Linn Marks Collins, James E. Powell Jr., Carolyn E Dunford, Ketan K. Mane, & Mark L.B. Martinez. (2008). Emergency information Synthesis and awareness using E-SOS. In B. V. de W. F. Fiedrich (Ed.), Proceedings of ISCRAM 2008 – 5th International Conference on Information Systems for Crisis Response and Management (pp. 618–623). Washington, DC: Information Systems for Crisis Response and Management, ISCRAM.
Abstract: In an emergency, people need to be able to report and find relevant information quickly. Fulfilling these information needs is the design goal of E-SOS: Emergency Situation Overview and Synthesis, a research project in progress. E-SOS will consist of (1) a website where users can report information, (2) web services that find and synthesize related information from multiple sources, and (3) interface tools that visualize and display links to this information. In this paper we describe three of these services and tools: the topic, geographic, and information space awareness tools. When a user writes a report, the topic awareness tool will execute a federated search and display links to related information. The information space awareness tool will highlight these links in a visualization of the information space. If the user refers to a location, the geographic awareness tool will focus a map on this location and display topic-related icons.
|
Tina Comes, Claudine Conrado, Michael Hiete, Michiel Kamermans, Gregor Pavlin, & Niek Wijngaards. (2010). An intelligent decision support system for decision making under uncertainty in distributed reasoning frameworks. 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: This paper presents an intelligent system facilitating better-informed decision making under severe uncertainty as found in emergency management. The construction of decision-relevant scenarios, being coherent and plausible descriptions of a situation and its future development, is used as a rationale for collecting, organizing, filtering and processing information for decision making. The development of scenarios is geared to assessing decision alternatives, thus avoiding time-consuming analysis and processing of irrelevant information. The scenarios are constructed in a distributed setting allowing for a flexible adaptation of reasoning (principles and processes) to the problem at hand and the information available. This approach ensures that each decision can be founded on a coherent set of scenarios, which was constructed using the best expertise available within a limited timeframe. Our theoretical framework is demonstrated in a distributed decision support system by orchestrating both automated systems and human experts into workflows tailored to each specific problem.
|
Tina Comes, Michael Hiete, Niek Wijngaards, & Masja Kempen. (2009). Integrating scenario-based reasoning into multi-criteria decision analysis. In S. J. J. Landgren (Ed.), ISCRAM 2009 – 6th International Conference on Information Systems for Crisis Response and Management: Boundary Spanning Initiatives and New Perspectives. Gothenburg: Information Systems for Crisis Response and Management, ISCRAM.
Abstract: Multi-criteria decision analysis (MCDA) is a technique for decision support which aims at providing transparent and coherent support for complex decision situations taking into account subjective preferences of the decision makers. However, MCDA does not foresee an analysis of multiple plausible future developments of a given situation. In contrast, scenario-based reasoning (SBR) is frequently used to assess future developments on the longer term. The ability to discuss multiple plausible future developments provides a rationale for strategic plans and actions. Nevertheless, SBR lacks an in-depth performance evaluation of the considered actions. This paper explores the integration of both techniques that combines their respective strengths as well as their application in environmental crisis management. The proposed methodology is illustrated by an environmental incident example. Future work is to conduct validations on the basis of real-world scenarios by public Dutch and Danish chemical incident crisis management authorities.
|
Tina Comes, Niek Wijngaards, & Frank Schultmann. (2012). Efficient scenario updating in emergency management. In Z.Franco J. R. L. Rothkrantz (Ed.), ISCRAM 2012 Conference Proceedings – 9th International Conference on Information Systems for Crisis Response and Management. Vancouver, BC: Simon Fraser University.
