toggle visibility Search & Display Options

Select All    Deselect All
 |   | 
Details
   print
  Record Links
Author Dragos Datcu; Leon J.M. Rothkrantz pdf  isbn
openurl 
  Title (up) A Dialog Action Manager for automatic crisis management Type Conference Article
  Year 2008 Publication Proceedings of ISCRAM 2008 – 5th International Conference on Information Systems for Crisis Response and Management Abbreviated Journal ISCRAM 2008  
  Volume Issue Pages 384-393  
  Keywords Bayesian networks; Information systems; Management information systems; Mobile devices; Safe handling; Automatic systems; Crisis management; Crisis management systems; Crisis situations; Data-communication; Reasoning; System architectures; System knowledge; Managers  
  Abstract This paper presents the results of our research on the development of a Dialog Action Manager-DAM as part of a complex crisis management system. Imagine the utility of such an automatic system to detect the crisis and to provide support to people in contexts similar to what happened recently at the underground in London and Madrid. Preventing and handling the scenarios of terrorism and other crisis are nowadays maybe the most important issues for a modern and safe society. In order to automate the crisis support, DAM simulates the behavior of an employee at the crisis centre handling telephone calls from human observers. Firstly, the system has to mimic the natural support for the paradigm 'do you hear me?' and next for the paradigm 'do you understand me?'. The people witnessing the crisis event as well as human experts provide reports and expertise according to their observations and knowledge on the crisis. The system knowledge and the data communication follow the XML format specifications. The system is centered on the results of our previous work on creating a user-centered multimodal reporting tool that works on mobile devices. In our paper we describe the mechanisms for creating an automatic DAM system that is able to analyze the user messages, to identify and track the crisis contexts, to support dialogs for crisis information disambiguation and to generate feedback in the form of advice to the users. The reasoning is done by using a data frame and rule based system architecture and an alternative Bayesian Network approach. In the paper we also present a series of experiments we have attempted in our endeavor to correctly identify natural solutions for the crisis situations.  
  Address Man-Machine Interaction Group, Delft University of Technology, 2628 CD, Delft, Netherlands  
  Corporate Author Thesis  
  Publisher Information Systems for Crisis Response and Management, ISCRAM Place of Publication Washington, DC Editor F. Fiedrich, B. Van de Walle  
  Language English Summary Language English Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN 2411-3387 ISBN 9780615206974 Medium  
  Track Observation Systems in Crisis Situations Expedition Conference 5th International ISCRAM Conference on Information Systems for Crisis Response and Management  
  Notes Approved no  
  Call Number Serial 424  
Share this record to Facebook
Select All    Deselect All
 |   | 
Details
   print

Save Citations:
Export Records: