<p>Simulation modeling has proven beneficial in gathering insights that may aid safety policy considerations for schools, offices, and outdoor events. This is especially true when conducting a drill that is not practical or possible, such as active shooter response. However, we can improve the current modeling practices with high-fidelity simulation logic reflecting a victim's well-being. Currently, victims are modeled either as “killed,” or they continue their normal movement. The binary approach is suitable for many simulations developed to understand course trends in an event space but does not allow for more fine-tuned insights that may be beneficial when developing a safety and response protocol for a specific facility or event. Additional victim characteristics, such as tracking the location of a victim's wound and the rate of physiological decline, may be added into a model that will improve the realism and lead to an improved response protocol. The increased fidelity will be helpful when simulating and assessing the effects of volunteer response, critical care transport for medical intervention, and other first-responder interventions.</p> <p>While some think it is not possible or necessary to simulate how fast gunshot victims would lose blood, we show that a high-fidelity simulation is possible. The main counterargument is that there is no sufficient data, and also it will be challenging to implement this process as it is occurring. However, we found enough data or were able to extrapolate the missing pieces and develop a consistent and realistic blood loss model. In addition, the state of current simulation packages, such as AnyLogic, has advanced to the point where we can model a liquid system dynamic within an agent-based model. Furthermore, there is an acute benefit to conducting this type of research as it can help us develop better response policies, which result in more saved lives.</p> <p>The research aims to improve emergency-response simulation fidelity by developing a model that simulates gunshot wounds and the subsequent blood loss while accounting for a victim's age, weight, gender, and the affected area. The model also accounts for the body's compensatory response and medical interventions, such as tourniquet application, wound packing, and direct pressure. The work presents an analytical model and its implementation using agent-based modeling in AnyLogic. This AnyLogic module can be inserted into active shooter simulations that easily integrate with the existing logic. This integration happens through a high-level application programming interface (API) exposed to the user. The API allows for automatic infliction of injury and mitigation. The extensive literature review and case studies provide a sound foundation for creating the model. AnyLogic was chosen due to its common usage and versatility with other systems and computer programming languages.</p>

No description available.

<p>The dataset is a compiliation of firearm related incidents on US k-12 schools from 1999-2023. The statistical analysis results are used in a systems dynamics simulation model to measure risk response effectiveness and evaluate secondary risks.</p>

This dissertation investigates the value of deep reinforcement learning (DRL) within an agent-based model (ABM) of a large open-air venue. The intent is to reduce civilian casualties in an active shooting incident (ASI). There has been a steady increase of ASIs in the United States of America for over 20 years, and some of the most casualty-producing events have been in open spaces and open-air venues. More research should be conducted within the field to help discover policies that can mitigate the threat of a shooter in extremis. This study uses the concept of dynamic signage, controlled by a DRL policy, to guide civilians away from the threat and toward a safe exit in the modeled environment. It was found that a well-trained DRL policy can significantly reduce civilian casualties as compared to baseline scenarios. Further, the DRL policy can assist decision makers in determining how many signs to use in an environment and where to place them. Finally, research using DRL in the ASI space can yield systems and policies that will help reduce the impact of active shooters during an incident.