Rustenberg, K., Radianti, J., & Gjøsæter, T. (2023). Exploring Demons for the Establishment of Team Situational Awareness. In Jaziar Radianti, Ioannis Dokas, Nicolas Lalone, & Deepak Khazanchi (Eds.), Proceedings of the 20th International ISCRAM Conference (pp. 636–648). Omaha, USA: University of Nebraska at Omaha.
Abstract: Individual situational awareness (SA) is crucial for building team SA, which is necessary for achieving a shared understanding of a situation, making informed decisions, and taking appropriate actions. This article examines the communication barriers that emerge when transitioning from individual to team SA in emergency management scenarios. We observed two emergency exercises on “ongoing life-threatening violence” and dam failure causing hospital congestion. The study was complemented with interviews with participants of these exercises, aiming at identifying barriers called SA-demons in the team setting. We discovered barriers that hinder the establishment of team SA, including a vicious cycle of mistrust, a fragmented information trap, a false feeling of mastery trap, and a decaying memory trap. These barriers can stem from individual, organizational, or technological factors. To complement existing SA theories, we applied the Cynefin framework and found that standard operating procedures can be potential barriers when transitioning into chaotic or complex domains.
|
|
Tasneem, F., Chakraborty, S., & Chy, A. N. (2023). An Early Synthesis of Deep Neural Networks to Identify Multimodal Informative Disaster Tweets. In Jaziar Radianti, Ioannis Dokas, Nicolas Lalone, & Deepak Khazanchi (Eds.), Proceedings of the 20th International ISCRAM Conference (pp. 428–438). Omaha, USA: University of Nebraska at Omaha.
Abstract: Twitter is always worthwhile in facilitating communication during disasters. It helps in raising situational awareness and undertaking disaster control actions as quickly as possible to alleviate the miseries. But the noisy essence of Twitter causes difficulty in distinguishing relevant information from the heterogeneous contents. Therefore, extracting informative tweets is a substantial task to help in crisis intervention. Analyzing only the text or image content of the tweet often misses necessary insights which might be helpful during disasters. In this paper, we propose a multimodal framework to address the challenges of identifying informative crisis-related tweets containing both texts and images. Our presented approach incorporates an early fusion strategy of BERT-LSTM and ResNet50 networks which effectively learns from the joint representation of texts and images. The experiments and evaluation on the benchmark CrisisMMD dataset show that our fusion method surpasses the baseline by 7% and substantiates its potency over the unimodal systems.
|
|
Eulalia Gomez Martin, Josune Hernantes, Leire Labaka, & Marcos Borges. (2022). Building upon the Existing Knowledge: Updating and Improving the Smart Mature Resilience Model. In Rob Grace, & Hossein Baharmand (Eds.), ISCRAM 2022 Conference Proceedings – 19th International Conference on Information Systems for Crisis Response and Management (pp. 437–459). Tarbes, France.
Abstract: In recent years the concept of urban resilience has acquired great relevance within urban planning. The complexity of urban systems and the wide scope of the resilience concept require tools to facilitate the integration of the concept in urban development. Numerous studies, tools, and theoretical frameworks have been developed to support the resilient transformation of cities. However, these initiatives are usually not holistically integrated and limit incorporating the changes and advances in the resilience concept. This article highlights the importance of shifting from a continuously-building-new approach to building on an existing knowledge approach. This study has updated and improved the maturity model developed within the Horizon 2020 project Smart Mature Resilience. A bibliometric analysis was carried out to study the developments in resilience over the past four years and to integrate the relevant advances in the area into a new version of the Smart Mature Resilience Maturity Model (SMR MM).
|
|
Thomas Papadimos, Nick Pantelidis, Stelios Andreadis, Aristeidis Bozas, Ilias Gialampoukidis, Stefanos Vrochidis, et al. (2022). Real-time Alert Framework for Fire Incidents Using Multimodal Event Detection on Social Media Streams. In Rob Grace, & Hossein Baharmand (Eds.), ISCRAM 2022 Conference Proceedings – 19th International Conference on Information Systems for Crisis Response and Management (pp. 623–635). Tarbes, France.
Abstract: The frequency of wildfires is growing day by day due to vastly climate changes. Forest fires can have a severe impact on human lives and the environment, which can be minimised if the population has early and accurate warning mechanisms. To date, social media are able to contribute to early warning with the additional, crowd-sourced information they can provide to the emergency response workers during a crisis event. Nevertheless, the detection of real-world fire incidents using social media data, while filtering out the unavoidable noise, remains a challenging task. In this paper, we present an alert framework for the real-time detection of fire events and we propose a novel multimodal event detection model, which fuses both probabilistic and graph methodologies and is evaluated on the largest fires in Spain during 2019.
|
|
Stella Polikarpus, Tobias Ley, & Katrin Poom-Valickis. (2021). Collaborative Authoring of Virtual Simulation Scenarios for Assessing Situational Awareness. 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. 229–237). Blacksburg, VA (USA): Virginia Tech.
Abstract: Situational awareness (SA), the ability to perceive, comprehend and predict situation around you and it is a key in attending any incident as critical foundation for successful decision-making. Because incidents are solitary events, development and assessment of SA presents a significant challenge. In this article we analyze the authoring process of twenty-two scenarios implemented in the XVR on-scene virtual simulation software used to assess rescue incident commanders' (ICs) SA. To allow the scenarios to be used by different assessors, the Collaborative Authoring Process Model for Virtual Simulation Scenarios (CAPM) was developed. In Estonia, 473 assessments were recorded in Effective Command database and analysed by all three levels of SA as recommended by Endsley (2000). Introduction of CAPM resulted in scenarios being re-used by different assessors for authentic SA measuring. In the last sections of this article, we introduce our suggestions to improve virtual scenario design and SA research.
|
|