Pupil size and gender-driven occupant's productivity predictive model for diverse indoor lighting conditions in the office environment. (December 2022)

• Record Type: Journal Article
• Authors: Kim, Taegeun; Lim, Seheon; Yoon, Sung-Guk; Yeom, Dongwoo (Jason)
• Is Part Of: Building and environment. Volume 226(2022)
• Publication Date: 2022-12
• Subjects: Lighting environment -- Productivity -- Cognitive performance -- Predictive model -- Physiological signal; Buildings -- Environmental engineering -- Periodicals; Building -- Research -- Periodicals; Constructions -- Technique de l'environnement -- Périodiques; Electronic journals; 696
• DOI: 10.1016/j.buildenv.2022.109673
• Languages: English
• ISSNs: 0360-1323

Abstract

Abstract: The purpose of this study is to investigate the relationship between indoor lighting environment factors, occupant's physiological signals, and the occupants' productivity and to develop a productivity predictive model by using the occupants' physiological signals. The physical scope of this study is an indoor office environment, and this study adapted the occupant's pupil size as a physiological signal. To achieve the research goal, a series of experiments were conducted to analyze the occupants' pupil size and their productivity in diverse lighting conditions. The operation span task (OSPAN) was used in this study to measure cognitive performance as a means to evaluate the participant's productivity. To develop the occupants' productivity predictive model, the Light gradient boosting model (LightGBM) classifier was used. The significance of each input factor that affects accuracy was applied, and the change of LightGBM parameters such as depth and leaf were compared to develop an optimum predictive model. The result provides new insights that the occupant's pupil size is correlated significantly with their productivity in different indoor lighting conditions, and pupil size and gender can be used as an effective factor to estimate the occupant's productivity in various lighting environments with 94.7% accuracy, depending on the LGBM factor. The new findings of this study contribute to establishing personalized lighting management systems with the help of modern technologies, such as building IoT. Highlights: Pupil size are correlated with the cognitive performance in certain lighting conditions. Certain cognitive performance can be improved in specific lighting environment. The occupant's productivity can be predicted via human pupil size and gender. A productivity predictive model was determined with 94.7% accuracy. High lighting intensity and high CCT has a positive impact on the productivity.