A comprehensive literature review of personalised indoor comfort: artificial intelligence approaches and applications

Sun, Shiyi, Li, Haijiang ORCID: https://orcid.org/0000-0001-6326-8133 and Khudhair, Ali ORCID: https://orcid.org/0000-0002-5062-7448 2025. A comprehensive literature review of personalised indoor comfort: artificial intelligence approaches and applications. Presented at: International Workshop on Intelligent Computing in Engineering, The 32nd EG-ICE International Workshop on Intelligent Computing in Engineering, Glasgow, UK, 1-4 July 2025.

Preview

PDF - Presentation Download (972kB) | Preview

Abstract

With the rising demand for human-centric and energy-efficient indoor environments, Artificial Intelligence (AI) has emerged as a transformative tool for enhancing personalised comfort in buildings. This review synthesises findings from 90 peer-reviewed studies published between 2008 and 2024, focusing on AI applications across four primary comfort dimensions: Thermal Comfort (TC), Indoor Air Quality (IAQ), Acoustic Environment (AE), and Visual Comfort (VC). Results reveal a significant research disparity, with 97.75% of studies focusing solely on TC, leaving IAQ, AE, and VC untapped. While AI techniques, such as Artificial Neural Networks (ANNs), Support Vector Machines (SVMs), and Random Forests (RF), demonstrate high predictive accuracy for TC, integrated, multidimensional comfort models remain scarce. Key gaps include cross-domain modelling, context-specific adaptation, integration of physiological and psychological indicators, and privacy-aware AI deployment. This study proposes a multidimensional framework that fuses environmental and personal factors to support holistic comfort modelling. It presents strategic insights for developing inclusive, adaptive, and privacy-conscious AI-driven comfort systems, guiding future research and practical implementation in the built environment.

Item Type:	Conference or Workshop Item (Speech)
Status:	Unpublished
Schools:	Schools > Engineering
Last Modified:	26 Jun 2025 16:00
URI:	https://orca.cardiff.ac.uk/id/eprint/178384

Actions (repository staff only)

Edit Item