Abstract: Emergency managers need to assess, combine and process large volumes of information with varying degrees of (un)certainty. To keep track of the uncertainties and to facilitate gaining an understanding of the situation, the information is combined into scenarios: stories about the situation and its development. As the situation evolves, typically more information becomes available and already acknowledged information is changed or revised. Meanwhile, decision-makers need to keep track of the scenarios including an assessment whether the infor-mation constituting the scenario is still valid and relevant for their purposes. Standard techniques to support sce-nario updating usually involve complete scenario re-construction. This is far too time-consuming in emergency management. Our approach uses a graph theoretical scenario formalisation to enable efficient scenario updating. MCDA techniques are employed to decide whether information changes are sufficiently important to warrant scenario updating. A brief analysis of the use-case demonstrates a large gain in efficiency. © 2012 ISCRAM.
|
Louise K. Comfort, Brian A. Chalfant, Jee Eun Song, Mengyao Chen, & Brian Colella. (2014). Managing information processes in disaster events: The impact of superstorm sandy on business organizations. In and P.C. Shih. L. Plotnick M. S. P. S.R. Hiltz (Ed.), ISCRAM 2014 Conference Proceedings – 11th International Conference on Information Systems for Crisis Response and Management (pp. 230–239). University Park, PA: The Pennsylvania State University.
Abstract: Building community resilience to natural disasters represents a major policy priority for the United States as hazards impact vulnerable urban regions with increasing frequency and severity. Applying network analysis techniques, we examine the dynamics of emergency response to Superstorm Sandy, which struck the United States east coast in late October 2012 and caused over $72 billion in damages. Drawing on a variety of data sources and analytical techniques, we document the storm's impact on a system of interacting private, public, and nonprofit organizations. We find that the storm's response network exhibited clear patterns of information gaps and flows among different types of organizations. Our findings suggest a general lack of communication between government agencies and businesses, an area of potential improvement in future regional-scale emergency response systems.
|
Louise K. Comfort, Brian Colella, Mark Voortman, Scott Connelly, Jill L. Drury, Gary L. Klein, et al. (2013). Real-time decision making in urgent events: Modeling options for action. In J. Geldermann and T. Müller S. Fortier F. F. T. Comes (Ed.), ISCRAM 2013 Conference Proceedings – 10th International Conference on Information Systems for Crisis Response and Management (pp. 571–580). KIT; Baden-Baden: Karlsruher Institut fur Technologie.
Abstract: Decision making in extreme events presents a difficult challenge to emergency managers who are legally responsible for protecting life, property, and maintaining continuity of operations for their respective organizations or communities. Prior research has identified the benefits of gaining situation awareness in rapidly changing disaster contexts, but situation awareness is not always sufficient. We have investigated “option awareness” and the decision space to provide cognitive support for emergency managers to simulate computationally possible outcomes of different options before they make a decision. Employing a user-centered design process, we developed a computational model that rapidly generates ranges of likely outcomes for different options and displays them visually through a prototype decision-space interface that allows rapid comparison of the options. Feedback from emergency managers suggests that decision spaces may enable emergency managers to consider a wider range of options for decisions and may facilitate more targeted, effective decision making under uncertain conditions.
|
Sherri L. Condon, & Jason R. Robinson. (2014). Communication media use in emergency response management. In and P.C. Shih. L. Plotnick M. S. P. S.R. Hiltz (Ed.), ISCRAM 2014 Conference Proceedings – 11th International Conference on Information Systems for Crisis Response and Management (pp. 687–696). University Park, PA: The Pennsylvania State University.
Abstract: The communications of emergency response managers were tracked during simulated catastrophic events at a university campus in the Washington, D.C. region. Local, state, and federal response managers interacted with each other and with students using a variety of communication media in order to investigate the utility of new communication channels for emergency response management. Students and emergency managers interacted using a Twitter-like platform and a portal built with Ushahidi crowd-sourcing software. The emergency managers also used a chat interface that included private instant messaging, telephone, and the county's existing emergency web portal. Their media use was analyzed along with the functions of their communications, and the patterns that emerged are described and quantified.
|
Congcong Wang, Paul Nulty, & David Lillis. (2021). Transformer-based Multi-task Learning for Disaster Tweet Categorisation. In Anouck Adrot, Rob Grace, Kathleen Moore, & Christopher W. Zobel (Eds.), ISCRAM 2021 Conference Proceedings – 18th International Conference on Information Systems for Crisis Response and Management (pp. 705–718). Blacksburg, VA (USA): Virginia Tech.
Abstract: Social media has enabled people to circulate information in a timely fashion, thus motivating people to post messages seeking help during crisis situations. These messages can contribute to the situational awareness of emergency responders, who have a need for them to be categorised according to information types (i.e. the type of aid services the messages are requesting). We introduce a transformer-based multi-task learning (MTL) technique for classifying information types and estimating the priority of these messages. We evaluate the effectiveness of our approach with a variety of metrics by submitting runs to the TREC Incident Streams (IS) track: a research initiative specifically designed for disaster tweet classification and prioritisation. The results demonstrate that our approach achieves competitive performance in most metrics as compared to other participating runs. Subsequently, we find that an ensemble approach combining disparate transformer encoders within our approach helps to improve the overall effectiveness to a significant extent, achieving state-of-the-art performance in almost every metric. We make the code publicly available so that our work can be reproduced and used as a baseline for the community for future work in this domain.
|
Gregorio Convertino, Helena M. Mentis, Prajakta Bhambare, Caitlin Ferro, John M. Carroll, & Mary Beth Rosson. (2008). Comparing media in emergency planning. In B. V. de W. F. Fiedrich (Ed.), Proceedings of ISCRAM 2008 – 5th International Conference on Information Systems for Crisis Response and Management (pp. 632–641). Washington, DC: Information Systems for Crisis Response and Management, ISCRAM.
Abstract: The research on technology for emergency management is usually based either on studies in the field that focus on workers using current tools or on the development, testing, and deployment of novel software tools used in controlled settings. Little is known about the effects of the new collaborative media and work conditions 'in comparison to' the current media and conditions. In 2007, we presented at ISCRAM a method for studying common ground development through a paper prototype in face-to-face collaboration and subsequently presented preliminary findings on common ground development. In this paper we present preliminary findings from an analogous experiment on teams working remotely via a geo-collaborative software prototype. We compare these findings with those from the prior paper prototype study. We use this comparative research design to explore implications for system design and theory development in computer-supported cooperative work.
|
Kelli de Faria Cordeiro, Maria Luiza M Campos, & Marcos R. S. Borges. (2014). Adaptive integration of information supporting decision making: A case on humanitarian logistic. In and P.C. Shih. L. Plotnick M. S. P. S.R. Hiltz (Ed.), ISCRAM 2014 Conference Proceedings – 11th International Conference on Information Systems for Crisis Response and Management (pp. 225–229). University Park, PA: The Pennsylvania State University.
Abstract: There is an urgent demand for information systems to gather heterogeneous information about needs, donations and warehouse stocks to provide an integrated view for decision making in humanitarian logistics. The dynamic flow of information, due to the unpredicted events, requires adaptive features. The traditional relational data model is not suitable due to its schema rigidity. As an alternative, Graph Data models complemented by semantic representations, like Linked Open Data on the Web, can be used. Based on both, this research proposes an approach for the adaptive integration of information and an associated architecture. An application example is discussed in a real scenario where relief goods are managed through a dynamic and multi-perspective view.
|
Erman Coskun, & Dilek Ozceylan. (2011). Complexity in emergency management and disaster response information systems (EMDRIS). 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: Today emergencies seem more complex than ever. Process of managing these emergencies also becomes more complex because of increasing number of involved parties, increasing number of people affected, and increasing amount of resources. This complexity, inherent in emergency management, brings lots of challenges to decision makers and emergency responders. Information systems and technologies are utilized in different areas of emergency management. However complexity increases exponentially in emergency situations and it requires more sophisticated IS and IT and it makes response and management more challenging. Thus analyzing the root causes of emergency management information systems complexity is crucial for improving emergency response effectiveness. This paper frames the issue of information systems complexity by focusing on the types of complexities involved in emergency management phases and explaining each complexity type. We propose 6 different complexity types: Human Complexity, Technologic Complexity, Event Complexity, Interaction Complexity, Decision Making Complexity, and Cultural Complexity.
|
Cossentino, M., Guastella, D. A., Lopes, S., & Sabatucci, L. (2023). Adaptive Execution of Workflows in Emergency Response. In Jaziar Radianti, Ioannis Dokas, Nicolas Lalone, & Deepak Khazanchi (Eds.), Proceedings of the 20th International ISCRAM Conference (pp. 784–796). Omaha, USA: University of Nebraska at Omaha.
Abstract: In emergencies, preparation is of paramount importance but it is not sufficient. As we know, emergency agencies develop extensive (text) plans to deal with accidents that could occur in their territories; their personnel train to enact such procedures, but, despite that, the unpredictable conditions that occur during an emergency require the ability to adapt the plan promptly. This paper deals with the last mile of a process we defined for enabling the adaptive execution of such emergency plans. In previous works, we discussed how to convert a free-text plan into a structured-text form, represent this plan using standard modelling notations, and extract goals that plans prescribe to be fulfilled. In this paper, we propose an approach for executing these plans with a workflow execution engine enriched by the capability to support runtime adaptation.
|
Martine Couturier, & Edith Wilkinson. (2005). Open advanced system for improved crisis management (OASIS). In B. C. B. Van de Walle (Ed.), Proceedings of ISCRAM 2005 – 2nd International Conference on Information Systems for Crisis Response and Management (pp. 283–286). Brussels: Royal Flemish Academy of Belgium.
Abstract: The OASIS Project addresses the Strategic objective 2.3.2.9, “Improving Risk Management”, of the second call for tender of the European Commission FP6 Information Society Technologies program. The objective of OASIS is to define and develop an Information Technology (IT) framework based on an open and flexible architecture and using standards that will be the basis of a European Emergency Management system. OASIS is intended to facilitate the cooperation between the information systems used by civil protection organisations, in a local, regional, national or international environment. This Disaster and Emergency Management system aims to support the response operations in the case of large scale as well as local emergencies.
|
Nuala M. Cowan. (2011). A geospatial data management framework for humanitarian response. 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: The success of humanitarian relief efforts is contingent upon the quality and timeliness of information provided to both the decision making and coordinating functions. Poor or fragmented information can lead to inappropriate decisions or poorly coordinated activities. This research focuses on how the application of spatially aware technologies can allow the information dimension of the challenge to become more effective. This will be achieved through the development of a comprehensive framework for the organization of spatially referenced humanitarian information, and corresponding geospatial data model for practical application in the field. The development of a spatial data framework that is both comprehensive and scalable can unleash the power of GIS for humanitarian data managers, and facilitate the collection and sharing of information between agencies that share similar goals. The research involves the development of a framework based on a literature review of best-practices, which will be refined and tested through interaction with the humanitarian information management community.
|
Cruz, J. A. dela, Hendrickx, I., & Larson, M. (2023). Towards XAI for Information Extraction on Online Media Data for Disaster Risk Management. In Jaziar Radianti, Ioannis Dokas, Nicolas Lalone, & Deepak Khazanchi (Eds.), Proceedings of the 20th International ISCRAM Conference (pp. 478–486). Omaha, USA: University of Nebraska at Omaha.
Abstract: Disaster risk management practitioners have the responsibility to make decisions at every phase of the disaster risk management cycle: mitigation, preparedness, response and recovery. The decisions they make affect human life. In this paper, we consider the current state of the use of AI in information extraction (IE) for disaster risk management (DRM), which makes it possible to leverage disaster information in social media. We consolidate the challenges and concerns of using AI for DRM into three main areas: limitations of DRM data, limitations of AI modeling and DRM domain-specific concerns, i.e., bias, privacy and security, transparency and accountability, and hype and inflated expectations. Then, we present a systematic discussion of how explainable AI (XAI) can address the challenges and concerns of using AI for IE in DRM.
|
Steven Curnin, & Christine Owen. (2013). A typology to facilitate multi-agency coordination. In J. Geldermann and T. Müller S. Fortier F. F. T. Comes (Ed.), ISCRAM 2013 Conference Proceedings – 10th International Conference on Information Systems for Crisis Response and Management (pp. 115–119). KIT; Baden-Baden: Karlsruher Institut fur Technologie.
Abstract: Multi-agency coordination in emergency management presents many challenges. Agencies that normally operate independently have to assemble into a unified supra organization to achieve a common goal. To achieve successful multi-agency coordination organizations need to span organizational boundaries and provide linkages with multiple agencies. This requires interorganizational compatibility of information and communication systems. Necessary for this success are the stakeholders responsible for facilitating these organizational boundary spanning activities. This paper proposes that the preliminary research findings can create a typology of dimensions crucial to facilitating multi-agency emergency management coordination. It is envisaged that the typology will culminate into a diagnostic tool that will enable stakeholders to examine the breakdowns and successes of multi-agency emergency management coordination.
|
Daniel Auferbauer, Christoph Ruggenthaler, Gerald Czech, & Ivan Gojmerac. (2019). Taxonomy of Community Interaction in Crises and Disasters. In Z. Franco, J. J. González, & J. H. Canós (Eds.), Proceedings of the 16th International Conference on Information Systems for Crisis Response And Management. Valencia, Spain: Iscram.
Abstract: Taxonomies are integral to systems engineering, as they structure our knowledge of a field and so provide the
foundation for technological development. We contribute such taxonomies for the field of Community
Interaction and Engagement in Crisis and Disaster Management, which represents the interface between
members of the public who commit to relief efforts and established organisations that have a pre-defined role in
crisis management. These actors are unified in their purpose to help those in need, but also set apart by their
organisational structures and modes of operation. We classify the actors of Community Interaction and
Engagement, as well as the interactions between them. Our contribution outlines areas where the application of
Information and Communication Technology can offer benefits to Community Interaction and Engagement.
|
Daniel Auferbauer, Roman Ganhör, & Hilda Tellioglu. (2015). Moving Towards Crowd Tasking for Disaster Mitigation. In L. Palen, M. Buscher, T. Comes, & A. Hughes (Eds.), ISCRAM 2015 Conference Proceedings ? 12th International Conference on Information Systems for Crisis Response and Management. Kristiansand, Norway: University of Agder (UiA).
Abstract: Advancements in information and communication technology (ICT) offer new possibilities when dealing with crisis situations. In this paper we present the design for a crowd tasking tool (CTT) that is currently under development. We describe how the tool can assist disaster relief coordinators during a crisis by selectively distributing tasks to a crowd of volunteers. We also compare the CTT with an already existing ICT based solution for supporting volunteerism during crisis. The differences between these two tools are addressed and the implications for volunteerism are discussed. The paper concludes with an outlook on future work emphasizing a form of volunteer involvement that offers potential for gathering information that is more relevant and easier to digest for decision-making than information provided solely by self-organised volunteers through social media.
|
Daniel Auferbauer, Roman Ganhör, & Hilda Tellioglu. (2019). Opportunistic Affiliation in Spontaneous Volunteer Management. In Z. Franco, J. J. González, & J. H. Canós (Eds.), Proceedings of the 16th International Conference on Information Systems for Crisis Response And Management. Valencia, Spain: Iscram.
Abstract: Spontaneous volunteers influence crisis and disaster relief efforts as both an effective aid and a stressing factor for emergency organisations. Managing the negative impacts of spontaneous volunteering has thus become part of command and control deliberations. In this paper, we take a closer look at integrating spontaneous volunteers into the formal response system to mitigate negative impacts.
Working with participants from formal response organisations, we gathered qualitative data regarding the management of spontaneous volunteers during the European migration crisis in 2015.
Through thematic analysis, we extracted topics to systematically describe the interaction between emergency organisations and spontaneous volunteers. As implication thereof, we propose how computer supported systems can be applied to better manage spontaneous volunteers. In our discussion, we focus on the registration process and ad hoc verification of spontaneous volunteers to better integrate them in the formal response process.
|
Daniel Auferbauer, Roman Ganhör, Hilda Tellioglu, & Jasmin Pielorz. (2016). Crowdtasking: Field Study on a Crowdsourcing Alternative. In A. Tapia, P. Antunes, V.A. Bañuls, K. Moore, & J. Porto (Eds.), ISCRAM 2016 Conference Proceedings ? 13th International Conference on Information Systems for Crisis Response and Management. Rio de Janeiro, Brasil: Federal University of Rio de Janeiro.
Abstract: In this paper we elaborate on the concept of crowdtasking as a form of crowdsourcing. The paper describes the setup and boundaries of a first controlled live field test of a prototypical implementation of a possible crowdtasking workflow. The implemented workflow allows crisis managers rapid intelligence gathering due to direct and tailored task distribution. Practitioners of Crisis and Disaster Management and volunteer managers who were present during the field test made favourable comments on the approach and its implementation. The analysis of the records and the conducted interviews give new insights and ideas for further development.
|
Daniel Link, Bernd Hellingrath, & Jie Ling. (2016). A Human-is-the-Loop Approach for Semi-Automated Content Moderation. In A. Tapia, P. Antunes, V.A. Bañuls, K. Moore, & J. Porto (Eds.), ISCRAM 2016 Conference Proceedings ? 13th International Conference on Information Systems for Crisis Response and Management. Rio de Janeiro, Brasil: Federal University of Rio de Janeiro.
