Quality-aware human-driven information fusion model

Abstract

Situational Awareness (SAW) is a widespread concept in areas that require critical decision-making and refers to the level of consciousness that an individual or team has about a situation. A poor SAW can induce humans to failures in the decision-making process, leading to losses of lives and property damage. Data fusion processes present opportunities to enrich the knowledge about situations by integrating heterogeneous and synergistic data from different sources and transforming them into more meaningful subsidies for decision-making. However, a problem arises when information is subject to problems concerning its quality, especially when humans are the main sources of data (HUMINT). Motivated by the informational demand from the emergency management domain and by the limitations and challenges of the state of the art, this work proposes and describes a new information fusion model, called Quantify (Quality-aware Human-Driven Information Fusion Model), whose main contribution is the exhaustive use of the quality information management throughout the fusion process to parameterize and to guide the work of humans and systems. To validate the model, an emergency situation assessment system prototype was developed, called ESAS (Emergency Situation Assessment Systems). Then, experts from the Sao Paulo State Police (PMESP) tested the prototypes and the system was evaluated using SART (Situation Awareness Rating Technique), which showed higher rates of SAW using the Quantify model, compared to the model from the state-of-the-art, especially in questions relating to the components of resource supply and situational understanding.