Alexander Almer, Thomas Schnabel, Johann Raggam, Armin Köfler, Roland Wack, & Richard Feischl. (2015). Airborne multi-sensor management support system for emergency teams in natural disasters. 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: This paper describes the development of a multi-functional airborne management support system within the frame of the Austrian national safety and security research programme. The objective was to assist crisis management tasks of emergency teams and armed forces in disaster management by providing multi spectral, near real-time airborne image data products. As time, flexibility and reliability as well as objective information are crucial aspects in emergency management, the used components are tailored to meet these requirements. This article includes the individual system components as well as their performance using examples from lab tests and real-life deployments. Based on this, the impact of existing command and control processes as well as the benefits for time critical decision making processes are described based on expertise of the involved end users. In addition, it gives an outlook on future perspectives.
|
Alexander Garcia-Aristizabal, Maria Polese, Giulio Zuccaro, Miguel Almeida, & Christoph Aubrecht. (2015). Improving emergency preparedness with simulation of cascading events scenarios. 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: Natural or man-made disasters can trigger other negative events leading to tremendous increase of fatalities and damages. In case of Low Probability ? High consequences events, decision makers are faced with very difficult choices and the availability of a tool to support emergency decisions would be very much beneficial. Within EU CRISMA project a concept model and tool for evaluating cascading effects into scenario-based analyses was implemented.This paper describes the main concepts of the model and demonstrates its application with reference to two earthquake-triggered CE scenarios, including (the first) the falling of an electric cable, ignition and spreading of forest fire and (the second) the happening of a second earthquake in a sequence. Time dependent seismic vulnerability of buildings and population exposure are also considered for updating impact estimation during an earthquake crisis.
|
Bo Andersson, & Jonas Hedman. (2006). Issues in the development of a mobile based communication platform for the swedish police force and appointed security guards. In M. T. B. Van de Walle (Ed.), Proceedings of ISCRAM 2006 – 3rd International Conference on Information Systems for Crisis Response and Management (pp. 181–187). Newark, NJ: Royal Flemish Academy of Belgium.
Abstract: This paper presents the learning experiences from the development of a mobile-based communication platform, called OrdningsVaktsCentralen (OVC). OVC can be translated to Security Guard Central. OVC is designed to enable the Swedish Police Force (SPF) to comply with new legal requirements and enhance their collaboration with Appointed Security Guards (ASG). The focus of this paper is on the early phases of development; in particular on the specific technical issues such as interoperability and standards used in the development of mobile based systems. The learning experiences are as follows: firstly, when developing mobile based systems we suggest and recommend that the analysis phase should be enhanced and it should address the interoperability between mobile phones on one hand and operators on the other hand. Secondly, global and national standards, such as the MMS7 for sending multi-media messages, are not always standardized. It seems that operators and mobile phone manufacturers make minor alterations and interpretations of the standard and thereby some of the benefits found in standards disappear. Thirdly, mobile based communication platforms have a large potential for contributing to the field of emergency management information systems since they can be based on open and nationally accepted standards.
|
Dennis Andersson, Sofie Pilemalm, & Niklas Hallberg. (2008). Evaluation of crisis management operations using Reconstruction and Exploration. In B. V. de W. F. Fiedrich (Ed.), Proceedings of ISCRAM 2008 – 5th International Conference on Information Systems for Crisis Response and Management (pp. 118–125). Washington, DC: Information Systems for Crisis Response and Management, ISCRAM.
Abstract: In this paper we present the Reconstruction and Exploration approach (R&E) and F-REX tool and their applications in a field exercise with the Swedish Rescue Services Agency with the purpose of investigating features needed for a computer supported approach for evaluation of large scale crisis management operations. After the exercise several interviews and one seminar were held to evaluate R&E as a representative for computer supported evaluation approaches for crisis management operations. Initial results indicate that multimedia presentation of key events from an operation can be very valuable not only to stimulate the participants to reflect on their own performance, but also to document and share lessons learned to non-participants.
|
Andrew Sherson, S Uma, & Raj Prasanna. (2018). The effect of localised factors on water pipe repair times post-earthquake. In Kristin Stock, & Deborah Bunker (Eds.), Proceedings of ISCRAM Asia Pacific 2018: Innovating for Resilience – 1st International Conference on Information Systems for Crisis Response and Management Asia Pacific. (pp. 366–380). Albany, Auckland, New Zealand: Massey Univeristy.
Abstract: In the Wellington Region, many lifelines are at risk, because they are in vulnerable narrow corridors close to active faults. In an earthquake, it is expected that these lifelines will be significantly damaged and unusable for extended periods of time. Because of this risk, many studies have been conducted to investigate the resulting downtimes. These studies, despite their usefulness, do not incorporate or make significant assumptions about localised factors. This paper summarises a thesis that aimed to improve the current predictive models, by including these local, and contextual influences. Multiple stakeholders who manage and repair the lifelines were interviewed to identify these factors which were then included into one of the current predictive models, and the influence on repair times was recorded. It was discovered that localised impacts such as staff logistics, land sliding, the land gradient, interdependency, and access doubled previous predicted repair times.
|
Asmelash Teka Hadgu, Sallam Abualhaija, & Claudia Niederée. (2019). Real-time Adaptive Crawler for Tracking Unfolding Events on Twitter. 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: When a major event such as a crisis situation occurs, people post messages on social media sites such as Twitter, in
order to exchange information or to share emotions. These posts can provide useful information to raise situation
awareness and support decision making, e.g., by aid organizations. In this paper, we propose a novel method for
social media crawling, which exploits a Bayesian inference framework to keep track of keyword changes over time
and uses a counter-stream to gauge the inclusion of noise and irrelevant information. In addition, we present a
framework to evaluate real-time adaptive social search algorithms in a reproducible manner, which relies on a
semi-automated approach for ground-truth construction. We show that our method outperforms previous methods
for very large scale events.
|
Ayda Kianmehr, & Duygu Pamukcu. (2022). Analyzing Citizens’ Needs during an Extreme Heat Event, based on 311 Service Requests: A Case Study of the 2021 Heatwave in Vancouver, British Columbia. In Rob Grace, & Hossein Baharmand (Eds.), ISCRAM 2022 Conference Proceedings – 19th International Conference on Information Systems for Crisis Response and Management (pp. 174–182). Tarbes, France.
Abstract: Heat waves are becoming more common and intense with global climate change, which requires deploying resilience strategies of governments to prepare for long-term trends of higher temperatures and carefully plan emergency responses for such extreme heat events. The British Columbia province of Canada is one of the regions severely affected by extreme climatic events in 2021, which resulted in several deaths and put hundreds of thousands of people scrambling for relief. This study examines the public reactions to one of these extreme climatic events, the 2021 Pacific Northwest heatwave, in a non-emergency service request platform to uncover the types of municipal service needs during severe climatic disasters. City of Vancouver 311 system data is used to identify the impact of the heatwave on the frequency and types of service needs and examine the significance of the relationship between climatic conditions and the non-emergency service volumes.
|
Michael R. Bartolacci, Christoph Aubrecht, & Dilek Ozceylan Aubrecht. (2014). A portable base station optimization model for wireless infrastructure deployment in disaster planning and 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. 50–54). University Park, PA: The Pennsylvania State University.
Abstract: Disaster response requires communications among all affected parties including emergency responders and the affected populace. Wireless telecommunications, if available through a fixed structure cellular mobile network, satellites, portable station mobile networks and ad hoc mobile networks, can provide this means for such communications. While the deployment of temporary mobile networks and other wireless equipment following disasters has been successfully accomplished by governmental agencies and mobile network providers following previous disasters, there appears to be little optimization effort involved with respect to maximizing key performance measures of the deployment or minimizing overall 'cost' (including time aspects) to deploy. This work-in-progress does not focus on the question of what entity will operate the portable base during a disaster, but on optimizing the placement of mobile base stations or similar network nodes for planning and real time management purposes. An optimization model is proposed for the staging and placement of portable base stations to support disaster relief efforts.
|
Alena L. Benson, Keith Biggers, Jim Wall, & Mark P. Haselkorn. (2010). Adaptive development of a common operating environment for crisis response and 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: Complex information and communication systems present a special challenge to system designers because these are generally deployed as large, distributed systems with diverse user groups. Crisis response and management organizations in particular expect systems to be interoperable, resilient, flexible and provide lasting benefit. Currently, systems such as Virtual USA (Department of Homeland Security) and WatchKeeper (United States Coast Guard) seek to create common situational awareness for all participating agencies in security and incident response operations. We propose adaptive development as a system development model to build upon the ideas of systems such as Virtual USA and WatchKeeper in order to create sustainable and adaptable systems. Adaptive development supports ongoing improvement through user-driven design and modification in the target environment. An internet-based dashboard demonstrated during a United States Coast Guard Sector Seattle incident response exercise serves as an emergent case study for the adaptive model.
|
Lindsley G. Boiney, Bradley Goodman, Robert Gaimari, Jeffrey Zarrella, Christopher Berube, & Janet Hitzeman. (2008). Taming multiple chat room collaboration: Real-time visual cues to social networks and emerging threads. In B. V. de W. F. Fiedrich (Ed.), Proceedings of ISCRAM 2008 – 5th International Conference on Information Systems for Crisis Response and Management (pp. 660–668). Washington, DC: Information Systems for Crisis Response and Management, ISCRAM.
Abstract: Distributed teams increasingly rely on collaboration environments, typically including chat, to link diverse experts for real time information sharing and decision-making. Current chat-based technologies enable easy exchange of information, but don't focus on managing those information exchanges. Important cues that guide face-to-face collaboration are either lost or missing. In some military environments, operators may juggle over a dozen chat rooms in order to collaborate on complex missions. This often leads to confusion, overload, miscommunication and delayed decisions. Our technology supports chat management. A summary display bar reduces the number of chat rooms operators need open by providing high level situational awareness pointers, in real-time, to: a) rooms with increasing message activity levels, b) rooms in which important collaborators are participating (those in the operator's social network), and c) rooms in which operator-selected keywords are used. This ability to peripherally monitor less critical chat rooms reduces operator overload, while enhancing the ability to rapidly detect important emerging discussion threads. © 2008 The MITRE Corporation. All rights reserved.
|
Aaron Burgman, Nikhil Kalghatgi, Erika Darling, Chris M. Newbern, Kristine Recktenwald, Shawn Chin, et al. (2006). Emergency data analysis via semantic lensing. In M. T. B. Van de Walle (Ed.), Proceedings of ISCRAM 2006 – 3rd International Conference on Information Systems for Crisis Response and Management (pp. 334–338). Newark, NJ: Royal Flemish Academy of Belgium.
Abstract: Emergency situations often play out over extended geographic regions and can present response personnel with numerous types of data at various level of detail. Such data may be displayed in mapping software tools that organize the data into layers. Sufficiently complex scenarios can result in dense, occluded, and cluttered map displays. We investigated a localized, detail-on-demand filtering strategy called semantic lensing that in certain situations provides a more efficient and desirable approach than filtering global layers for mitigating clutter and occlusion. An initial formal user study with these semantic lenses has shown their value in aiding decision makers during tasks that might occur during detection of and response to emergency situations. Completion times are significantly faster when using lenses, and workloads are significantly lower. Future work will evaluate additional features and task-specific applicability, and may support the distribution of such a lens tool to emergency preparedness and response personnel.
|
Cornelia Caragea, Anna Squicciarini, Sam Stehle, Kishore Neppalli, & Andrea H. Tapia. (2014). Mapping moods: Geo-mapped sentiment analysis during hurricane sandy. 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. 642–651). University Park, PA: The Pennsylvania State University.
Abstract: Sentiment analysis has been widely researched in the domain of online review sites with the aim of generating summarized opinions of product users about different aspects of the products. However, there has been little work focusing on identifying the polarity of sentiments expressed by users during disaster events. Identifying sentiments expressed by users in an online social networking site can help understand the dynamics of the network, e.g., the main users' concerns, panics, and the emotional impacts of interactions among members. Data produced through social networking sites is seen as ubiquitous, rapid and accessible, and it is believed to empower average citizens to become more situationally aware during disasters and coordinate to help themselves. In this work, we perform sentiment classification of user posts in Twitter during the Hurricane Sandy and visualize these sentiments on a geographical map centered around the hurricane. We show how users' sentiments change according not only to users' locations, but also based on the distance from the disaster.
|
Mifan Careem, David Bitner, & Ravindra De Silva. (2007). GIS integration in the Sahana disaster management system. 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. 211–218). Delft: Information Systems for Crisis Response and Management, ISCRAM.
Abstract: Disaster Management often involves using Information and Communications Technology (ICT) to manage large amounts of data efficiently. Data gathered from disasters are often related to geographic locations, such as the affected geographic region, thus requiring special forms of data management software to utilize and manage them efficiently. Geographic Information Systems (GIS) are specialized database systems with software that can analyze and display data using digitized maps and tables for decision making. Preparing and correctly formatting data for use in a GIS is nontrivial, and it is even more challenging during disasters because of tight time constraints and inherent unpredictability of many natural disasters. This paper describes the important role of GIS in disaster management, and discusses the most common characteristics of GIS and their potential use in disaster response. We follow up with a detailed description of the GIS prototype in the Sahana Disaster Management System.
|
Mark De Bruijne. (2007). Networked reliability: From monitoring to incident management. 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. 385–393). Delft: Information Systems for Crisis Response and Management, ISCRAM.
Abstract: The environment of many HROs in modern, western countries have undergone dramatic changes in the last decades. They have changed from High Reliability Organizations (HROs) into High Reliability Networks (HRNs). In nearly all industries, the formerly vertically integrated, state-owned monopolies were 'unbundled' and in many segments, competition was introduced. Consequently, the services of modern-day large-scale technical systems are provided by networks of organizations. In-depth research in a number of infrastructure industries explored the consequences of these changes for the reliable provision of services in networks of organizations. In networks of organizations, reliability is increasingly achieved through 'real-time' management. This paper highlights three important consequences of these findings and provides some tentative conclusions about their effect on the design and use of Information Systems in complex, large-scale technical systems.
|
Tom De Groeve, & Patrick Riva. (2009). Early flood detection and mapping for humanitarian response. 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: Space-based river monitoring can provide a systematic, timely and impartial way to detect floods of humanitarian concern. This paper presents a new processing method for such data, resulting in daily flood magnitude time series for any arbitrary observation point on Earth, with lag times as short as 4h. Compared with previous work, this method uses image processing techniques and reduces the time to obtain a 6 year time series for an observation site from months to minutes, with more accurate results and global coverage. This results in a daily update of major floods in the world, with an objective measure for their magnitude, useful for early humanitarian response. Because of its full coverage, the grid-based technique also allows the automatic creation of low-resolution flood maps only hours after the satellite passes, independent of cloud coverage.
|
Gonçalo De Jesus, Anabela Oliveira, Maria A. Santos, & João Palha-Fernandes. (2010). Development of a dam-break flood emergency information system. 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 a new information system, SAGE-B, structured to support all fundamental data related to dams and the elements associated to an emergency in case of a dam-break flood. Data such as information about the population located in the areas at risk or the vehicles available for rescue that are located in the areas impacted by the predicted flood are always changing. In order to support an effective update of the required information for emergency management, an emergency information system was conceived and proposed. This paper describes the motivation for this research and the basic requirements from an emergency management perspective. The platform has a modular architecture, developed in open and free technologies, which allows a continuous development and improvement. Examples of future developments include a multichannel emergency warning system, flood wave real-time forecast and dam-breaching real-time monitoring models.
|
Alvaro Pemartin De La Calle, & Murray Turoff. (2011). Three hundred decisions a day: A case study of local crisis management. 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: This paper is a case study of an emergency medical dispatch system that describes its operations and difficulties Emergency Management in Andalusia is the responsibility of the Internal Affairs Authority that operates in each province a Coordination Center that receives Emergency Calls and in cases where there is a medical emergency, passes the information to the Emergency Coordination Centers. The 112 Centers gather all the information generated in emergency situations and supposedly coordinate the response of the several emergency services (Police, and Fire Departments) that operate their own coordination centers. If necessary they send a medical request to the 112 Center that, acting as a hub, sends to EPES the information about the medical incident.
|
Valerio De Rubeis, Paola Sbarra, Diego Sorrentino, & Patrizia Tosi. (2009). Web based macroseismic survey: Fast information exchange and elaboration of seismic intensity effects in Italy. 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: A renewed method of macroseismic survey, based on voluntary collaboration through Internet, is running at Istituto Nazionale di Geofisica e Vulcanologia (INGV) since June 2007. The macroseismic questionnaire is addressed to a single non-specialist person; reported effects are statistically analyzed to extrapolate Mercalli-Cancani-Sieberg and European Macroseismic Scale intensity referred to that observer. Maps of macroseismic intensity are displayed online in almost real time and are continuously updated. The aim of the questionnaire is to evaluate seismic effects as felt by the compiler. The final result is the definition of a particular intensity degree, with the evaluation of the associated uncertainty. Results of medium-low magnitude earthquakes are here presented showing the ability of the method in giving fast and interesting results. Effects reported in questionnaires coming from towns are analyzed in deep and assigned intensities are compared with those derived from traditional macroseismic survey, showing the reliability of webbased method.
|
André Dittrich, & Christian Lucas. (2013). A step towards real-time analysis of major disaster events based on tweets. 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. 868–874). KIT; Baden-Baden: Karlsruher Institut fur Technologie.
Abstract: The most popular micro blogging platform Twitter has been the topic of a variety of research papers related to disaster and crisis management. As an essential first step and basis for a real-time methodology to exploit Twitter for event detection, localization and ultimately semantic content analysis, a functional model to describe the amount of tweets during a day has been developed. It was derived from a corpus of messages in an exemplary area of investigation. To satisfy the different daily behavior on particular days, two types of days are distinguished in this paper. Moreover, keyword-adjusted data is used to point out the potential of semantic tweet analysis in following steps. The consideration of spatial event descriptions in relevant tweets could significantly improve and accelerate the perception of a disaster. The results from the conducted tests demonstrate the capability of the functional model to detect events with significant social impact in Twitter data.
|
Douglas A. Samuelson, Matthew Parker, Austin Zimmerman, Loren Miller, Stephen Guerin, Joshua Thorp, et al. (2008). Agent-based simulations of mass egress after Improvised Explosive Device attacks. In B. V. de W. F. Fiedrich (Ed.), Proceedings of ISCRAM 2008 – 5th International Conference on Information Systems for Crisis Response and Management (pp. 59–70). Washington, DC: Information Systems for Crisis Response and Management, ISCRAM.
Abstract: For the Science and Technology Directorate (S&T) of the U. S. Department of Homeland Security, we developed agent-based computer simulation models of mass egress from a stadium and a subway station following one or more attacks with Improvised Explosive Devices (IEDs.) Anti-IED countermeasures we modeled included improved guidance to exits, baffles to absorb shock and shrapnel, and, for the stadium, egress onto the playing field. We found improved real-time information systems that provide better guidance to exits would substantially expedite egress and could reduce secondary (trampling and crush) casualties. Our results indicate that models like these can be useful aids to selecting countermeasures, and for training, preparation and exercises. We also discuss the unusual problems such models pose for real-time event management and for validation and evaluation.
|
Julie Dugdale, Bernard Pavard, Nico Pallamin, Mehdi El Jed, & Laurent Maugan. (2004). Emergency fire incident training in a virtual world. In B. C. B. Van de Walle (Ed.), Proceedings of ISCRAM 2004 – 1st International Workshop on Information Systems for Crisis Response and Management (pp. 167–172). Brussels: Royal Flemish Academy of Belgium.
Abstract: The effectiveness of 'close to reality' training simulations is due to the fact that they provide a sense of immersion and allow several participants to interact naturally. However, they are expensive, time-consuming, difficult to organise and have a limited scope. We present a virtual reality training simulator which overcomes these disadvantages. We describe the approach and methodology and conclude with a discussion of the most crucial challenges when developing such a system. In this paper we would like to introduce the notion of cultural technologies which produce a sense of social as well as cultural immersion. We will discuss the main ingredients of such an immersion, in particular the notion of situated virtual interaction (how interactions in a virtual world can be comparable with human interactions in real situations). We also discuss on the role of interfaces (real time motion capture) and emotional expression in the design of such environments. © Proceedings ISCRAM 2004.
|
Jerome A. Duval. (2008). WebEOC Resource Manager® a collaborative framework: Developing standard Resource Management processes for disaster relief. In B. V. de W. F. Fiedrich (Ed.), Proceedings of ISCRAM 2008 – 5th International Conference on Information Systems for Crisis Response and Management (127). Washington, DC: Information Systems for Crisis Response and Management, ISCRAM.
Abstract: I will demonstrate ESi's WebEOC Resource Manager® tool, which enables users to catalog and deploy resources in a manner that is compliant with FEMA's National Incident Management System (NIMS). The system is a proven and tested deployed in over 25 states throughout the U.S. The tool provides real-time data sharing in a collaborative and fast-paced environment.
|
Fatehkia, M., Imran, M., & Weber, I. (2023). Towards Real-time Remote Social Sensing via Targeted Advertising. In Jaziar Radianti, Ioannis Dokas, Nicolas Lalone, & Deepak Khazanchi (Eds.), Proceedings of the 20th International ISCRAM Conference (pp. 396–406). Omaha, USA: University of Nebraska at Omaha.
Abstract: Social media serves as an important communication channel for people affected by crises, creating a data source for emergency responders wanting to improve situational awareness. In particular, social listening on Twitter has been widely used for real-time analysis of crisis-related messages. This approach, however, is often hindered by the small fraction of (hyper-)localized content and by the inability to explicitly ask affected populations about aspects with the most operational value. Here, we explore a new form of social media data collected through targeted poll ads on Facebook. Using geo-targeted ads during flood events in six countries, we show that it is possible to collect thousands of poll responses within hours of launching the ad campaign, and at a cost of a few (US dollar) cents per response. We believe that this flexible, fast, and affordable data collection can serve as a valuable complement to existing approaches.
|
Ferda Ofli, Firoj Alam, & Muhammad Imran. (2020). Analysis of Social Media Data using Multimodal Deep Learning for Disaster Response. 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. 802–811). Blacksburg, VA (USA): Virginia Tech.
Abstract: Multimedia content in social media platforms provides significant information during disaster events. The types of information shared include reports of injured or deceased people, infrastructure damage, and missing or found people, among others. Although many studies have shown the usefulness of both text and image content for disaster response purposes, the research has been mostly focused on analyzing only the text modality in the past. In this paper, we propose to use both text and image modalities of social media data to learn a joint representation using state-of-the-art deep learning techniques. Specifically, we utilize convolutional neural networks to define a multimodal deep learning architecture with a modality-agnostic shared representation. Extensive experiments on real-world disaster datasets show that the proposed multimodal architecture yields better performance than models trained using a single modality (e.g., either text or image).
|
Florian Brauner, Thomas Münzberg, Marcus Wiens, Frank Fiedrich, Alex Lechleuthner, & Frank Schultmann. (2015). Critical Infrastructure Resilience: A Framework for Considering Micro and Macro Observation Levels. 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: The resilience mechanisms of Critical Infrastructures (CIs) are often hard to understand due to system complexity. With rising research interest, models are developed to reduce this complexity. However, these models imply reductions and limitations. According to the level of observation, models either focus on effects in a CI system or on effects in a single CI. In cases of limited resources, such limitations exclude some considerations of crisis interventions, which could be identified in combining both observation levels. To overcome these restrictions, we propose a two-step framework which enables to analyze the vulnerability of a CI and as well in comparison to other CIs. This enhances the understanding of temporal crisis impacts on the overall performance of the supply, and the crisis preparations in each CI can be assessed. The framework is applied to the demonstrating example of the functionalities of hospitals that are potentially suffering from a power outage.
|
