Borglund, E., A.M., & Granholm, M. (2023). Challenges in work procedures in distributed crisis management. In Jaziar Radianti, Ioannis Dokas, Nicolas Lalone, & Deepak Khazanchi (Eds.), Proceedings of the 20th International ISCRAM Conference (pp. 732–737). Omaha, USA: University of Nebraska at Omaha.
Abstract: This is a work in progress paper on work and IT usage in distributed crisis management. The data presented in this paper has been collected at a one-day tabletop exercise with four Swedish municipalities. Four members of the four municipalities’ crisis organizations were invited to the exercise, which was designed as one scenario divided into two cases. At the start of each case of the exercise, each municipality was split into two separate rooms, to simulate a distributed crisis management. During the first case they could communicate using phone, TETRA radio, and the Internet. During case two in the scenario, there was no Internet connection. The study indicates that all the municipalities managed to organize and solve the given tasks using primarily voice communication, in case one using phone or, e.g., Teams, and in case two using TETRA radio. Information sharing using IT was non-existing.
|
|
Lindhagen, A., Björnqvist, A., & Berggren, P. (2023). Supporting Instructors in Conducting Exercises. In Jaziar Radianti, Ioannis Dokas, Nicolas Lalone, & Deepak Khazanchi (Eds.), Proceedings of the 20th International ISCRAM Conference (pp. 721–731). Omaha, USA: University of Nebraska at Omaha.
Abstract: Planning, designing, facilitating, and evaluating are central activities for instructors when conducting exercises. When conducting these activities, instructors usually rely on past experiences since structured educations or guides for instructors do not exist. It is therefore evident that there is a need for such educations or guides. In this study, the contents of a guide for instructors are proposed. The contents are based on seven semi-structured interviews with novel and experienced instructors, where they were asked to map their procedures for conducting exercises through a journey map. The interviews resulted in material which was transcribed and analysed using a thematic analysis. The thematic analysis emphasized five themes to consider when acting as an instructor, namely roles, realism, defining purpose and goals, learning, and planning and acting. The results from the interviews, combined with past literature, resulted in proposed contents for an instructor’s guide which is currently being developed.
|
|
Pettersson, M. N., Axelsson, J., Svenson, P., & Johansson, A. (2023). Towards a Risk Analysis Method for Systems of Systems: A Case Study on Wildfire Rescue Operations. In Jaziar Radianti, Ioannis Dokas, Nicolas Lalone, & Deepak Khazanchi (Eds.), Proceedings of the 20th International ISCRAM Conference (pp. 530–545). Omaha, USA: University of Nebraska at Omaha.
Abstract: Crisis management (CM) is facing new challenges due to the increasing complexity of contemporary society. To mitigate a crisis, it is often necessary for a collection of independent systems, people, and organizations to cooperate. These collaborating entities constitute an interconnected socio-technical system of systems (SoS). An important question is how a CM SoS should be constructed to minimize the risk of failure and accurately handle a crisis. SoS pose new challenges in analysing risk during interactions. This paper investigates whether the risk analysis method STAMP (System-Theoretic Accident Model and Processes) is suitable for SoS, using a forest fire rescue operation case study. Results show characteristics of various risk sources and identify some SoS characteristics, such as dynamic structure and latent risks, that are not sufficiently handled in STAMP. The study further contributes to the body of knowledge by presenting potential directions for research on SoS risk assessment methods.
|
|
Pereira, J., Fidalgo, R., Lotufo, R., & Nogueira, R. (2023). Crisis Event Social Media Summarization with GPT-3 and Neural Reranking. In Jaziar Radianti, Ioannis Dokas, Nicolas Lalone, & Deepak Khazanchi (Eds.), Proceedings of the 20th International ISCRAM Conference (pp. 371–384). Omaha, USA: University of Nebraska at Omaha.
Abstract: Managing emergency events, such as natural disasters, requires management teams to have an up-to-date view of what is happening throughout the event. In this paper, we demonstrate how a method using a state-of-the-art open-sourced search engine and a large language model can generate accurate and comprehensive summaries by retrieving information from social media and online news sources. We evaluated our method on the TREC CrisisFACTS challenge dataset using automatic summarization metrics (e.g., Rouge-2 and BERTScore) and the manual evaluation performed by the challenge organizers. Our approach is the best in comprehensiveness despite presenting a high redundancy ratio in the generated summaries. In addition, since all pipeline components are few-shot, there is no need to collect training data, allowing us to deploy the system rapidly. Code is available at https://github.com/neuralmind-ai/visconde-crisis-summarization.
|
|
Long, Z., McCreadiem, R., & Imran, M. (2023). CrisisViT: A Robust Vision Transformer for Crisis Image Classification. In Jaziar Radianti, Ioannis Dokas, Nicolas Lalone, & Deepak Khazanchi (Eds.), Proceedings of the 20th International ISCRAM Conference (pp. 309–319). Omaha, USA: University of Nebraska at Omaha.
Abstract: In times of emergency, crisis response agencies need to quickly and accurately assess the situation on the ground in order to deploy relevant services and resources. However, authorities often have to make decisions based on limited information, as data on affected regions can be scarce until local response services can provide first-hand reports. Fortunately, the widespread availability of smartphones with high-quality cameras has made citizen journalism through social media a valuable source of information for crisis responders. However, analyzing the large volume of images posted by citizens requires more time and effort than is typically available. To address this issue, this paper proposes the use of state-of-the-art deep neural models for automatic image classification/tagging, specifically by adapting transformer-based architectures for crisis image classification (CrisisViT). We leverage the new Incidents1M crisis image dataset to develop a range of new transformer-based image classification models. Through experimentation over the standard Crisis image benchmark dataset, we demonstrate that the CrisisViT models significantly outperform previous approaches in emergency type, image relevance, humanitarian category, and damage severity classification. Additionally, we show that the new Incidents1M dataset can further augment the CrisisViT models resulting in an additional 1.25% absolute accuracy gain.
|
|