We are thrilled to announce a new achievement accomplished by University of Patras, within the context of TwinAir project!

The article “A text analytic framework for gaining insights on the integration of digital twins and machine learning for optimizing indoor building environmental performance” has been published in the “Developments in the Built Environment” Journal.

The authors of the article are: Stylianos Karatzas, Grigorios Papageorgiou, Vasiliki Lazari,Sotirios Bersimis, Andreas Fousteris, Polychronis Economou, Athanasios Chassiakos and its respective DOI is the following:  https://doi.org/10.1016/j.dibe.2024.100386

The abstract and the keywords of the publication can be found below.


Recent technological advancements in distributed sensing, pervasive computing, context-awareness, machine learning and Digital Twins (DTs) allow the built environment to cope with upcoming challenges in a better way than before and achieve comfort and well-being in buildings. This paper takes a unique approach by not conducting a systematic and exhaustive review, that would require enormous effort to uncover intricate interdependencies among various subtopics. Instead, it proposes a framework leveraging Artificial Intelligence and Machine Learning (AI/ML) techniques to extract valuable insights from the existing literature. Adopting the Digital Twin high-level architecture as its foundation, the paper introduces a clustering approach to scrutinize Indoor Environmental Quality, Energy Efficiency, and Occupant Comfort—key facets influencing indoor building performance. This innovative methodology aims to provide a more nuanced understanding of the relationships within these critical aspects by harnessing the capabilities of AI/ML techniques and the conceptual framework of Digital Twin architecture.

Keywords: Indoor environmental quality; Comfort; Digital twins; Artificial intelligence; Machine learning

You can reach the full article following this link: https://www.sciencedirect.com/science/article/pii/S266616592400067X?via%3Dihub