Abstract: ComPlan (A Combined, Collaborative Command and Control Planning tool) is an approach to providing knowledge-based decision support in the context of command and control. It combines technical research on automated planning tools with human-centered research on mission planning. At its core, ComPlan uses interconnected views of a planning situation to present and manipulate aspects of a scenario. By using domain knowledge flexibly, it presents immediate and directly visible feedback on constraint violations of a plan, facilitates mental simulation of events, and provides support for synchronization of concurrently working mission planners. The conceptual framework of ComPlan is grounded on three main principles from human-centered research on command and control: transparency, graceful regulation, and event-based feedback. As a result, ComPlan provides a model for applying a human-centered perspective on plan authoring tools for command and control, and a demonstration for how to apply that model in an integrated plan-authoring environment.

Abstract: Understanding the COVID-19 pandemic impacts on low-income households can inform social services about the needs of vulnerable communities. Some recent works have studied such impacts through social media content analysis, and supervised machine learning models have been proposed to automatically classify COVID-19 tweets into different categories, such as income and economy impacts, social inequality and justice issues, etc. In this paper, we propose semi-supervised learning models based on BERT with Self-Training and Knowledge Distillation for identifying COVID-19 tweets relevant to low-income households by leveraging readily available unlabeled data in addition to limited amounts of labeled data. Furthermore, we explore ChatGPT’s potential for annotating COVID-19 data and the performance of fine-tuned GPT-3 models. Our semi-supervised BERT model with Knowledge Distillation showed improvements compared to a supervised baseline model, while zero-shot ChatGPT showed good potential as a tool for annotating crisis data. However, our study suggests that the cost of fine-tuning large and expensive GPT-3 models may not be worth for some tasks.

Abstract: Serious games are an effective tool for giving players a hands-on, immersive experience of crisis situations. To simplify the design of such games while ensuring their relevance, we propose a design method that is based on reference tasks. The feasibility of this approach is demonstrated by the improved design of the serious game “Disaster in my Backyard” that has been played during ISCRAM Summer school 2013. The design incorporates humanitarian logistics, search-and-rescue and coordination tasks. We also present the lessons learned from this instantiation of the game and give an outlook towards future research, such as the evaluation of tools for crisis response and management through the use of serious games and reference tasks.

Abstract: We describe a co-design method for emergency response scenario creation, to support the evaluation of new information technologies. The aim of our use of the method were to achieve scenarios that could be used in experiments or training sessions with professional emergency response personnel. We have analyzed how the method facilitated the design of scenarios (events, resource demands, communication between players), and the description of constraints in a resource management matrix. Our research indicates that the resource management matrix could be an important complement to function-centric analysis methods such as Functional Resonance Analysis Method (FRAM). We also illustrate how the interplay between play and situation description allowed us to simultaneously design and validate the scenarios with respect to playability versus resource demands. We discuss how the resource matrix can be used to adjust the validated scenarios after the design sessions. © 2012 ISCRAM.

Abstract: Increasing market volatility and disruptions imply risks for companies and governments and have become therefore focus topics. Adequate tools to identify, assess and manage future developments are key to survive in a turbulent environment. In our paper, we present the systematic development process of an innovative, web-based foresight platform, which is a joint research project funded by the German Federal Government and aims to improve the robustness in decision making by collaborative foresight. Its four interlinked applications have the purpose to enable their users a collaborative generation, discussion, evaluation and development of future-oriented knowledge. Thereby, a special emphasis is on the relevance and the timeliness of the provided information. Within the multi-stage requirement analysis of the tool platform we analyzed existing concepts in order to identify strengths and weaknesses and conducted brainstorming sessions and interviews with professionals of 130 companies and organizations to account for different backgrounds, perspectives and intentions. © 2012 ISCRAM.

Abstract: The work of first responders is marked by unpredictable situations, quick decisions and peak performance. Gathering all important information related to an emergency situation forms the basis for a meaningful and purposeful planning and action. For example during an accident scene the execution of complex individual orders is crucial. The many rescue facilities, rescue vehicles, and first responders needed lead to complex workflows. Real-life exercises are necessary to train controllers and first responders in handling these special situations, but are difficult and costly to organize. This paper gives a short overview of such an exercise and draws a rough practitioner-based vision of a potential simulation-based interactive system that could support exercise leaders and decision makers towards an effective utilization of real-life exercise data.

Abstract: In most nations, continued concern exists regarding the potential for acts of terrorism. Healthcare providers, specifically those in Emergency Medicine, will find themselves in the forefront of responding to such events. Training for Emergency Preparedness for all potential hazards is critical. Many approaches to training in individual for All Hazard Preparedness exist. The authors describe a multifaceted approach to training for All Hazards Preparedness and planning for terrorism. The approach includes classroom exercises designed specifically at understanding hazardous material threats, high fidelity patient simulation, strategic management simulation, and simulated care exercises in a non-hospital based emergency department facility. The authors believe that this multifaceted training will provide the broadest most potentially useful training and evaluation for emergency providers to ensure optimal response in times of any and all future terrorist attacks.

Abstract: This paper explores the design of training environments in which emergency response professionals can use information technologies to train for responding to unplanned-for situations. This approach – designing for improvisation – is fundamentally different than designing for plan execution. In this paper, we identify three dimensions of this difference and outline a set of research questions that are intended to lead to a better understanding of the role of improvisation in emergency response, as well as how it can be trained for and supported. Both questions are intertwined, since without a firm understanding of how improvisation occurs it is difficult to train for and support it. © Proceedings ISCRAM 2004.

Abstract: Societal threats such as global warming and terror attacks make crisis preparedness and crisis training a major priority in governments worldwide. Unfortunately, training is limited, partly due to complex and resource-demanding planning of traditional exercises. Several crisis training software have been developed as a complement. However, reports in research on their usage are rare, which indicates that the diffusion is limited. A potential explanation is that the systems fail to meet important needs in the organizations and/or sound information systems (IS) design principles. This paper describes the first phase of a design science research (DSR) project aiming at developing information systems for disaster management (ISDM) training, and accompanying training methods in local and regional governments. The purpose of this paper is to investigate perceived problems in current crisis training and identify opportunities for ISDM training in the application domain. Another purpose is to outline expected artifacts in the project.

Abstract: We report the findings of a crisis management survey on the role of IT in the crisis exercising, training and planning activities among companies in 6 different industries in two neighbouring European countries, Belgium and the Netherlands, having at least 50 employees. The survey was sent to 1450 Dutch and 1245 Belgian companies, 245 of which were returned, resulting in a response rate of 9%. The results of the survey show that the role of IT in these activities in both countries is very limited.

Abstract: Disasters often lead to other kinds of disasters, forming multi-hazards such as landslides, which may be caused by earthquakes, rainfalls, water erosion, among other reasons. Effective detection and management of multihazards cannot rely only on one information source. In this paper, we evaluate a landslide detection system LITMUS, which combines multiple physical sensors and social media to handle the inherent varied origins and composition of multi-hazards. LITMUS integrates near real-time data from USGS seismic network, NASA TRMM rainfall network, Twitter, YouTube, and Instagram. The landslide detection process consists of several stages of social media filtering and integration with physical sensor data, with a final ranking of relevance by integrated signal strength. Applying LITMUS to data collected in October 2013, we analyzed and filtered 34.5k tweets, 2.5k video descriptions and 1.6k image captions containing landslide keywords followed by integration with physical sources based on a Bayesian model strategy. It resulted in detection of all 11 landslides reported by USGS and 31 more landslides unreported by USGS. An illustrative example is provided to demonstrate how LITMUS' functionality can be used to determine landslides related to the recent Typhoon Haiyan.

Abstract: This paper reports research in progress into a study of information flow and teamwork in Incident Management Teams (IMTs) in Australia. The research project, funded by the Bushfire Co-operative Research Centre. The overall research design includes interviews with experienced personnel, observations of real-time incidents and training simulations and a national questionnaire of incident management practices. Data reported in this conference session will focus on a sample of observation data conducted in two training simulations of a wildfire incident. Observations were video recorded and key IMT members wore lapel microphones. Video data has been coded for use of artifacts (e.g., maps, status boards) and room movement. Audio data has been coded for by the quantity and quality of interactions within and between IMT functions. The presentation aims to contribute to an understanding of what enables and constrains effective teamwork and information flow within Incident Control Centers (ICCs) in Australia.