which are verified by the experiments. The dual competence numerical /experimental data is essential in this type of study since the experimental data suffer from a lack of resolution (spatial, temporal) but nevertheless represent information necessary for validating the codes.
|
|
Simon French, Nikos Argyris, Jim Q. Smith, Stephanie Haywood, & Matthew Hort. (2017). Uncertainty Handling during Nuclear Accidents. In eds Aurélie Montarnal Matthieu Lauras Chihab Hanachi F. B. Tina Comes (Ed.), Proceedings of the 14th International Conference on Information Systems for Crisis Response And Management (pp. 15–24). Albi, France.
Abstract: In the years following Chernobyl, many reports and projects reflected on how to improve emergency management processes in dealing with an accidental offsite release of radiation at a nuclear facility. A common observation was the need to address the inevitable uncertainties. Various suggestions were made and some of these were researched in some depth. The Fukushima Daiichi Disaster has led to further reflections. However, many of the uncertainties inherent in responding to a threatened or actual release remain unaddressed in the analyses and model runs that are conducted to support the emergency managers in their decision making. They are often left to factor in allowances for the uncertainty through informal discussion and unsupported judgement, and the full range of sources of uncertainty may not be addressed. In this paper, we summarise the issues and report on a project which has investigated the handling of uncertainty in the UK’s national crisis cell. We suggest the R&D programmes needed to provide emergency managers with better guidance on uncertainty and how it may affect the consequences of taking different countermeasures.
|
|
Zoha Sheikh, Hira Masood, Sharifullah Khan, & Muhammad Imran. (2017). User-Assisted Information Extraction from Twitter During Emergencies. In eds Aurélie Montarnal Matthieu Lauras Chihab Hanachi F. B. Tina Comes (Ed.), Proceedings of the 14th International Conference on Information Systems for Crisis Response And Management (pp. 684–691). Albi, France.
Abstract: Disasters and emergencies bring uncertain situations. People involved in such situations look for quick answers to their rapid queries. Moreover, humanitarian organizations look for situational awareness information to launch relief operations. Existing studies show the usefulness of social media content during crisis situations. However, despite advances in information retrieval and text processing techniques, access to relevant information on Twitter is still a challenging task. In this paper, we propose a novel approach to provide timely access to the relevant information on Twitter. Specifically, we employee Word2vec embeddings to expand initial users queries and based on a relevance feedback mechanism we retrieve relevant messages on Twitter in real-time. Initial experiments and user studies performed using a real world disaster dataset show the significance of the proposed approach.
|
|
Michael Aupetit, & Muhammad Imran. (2017). Interactive Monitoring of Critical Situational Information on Social Media. In eds Aurélie Montarnal Matthieu Lauras Chihab Hanachi F. B. Tina Comes (Ed.), Proceedings of the 14th International Conference on Information Systems for Crisis Response And Management (pp. 673–683). Albi, France.
Abstract: According to many existing studies, the data available on social media platforms such as Twitter at the onset of a crisis situation could be useful for disaster response and management. However, making sense of this huge data coming at high-rate is still a challenging task for crisis managers. In this work, we present an interactive social media monitoring tool that uses a supervised classification engine and natural language processing techniques to provide a detailed view of an on-going situation. The tool allows users to apply various filtering options using interactive timelines, critical entities, and other logical operators to get quick access to situational information. The evaluation of the tool conducted with crisis managers shows its significance for situational awareness and other crisis management related tasks.
|
|
Hongmin Li, Doina Caragea, & Cornelia Caragea. (2017). Towards Practical Usage of a Domain Adaptation Algorithm in the Early Hours of a Disaster. In eds Aurélie Montarnal Matthieu Lauras Chihab Hanachi F. B. Tina Comes (Ed.), Proceedings of the 14th International Conference on Information Systems for Crisis Response And Management (pp. 692–704). Albi, France.
Abstract: Many machine learning techniques have been proposed to reduce the information overload in social media data during an emergency situation. Among such techniques, domain adaptation approaches present greater potential as compared to supervised algorithms because they don’t require labeled data from the current disaster for training. However, the use of domain adaptation approaches in practice is sporadic at best. One reason is that domain adaptation algorithms have parameters that need to be tuned using labeled data from the target disaster, which is presumably not available. To address this limitation, we perform a study on one domain adaptation approach with the goal of understanding how much source data is needed to obtain good performance in a practical situation, and what parameter values of the approach give overall good performance. The results of our study provide useful insights into the practical application of domain adaptation algorithms in real crisis situations.
|
|
|
