skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Occupancy prediction through machine learning and data fusion of environmental sensing and Wi-Fi sensing in buildings

Abstract

Occupancy information is crucial to building facility design, operation, and energy efficiency. Many studies propose the use of environmental sensors (such as carbon dioxide, air temperature, and relative humidity sensors) and radio-frequency sensors (Wi-Fi networks) to monitor, assess, and predict occupancy information for buildings. As many methods have been developed and a variety of sensory data sources are available, establishing a proper selection of model and data source is critical to the successful implementation of occupancy prediction systems. This study compared three popular machine learning algorithms, including k-nearest neighbors (kNN), support vector machine (SVM), and artificial neural network (ANN), combined with three data sources, including environmental data, Wi-Fi data, and fused data, to optimize the occupancy models’ performance in various scenarios. Three error measurement metrics, the mean average error (MAE), mean average percentage error (MAPE), and root mean squared error (RMSE), have been employed to compare the models’ accuracies. Examined with an on-site experiment, the results suggest that the ANN-based model with fused data has the best performance, while the SVM model is more suitable with Wi-Fi data. The results also indicate that, comparing with independent data sources, the fused data set does not necessarily improve model accuracy but showsmore » a better robustness for occupancy prediction.« less

Authors:
 [1]; ORCiD logo [2];  [3]
  1. City University of Hong Kong, Kowloon (Hong Kong). Dept. of Architecture and Civil Engineering; Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States). Building Technology and Urban Systems Division
  2. City University of Hong Kong, Kowloon (Hong Kong). Dept. of Architecture and Civil Engineering, and Architecture and Civil Engineering Research Centre
  3. Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States). Building Technology and Urban Systems Division
Publication Date:
Research Org.:
Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States)
Sponsoring Org.:
USDOE Office of Energy Efficiency and Renewable Energy (EERE), Building Technologies Office (EE-5B)
OSTI Identifier:
1506367
Grant/Contract Number:  
AC02-05CH11231
Resource Type:
Journal Article: Accepted Manuscript
Journal Name:
Automation in Construction
Additional Journal Information:
Journal Volume: 94; Journal Issue: C; Journal ID: ISSN 0926-5805
Country of Publication:
United States
Language:
English
Subject:
32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATION

Citation Formats

Wang, Wei, Chen, Jiayu, and Hong, Tianzhen. Occupancy prediction through machine learning and data fusion of environmental sensing and Wi-Fi sensing in buildings. United States: N. p., 2018. Web. doi:10.1016/j.autcon.2018.07.007.
Wang, Wei, Chen, Jiayu, & Hong, Tianzhen. Occupancy prediction through machine learning and data fusion of environmental sensing and Wi-Fi sensing in buildings. United States. doi:10.1016/j.autcon.2018.07.007.
Wang, Wei, Chen, Jiayu, and Hong, Tianzhen. Sat . "Occupancy prediction through machine learning and data fusion of environmental sensing and Wi-Fi sensing in buildings". United States. doi:10.1016/j.autcon.2018.07.007.
@article{osti_1506367,
title = {Occupancy prediction through machine learning and data fusion of environmental sensing and Wi-Fi sensing in buildings},
author = {Wang, Wei and Chen, Jiayu and Hong, Tianzhen},
abstractNote = {Occupancy information is crucial to building facility design, operation, and energy efficiency. Many studies propose the use of environmental sensors (such as carbon dioxide, air temperature, and relative humidity sensors) and radio-frequency sensors (Wi-Fi networks) to monitor, assess, and predict occupancy information for buildings. As many methods have been developed and a variety of sensory data sources are available, establishing a proper selection of model and data source is critical to the successful implementation of occupancy prediction systems. This study compared three popular machine learning algorithms, including k-nearest neighbors (kNN), support vector machine (SVM), and artificial neural network (ANN), combined with three data sources, including environmental data, Wi-Fi data, and fused data, to optimize the occupancy models’ performance in various scenarios. Three error measurement metrics, the mean average error (MAE), mean average percentage error (MAPE), and root mean squared error (RMSE), have been employed to compare the models’ accuracies. Examined with an on-site experiment, the results suggest that the ANN-based model with fused data has the best performance, while the SVM model is more suitable with Wi-Fi data. The results also indicate that, comparing with independent data sources, the fused data set does not necessarily improve model accuracy but shows a better robustness for occupancy prediction.},
doi = {10.1016/j.autcon.2018.07.007},
journal = {Automation in Construction},
issn = {0926-5805},
number = C,
volume = 94,
place = {United States},
year = {2018},
month = {7}
}

Journal Article:
Free Publicly Available Full Text
This content will become publicly available on July 14, 2019
Publisher's Version of Record

Save / Share: