Abstract: This article aims at presenting a whole approach of Information Systems interoperability management in a crisis management cell. We propose a Mediation Information System (MIS) to help the crisis cell partners to design, run and manage the workflows of the response to a crisis situation. The architecture of the MIS meets the need of low coupling between the partners' Information System components and the need of agility for a such platform. Based on the Service Oriented Architecture (SOA) and the Event Driven Architecture (EDA) principles which, combined to the Complex Event Processing (CEP) principles, it will leads to an easier orchestration, choreography and real-time monitoring of the workflows' activities, and even allows the automated agility of the crisis response on-the-fly-we consider agility as the ability of the processes to remain consistent with the response to the crisis-. © 2012 ISCRAM.

Abstract: This paper describes the WIPER system, a proof of concept prototype, and progress made on its development to date. WIPER is intended to provide emergency response managers with an integrated system that detects possible emergencies from cellular communication data, attempts to predict the development of emergency situations, and provides tools for evaluating possible courses of action in dealing with emergency situations. We describe algorithms for detecting anomalies in streaming cellular communication network data, the implementation of a simulation system that validates running simulations with new real world data, and a web-based front end to the WIPER system. We also discuss issues relating to the real-time aggregation of data from the cellular service provider and its distribution to components of the WIPER system.

Abstract: Good support for information sharing and processing is essential for successful crisis management. A crisis manager handles information from many different sources and collaborates with many different actors. This study is therefore focusing on specifying some needs and requirements for information support systems for crisis management command and control centres. The study is based on case studies and interviews in Sweden with the aim to understand how information processing best can be supported from a crisis manager's perspective. The needs and requirements found in the study can be used in future system design or improvement.

Abstract: Efficient management of mass casualty incidents is complex, since regular emergency medical services structures have to be switched to a temporary “disaster mode” involving additional operational and tactical structures. Most of the relevant decisions have to be taken on-site in a provisional and chaotic environment. Data gathering about affected persons is one side of the coin; the other side is on-site patient dispatching requiring information exchange with the regular emergency call center and destination hospitals. In this paper we extend a previous conference contribution about the research project e-Triage to the aspect of patient data and on-site patient dispatching. Our considerations reflect the situation in Germany, which deserves from our point of view substantial harmonization. © 2012 ISCRAM.

Abstract: Upon developing a software agent-based simulator for training roles in emergency response scenarios, the PARVAC team at the University of Washington has pursued building a tool for better investigative review and insight generation on the performance of an emergency response game session team. While our RimSim Response software included the opportunity to re-run a simulated team performance in order to review player and agent behavior, we did not provide our trainees the ability to visually query their performance outside of a sequential review of the emergency response effort. By integrating our RSR visualization components with an existing visual query software package called Improvise, we were able to construct highly-coordinated visualizations of our data model for the ability to apply a sense making approach in the investigation of live player and software agent-based behavior – both as individual players and as combinations of players working on tasks associated with an emergency response scenario. The resultant tool is now our primary visualization tool for discussing first responder team performance and supports the overall RSR objective of training teams to make the most effective, recognition-primed decisions when a real emergency crisis occurs in their community. This paper reviews our visualization tool and demonstrates its use.

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.

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.

Abstract: People increasingly use microblogging platforms such as Twitter during natural disasters and emergencies. Research studies have revealed the usefulness of the data available on Twitter for several disaster response tasks. However, making sense of social media data is a challenging task due to several reasons such as limitations of available tools to analyze high-volume and high-velocity data streams. This work presents an extensive multidimensional analysis of textual and multimedia content from millions of tweets shared on Twitter during the three disaster events. Specifically, we employ various Artificial Intelligence techniques from Natural Language Processing and Computer Vision fields, which exploit different machine learning algorithms to process the data generated during the disaster events. Our study reveals the distributions of various types of useful information that can inform crisis managers and responders as well as facilitate the development of future automated systems for disaster management.

Abstract: Despite intense research on decision-making in action, we still know little about when decision-makers rely on deliberate vs. intuitive decision-making in decision situations under complexity and uncertainty. This paper studies decision-making modes (deliberate vs. intuitive) in complex task environments contingent on perceived complexity, experience, and decision style preference. We find that relatively inexperienced decision-makers respond to increases in subjective complexity with an increase in deliberation and tend to follow their decision style preference. Experienced decision-makers are less guided by their decision preference and respond to increases in subjective complexity only minimally. Our paper contributes to a developing stream of research linking decision-making with intra-personal and environmental properties and fosters our understanding of the conditions under which decision-makers rely on intuitive vs. deliberate decision modes. In doing so, we go one step further towards a comprehensive theory of decision-making in action.

Abstract: Social media has recently become a digital lifeline used to relay information and locate survivors in disaster situations. Currently, officials and volunteers scour social media for any valuable information; however, this approach is implausible as millions of posts are shared by the minute. Our goal is to automate actionable information extraction from social media posts to efficiently direct relief resources. Identifying damage and human casualties allows first responders to efficiently allocate resources and save as many lives as possible. Since social media posts contain text, images and videos, we propose a multimodal deep learning framework to identify damage related information. This framework combines multiple pretrained unimodal convolutional neural networks that extract features from raw text and images independently, before a final classifier labels the posts based on both modalities. Experiments on a home-grown database of labeled social media posts showed promising results and validated the merits of the proposed approach.

Abstract: The application of event processing methods and systems carries high potential for the domain of crisis management and emergency response for different use cases and architectural aspects. This hypothesis is based on the general event based characteristics of the domain as well as former research approaches. Resource management represents a complex task for decision makers; therefore it is taken as a basic use case for this work. It builds up on foundations of resource management (use case and demand side) and event processing (technology and supply side). Methods and results are presented for the identification, definition and validation of events that happen in reality and corresponding event objects which are processed by information systems.

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.