Adaptive Multi-agent-based Alert System for Diseases’ Detection

Abstract

Monitoring the epidemiological situation of public health remains a challenge, given the exponential growth of health data. Indeed, these latter come from various sources such as, health professionals, biologists, experts in health organizations, etc. In this context, reconciling the search for the greatest amount of appropriate signals and the way of treating them, is the ultimate challenge. Developing alert systems in the health field is yet a necessity, but what counts, even more, is to propose a powerful and effective solution. To that purpose, we propose a multi-agent-based system that alerts the users when bizarre situations are detected. At the heart of the system, an adaptive agent is proposed which uses the neural network deep learning algorithm. To validate our proposal, we tested both its effectiveness and its efficiency and compared the obtained results against the Q-learning algorithm. Obtained results have proved the adequacy of the chosen algorithm especially in the context of health data.