Menelaos Bakopoulos, Sofia Tsekeridou, Eri Giannaka, Zheng-Hua Tan, & Ramjee Prasad. (2011). Command & control: Information merging, selective visualization and decision support for emergency handling. In E. Portela L. S. M.A. Santos (Ed.), 8th International Conference on Information Systems for Crisis Response and Management: From Early-Warning Systems to Preparedness and Training, ISCRAM 2011. Lisbon: Information Systems for Crisis Response and Management, ISCRAM.
Abstract: Emergency situations call for the timely collaboration and error free communication of first responder (FR) teams from their Command Posts (CP) and between themselves. First responder teams must form and adapt their plans and actions as a real-time critical situation unfolds. This paper presents an advanced Command Post application that manages a diversity of FR teams during an emergency. Data from biometric, fire and/or gas sensors in addition to received annotated videos from first responders on site, carrying personal digital assistants (PDAs), are simultaneously managed. The presented system provides properly configured access to and alert-dependent visualization of real time location, biometric, gas, fire and annotated video data from FRs in the field to allow for effective reaction and decision support from CP personnel. Additionally, the system forms an information management system for all necessary information to be quickly handy during emergency handling, such as FR information, critical infrastructure information, historical information, etc. This system has been validated through qualitative analysis in a field trial at the M30 tunnel in Madrid by participating end users.
|
Tuncay Bayrak. (2007). Performance metrics for disaster monitoring systems. In K. Nieuwenhuis P. B. B. Van de Walle (Ed.), Intelligent Human Computer Systems for Crisis Response and Management, ISCRAM 2007 Academic Proceedings Papers (pp. 125–132). Delft: Information Systems for Crisis Response and Management, ISCRAM.
Abstract: Understanding the performance of disaster monitoring systems is a key to understanding their success, therefore; various qualitative and quantitative measures and metrics can be applied in the characterization and analysis of such systems. Through evaluation studies, problems that impede a disaster monitoring system performance can be identified. The results can be used for system control, design, and capacity planning. Previous studies address technical performance analysis metrics for analyzing monitoring systems leaving out human and organizational dimensions of such systems. Thus, the primary objective of this study is to identify and describe a set of disaster monitoring systems performance analysis metrics that may be employed to evaluate such systems. This study may be valuable to researchers and practitioners involved in disaster and emergency response studies in planning the transportation of vital first-aid supplies and emergency personnel to disaster-affected areas, and in improving chances of survival after a natural disaster.
|
Nasik Muhammad Nafi, Avishek Bose, Sarthak Khanal, Doina Caragea, & William H. Hsu. (2020). Abstractive Text Summarization of Disaster-Related Documents. In Amanda Hughes, Fiona McNeill, & Christopher W. Zobel (Eds.), ISCRAM 2020 Conference Proceedings – 17th International Conference on Information Systems for Crisis Response and Management (pp. 881–892). Blacksburg, VA (USA): Virginia Tech.
Abstract: Abstractive summarization is intended to capture key information from the full text of documents. In the application domain of disaster and crisis event reporting, key information includes disaster effects, cause, and severity. While some researches regarding information extraction in the disaster domain have focused on keyphrase extraction from short disaster-related texts like tweets, there is hardly any work that attempts abstractive summarization of long disaster-related documents. Following the recent success of Reinforcement Learning (RL) in other domains, we leverage an RL-based state-of-the-art approach in abstractive summarization to summarize disaster-related documents. RL enables an agent to find an optimal policy by maximizing some reward. We design a novel hybrid reward metric for the disaster domain by combining \underline{Vec}tor Similarity and \underline{Lex}icon Matching (\textit{VecLex}) to maximize the relevance of the abstract to the source document while focusing on disaster-related keywords. We evaluate the model on a disaster-related subset of a CNN/Daily Mail dataset consisting of 104,913 documents. The results show that our approach produces more informative summaries and achieves higher \textit{VecLex} scores compared to the baseline.
|
Sébastien Tremblay, Daniel Lafond, Jean-François Gagnon, Vincent Rousseau, & Rego Granlund. (2010). Extending the capabilities of the C3Fire microworld as a testing platform for research in emergency response management. In C. Zobel B. T. S. French (Ed.), ISCRAM 2010 – 7th International Conference on Information Systems for Crisis Response and Management: Defining Crisis Management 3.0, Proceedings. Seattle, WA: Information Systems for Crisis Response and Management, ISCRAM.
Abstract: The present paper describes the C3Fire microworld and the testing capabilities it provides for research in emergency response management. We start with a general description of C3Fire and report extensions that add a new subtask (search and rescue) relevant to the context of emergency response and a vocal communication system. We then describe how various organizational structures can be designed using this task environment and several metrics of major interest for research in crisis management, related to task performance, communication, coordination effectiveness, monitoring effectiveness, recovery from interruptions, detection of critical changes, and team adaptation. The microworld constitutes a highly flexible testing platform for research in team cognition, cognitive systems engineering and decision support for crisis management.
|
