Designing Decision Support Systems for Emergency Response: Challenges and Opportunities

Abstract

Designing effective emergency response management (ERM) systems to respond to incidents such as road accidents is a major problem faced by communities. In addition to responding to frequent incidents each day (about 240 million emergency medical services calls and over 5 million road accidents in the US each year), these systems also support response during natural hazards. Recently, there has been a consistent interest in building decision support and optimization tools that can help emergency responders provide more efficient and effective response. This includes a number of principled subsystems that implement early incident detection, incident likelihood forecasting and strategic resource allocation and dispatch policies. In this paper, we highlight the key challenges and provide an overview of the approach developed by our team in collaboration with our community partners.

Generative Anomaly Detection for Time Series Datasets

“…Our conversations with local transportation agencies revealed that this monitoring is largely performed manually, an infeasible strategy in the long run. One approach to enable transportation agencies to utilize an extensive array of sensors is to detect potentially anomalous patterns in real-time using the data generated by the sensors; then, human experts (or potentially decision-theoretic approaches [2]) can narrow their focus on the anomalies and take necessary operational actions. Similarly, in large data centers, server machine KPIs, such as CPU, memory, TCP, UDP metrics, are periodically collected as multi-variate time series by some profilers.…”

How Personality and Communication Patterns Affect Online ad-hoc Teams Under Pressure

“…Situations that require working together, fast, and efficiently under pressure are on the rise, especially in an increasingly fragile global ecosystem (Schneider, 2011;Kretzschmar et al, 2022). From handling widespread geopolitical conflicts (Friede, 2022) to mitigating environmental disasters (Gay-Antaki, 2021), several organizations are investing in crowdsourcing intervention to aid large-scale mobilization of resources including emergency shelters and disaster-event detection (Pettet et al, 2022;Stephens and Robertson, 2022;Zhang, 2022). Likewise, virtual teamwork enacted in high-urgency, high-stress tasks is on demand.…”