An agent-Based self-organizing model for large-scale biosurveillance systems using mobile edge computing

Abstract

Early detection of biological attacks is vital for alleviating their effects and protecting human lives. Current biosurveillance systems rely on the complex processing of large volumes of data available from multiple sources such as hospitals, clinics and medical laboratories. As these systems are intended to monitor large-scale environments, they require intensive computational resources to analyze the monitored data. In addition, they lack the ability to detect potential threats in a timely manner. In this paper, we present an agent-based self-organizing model that utilizes the emerging Mobile Edge Computing concept for rapid biological threat detection. The model is comprised of a hierarchy of specialized agents. At the lower level, monitored humans are equipped with wearable sensors and personal agents that continuously capture and process the human’s vital signs. The processed data is transmitted to higher-level agents for further processing and to detect potential threats. To monitor a large-scale environment efficiently, the hierarchy of agents continuously interact with each other to dynamically re-organize the monitored environment into regions that aggregate focused information. The experimental results show that the proposed model is able to monitor large-scale environments efficiently and to accurately detect biological threats.