A Deep Learning Approach to Protecting Cultural Heritage Buildings Through IoT-Based Systems

Abstract

Cultural Heritage Buildings need to be preserved through interventions and actions that ensure accessibility and availability to present and future generations. The diffusion o f new technologies, including low-cost sensors and devices, has introduced many possibilities and strategies to monitor environments, including Historical and Cultural value buildings. Based on the Internet of Things (IoT) paradigm, modern devices and sensors can collect and manage helpful information to build a Digital Twin of the surrounding environment. In this scenario, reproducing a Digital Twin of Cultural Heritage Buildings could be crucial to monitoring, managing, and performing action aiming to protect them. One of the challenges in recent years is the automatic analysis of collected information. This paper introduces a novel approach to protecting Buildings using Heritage Building Information Modeling (HBIM), which leverages a sensor network and Deep Learning techniques to analyze sensor data. A case study related to the Archeological Park of Pompeii will be presented, where real-time collected data is managed and shared via a web-cloud-IoT platform. Then, collected data are analyzed through a Generative Adversarial Network (GAN) to prevent future issues related to Cultural Heritage Buildings, particularly humidity inside structures, which is crucial for ancient building preservation.