Abstract: Online social media has been recognized as a valuable information source for disaster management whose volume, velocity and variety exceed manual processing capacity. Current machine learning systems that support the processing of such data generally follow a human-in-the-loop approach, which has several inherent limitations. This work applies the human-is-the-loop concept from visual analytics to semi-automate a manual content moderation workflow, wherein human moderators take the dominant role. The workflow is instantiated with a supervised machine learning system that supports moderators with suggestions regarding the relevance and categorization of content. The instantiated workflow has been evaluated using in-depth interviews with practitioners and serious games. which suggest that it offers good compatibility with work practices in humanitarian assessment as well as improved moderation quality and higher flexibility than common approaches.
|
Dashley K. Rouwendal van Schijndel, Jo E. Hannay, & Audun Stolpe. (2020). Simulation Vignette Generation from Answer Set Specifications. 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. 110–121). Blacksburg, VA (USA): Virginia Tech.
Abstract: We investigate an approach that allows exercise managers to design simulations with an explicit focus on building skills, rather than having to focus on all the objects and interactions that a simulation must have. Exercise managers may design exercises at various levels of abstraction and always independently of how those sessions are implemented in simulations, while simulation components that implement the design are assembled and to some extent, automatically, behind the scenes. We outline (1) how Answer Set Programming can assist exercise managers in exercise planning and (2) how automated stage and content generation may be used to invoke appropriate simulation components to realize the design. For deliberate and recurrent training of decision-making skills, stages and content must vary to avoid familiarity (testing effects). We conclude by distilling a main research hypothesis that stipulates how (1) and (2) represent two modes of automated reasoning (so-called deductive versus abductive) and how that distinction clarifies the planning task.
|
Dat T. Nguyen, Firoj Alam, Ferda Ofli, & Muhammad Imran. (2017). Automatic Image Filtering on Social Networks Using Deep Learning and Perceptual Hashing During Crises. 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. 499–511). Albi, France: Iscram.
Abstract: The extensive use of social media platforms, especially during disasters, creates unique opportunities for humanitarian organizations to gain situational awareness and launch relief operations accordingly. In addition to the textual content, people post overwhelming amounts of imagery data on social networks within minutes of a disaster hit. Studies point to the importance of this online imagery content for emergency response. Despite recent advances in the computer vision field, automatic processing of the crisis-related social media imagery data remains a challenging task. It is because a majority of which consists of redundant and irrelevant content. In this paper, we present an image processing pipeline that comprises de-duplication and relevancy filtering mechanisms to collect and filter social media image content in real-time during a crisis event. Results obtained from extensive experiments on real-world crisis datasets demonstrate the significance of the proposed pipeline for optimal utilization of both human and machine computing resources.
|
Dragos Datcu, & Leon J.M. Rothkrantz. (2007). The use of active appearance model for facial expression recognition in crisis environments. 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. 515–524). Delft: Information Systems for Crisis Response and Management, ISCRAM.
Abstract: In the past a crisis event was notified by local witnesses that use to make phone calls to the special services. They reported by speech according to their observation on the crisis site. The recent improvements in the area of human computer interfaces make possible the development of context-aware systems for crisis management that support people in escaping a crisis even before external help is available at site. Apart from collecting the people's reports on the crisis, these systems are assumed to automatically extract useful clues during typical human computer interaction sessions. The novelty of the current research resides in the attempt to involve computer vision techniques for performing an automatic evaluation of facial expressions during human-computer interaction sessions with a crisis management system. The current paper details an approach for an automatic facial expression recognition module that may be included in crisis-oriented applications. The algorithm uses Active Appearance Model for facial shape extraction and SVM classifier for Action Units detection and facial expression recognition.
|
Dragos Datcu, & Leon J.M. Rothkrantz. (2008). A Dialog Action Manager for automatic crisis management. In B. V. de W. F. Fiedrich (Ed.), Proceedings of ISCRAM 2008 – 5th International Conference on Information Systems for Crisis Response and Management (pp. 384–393). Washington, DC: Information Systems for Crisis Response and Management, ISCRAM.
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.
|
