|   | 
Details
   web
Records
Author Siska Fitrianie; Ronald Poppe; Trung H. Bui; Alin Gavril Chitu; Dragos Datcu; Ramón Dor; Denis Hofs; Pascal Wiggers; Don J.M. Willems; Mannes Poel; Leon J.M. Rothkrantz; Louis G. Vuurpijl; Job Zwiers
Title A multimodal human-computer interaction framework for research into crisis management Type Conference Article
Year 2007 Publication (up) Intelligent Human Computer Systems for Crisis Response and Management, ISCRAM 2007 Academic Proceedings Papers Abbreviated Journal ISCRAM 2007
Volume Issue Pages 149-158
Keywords Character recognition; Communication systems; Disasters; Human computer interaction; Speech recognition; Communication modalities; Evaluation methods; Facial Expressions; Multi-modal information; Multimodal human computer interaction; Multimodal system; Rescue simulation; Technological aspects; Face recognition
Abstract Unreliable communication networks, chaotic environments and stressful conditions can make communication during crisis events difficult. The current practice in crisis management can be improved by introducing ICT systems in the process. However, much experimentation is needed to determine where and how ICT can aid. Therefore, we propose a framework in which predefined modules can be connected in an ad hoc fashion. Such a framework allows for rapid development and evaluation of such ICT systems. The framework offers recognition of various communication modalities including speech, lip movement, facial expression, handwriting and drawing, body gesture, text and visual symbols. It provides mechanisms to fuse these modalities into a context dependent interpretation of the current situation and generate appropriate the multimodal information responses. The proposed toolbox can be used as part of a disaster and rescue simulation. We propose evaluation methods, and focus on the technological aspects of our framework.
Address Man-Machine Interaction Group, Delft University of Technology, Netherlands; Human Media Interaction Group, University of Twente, Netherlands; Nijmegen Institute for Cognition and Information, Radboud University Nijmegen, Netherlands
Corporate Author Thesis
Publisher Information Systems for Crisis Response and Management, ISCRAM Place of Publication Delft Editor B. Van de Walle, P. Burghardt, K. Nieuwenhuis
Language English Summary Language English Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN 2411-3387 ISBN 9789054874171; 9789090218717 Medium
Track HCIS Expedition Conference 4th International ISCRAM Conference on Information Systems for Crisis Response and Management
Notes Approved no
Call Number Serial 497
Share this record to Facebook
 

 
Author Don J.M. Willems; Louis Vuurpijl
Title Designing interactive maps for crisis management Type Conference Article
Year 2007 Publication (up) Intelligent Human Computer Systems for Crisis Response and Management, ISCRAM 2007 Academic Proceedings Papers Abbreviated Journal ISCRAM 2007
Volume Issue Pages 159-166
Keywords Bayesian networks; Feature extraction; Human computer interaction; Personal computers; Crisis management; Crisis management systems; Data collection; Domain specific; Effective communication; Interactive maps; Mode detection; Recognition systems; Pattern recognition systems
Abstract This paper describes the design, implementation, and evaluation of pen input recognition systems that are suited for so-called interactive maps. Such systems provide the possibility to enter handwriting, drawings, sketches and other modes of pen input. Typically, interactive maps are used to annotate objects or mark situations that are depicted on the display of video walls, handhelds, PDAs, or tablet PCs. Our research explores the possibility of employing interactive maps for crisis management systems, which require robust and effective communication of, e.g., the location of objects, the kind of incidents, or the indication of route alternatives. The design process described here is a mix of “best practices” for building perceptive systems, combining research in pattern recognition, human factors, and human-computer interaction. Using this approach, comprising data collection and annotation, feature extraction, and the design of domain-specific recognition technology, a decrease in error rates is achieved from 9.3% to 4.0%.
Address Nijmegen Institute for Cognition and Information, Radboud University, Nijmegen, Netherlands
Corporate Author Thesis
Publisher Information Systems for Crisis Response and Management, ISCRAM Place of Publication Delft Editor B. Van de Walle, P. Burghardt, K. Nieuwenhuis
Language English Summary Language English Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN 2411-3387 ISBN 9789054874171; 9789090218717 Medium
Track HCIS Expedition Conference 4th International ISCRAM Conference on Information Systems for Crisis Response and Management
Notes Approved no
Call Number Serial 1092
Share this record to Facebook