Digital twin-enabled built environment sensing and monitoring through semantic enrichment of BIM with SensorML

Effective environmental condition monitoring provides constant surveillance of the built environment and reveals deteriorations that could impact the daily operation of facilities, especially amid COVID situations. However, the current Industry Foundation Classes (IFC) data schema for Building Information Modelling (BIM) provided limited support to represent full semantics related to environmental sensing and monitoring. How to semantically enrich the IFC schema with enhanced data description capability for informed decision-making in smart facilities management (FM) amid COVID situations remains an open question. This paper develops a semi-automatic extension and integration of IFC data schema with Sensor Model Language (SensorML) specification in order to support automated built environment sensing and monitoring. Referring to SensorML, an extended IFC model view definition for a comprehensive description of required sensor metadata and sensing entities is presented. An Internet of Things (IoT) sensor network is then established to realise continuous data collection from a variety of wireless sensing devices. The spatial-temporal data captured by the IoT sensor network are extracted by a regular expression-based data distillation algorithm and integrated with the digital twin, in which spatial interpolation algorithms further analyse, compute, and visualise the state of the environment. The proposed method is demonstrated via an experimental study which supports real-time environmental monitoring and delivers more actionable insights to facility managers to sustain the daily operation of buildings. This study contributes new methods and models to semantically enrich the digital twin from the data perspective for environmental condition monitoring during the pandemic time which fosters the development of holistic building facility management.

Supervised learning-based assessment of office layout satisfaction in academic buildings

Employee satisfaction significantly affects health, well-being and productivity, and office layout plays a dominant role in office psychological satisfaction. However, existing studies have not yet proposed a quantitative evaluation method for office layout satisfaction to assist design decisions. This study conducts a post-occupancy evaluation (POE) process of office layout satisfaction from 1,317 staff members at 3 universities in the Yangtze River Delta, China. The proposed office layout feature network supports the questionnaire design and environmental measurement. Based on the survey data, multiple resampling methods are considered to face the imbalanced dataset problem, and feature selection integrates statistical analysis methods and machine learning algorithms. Nine supervised learning algorithms are tested for office layout satisfaction prediction, and the final predictive model is established based on the random forest algorithm. The predictive model explanation is further integrated with original data analysis to extract the quantified impacts of various building characteristics. The workstation adjustment under the background of COVID-19 in an actual staff office is chosen to be an application scenario of the predictive model. The results show that the workstation distance, room depth and room width-depth ratio are dominant in the evaluation of office layout satisfaction. The proposed predictive model achieves 64.5% accuracy, and the prediction results are interpretable, which promotes its application in office design practice. The data processing methods in this study respond to the common data problems in the POE based opinion collection process. The extracted influence mechanisms of building characteristics can directly support user-centered office design.