Digital twin for healthy indoor environment: A vision for the post-pandemic era

Indoor environment has significant impacts on human health as people spend 90% of their time indoors. The COVID-19 pandemic and the increased public health awareness have further elevated the urgency for cultivating and maintaining a healthy indoor environment. The advancement in emerging digital twin technologies including building information modeling (BIM), Internet of Things (IoT), data analytics, and smart control have led to new opportunities for building design and operation. Despite the numerous studies on developing methods for creating digital twins and enabling new functionalities and services in smart building management, very few have focused on the health of indoor environment. There is a critical need for understanding and envisaging how digital twin paradigms can be geared towards healthy indoor environment. Therefore, this study reviews the techniques for developing digital twins and discusses how the techniques can be customized to contribute to public health. Specifically, the current applications of BIM, IoT sensing, data analytics, and smart building control technologies for building digital twins are reviewed, and the knowledge gaps and limitations are discussed to guide future research for improving environmental and occupant health. Moreover, this paper elaborates a vision for future research on integrated digital twins for a healthy indoor environment with special considerations of the above four emerging techniques and issues. This review contributes to the body of knowledge by advocating for the consideration of health in digital twin modeling and smart building services and presenting the research roadmap for digital twin-enabled healthy indoor environment.

Investigating the determinants of performance of artificial intelligence adoption in hospitality industry during COVID-19

PurposeDrawing on the technology-organization-environment (TOE) framework, this study aims to investigate determinants of performance of artificial intelligence (AI) adoption in hospitality industry during COVID-19 and identifies the relative importance of each determinant. Design/methodology/approachA two-stage approach that integrates partial least squares structural equation modeling (PLS-SEM) with artificial neural network (ANN) is used to analyze survey data from 290 managers in the hospitality industry. FindingsThe empirical results reveal that perceived AI risk, management support, innovativeness, competitive pressure and regulatory support significantly influence the performance of AI adoption. Additionally, the ANN results show that competitive pressure and management support are two of the strongest determinants. Practical implicationsThis research offers guidelines for hospitality managers to enhance the performance of AI adoption and presents policy-making insights to promote and support organizations to benefit from the adoption of AI technology. Originality/valueThis study conceptualizes the performance of AI adoption from both process and firm levels and examines its determinants based on the TOE framework. By adopting an innovative approach combining PLS-SEM and ANN, the authors not only identify the essential performance determinants of AI adoption but also determine their relative importance.