Predictive analytics in facilities management: A pilot study for predicting environmental comfort using wireless sensors

Abstract

Purpose

Advancements in wireless sensor technology and building modelling techniques have enabled facilities managers to understand the environmental performance of the workplace in more depth than ever before. However, it is unclear to what extent this data can be used to predict subjective environmental comfort. This study aims to pilot test a methodological framework for integrating real-time environmental data with subjective ratings of environmental comfort.

Design/methodology/approach

An open-plan office was fitted with environmental sensors to measure key indoor environmental quality parameters (carbon dioxide, temperature, humidity, illumination and sound pressure level). Additionally, building modelling techniques were used to calculate two spatial metrics (“workspace integration” and workspace density) for each workspace within the study area. In total, 15 employees were repeatedly sampled across an 11-day study period, providing 78 momentary assessments of environmental comfort. Multilevel models were used to explore the extent to which the objective environmental data predicted subjective environmental comfort.

Findings

Higher carbon dioxide levels were associated with more negative ratings of air quality, higher “workspace integration” was associated with higher levels of distractions, and higher workspace density was associated with lower levels of social interactions.

Originality/value

To our knowledge, this is the first field study to directly explore the relationship between physical environment data collected using wireless sensors and subjective ratings of environmental comfort. The study provides proof-of-concept for a methodological framework for the integration of building analytics and human analytics.

Citation

Roskams, M. and Haynes, B. (2019), "Predictive analytics in facilities management: A pilot study for predicting environmental comfort using wireless sensors", Journal of Facilities Management, Vol. 17 No. 4, pp. 356-370. https://doi.org/10.1108/JFM-03-2019-0008