Integrated Sensor Data Processing for Occupancy Detection in Residential Buildings
Chenli Wang, Jun Jiang, Thomas Roth, Cuong Nguyen, Yuhong Liu, Hohyun Lee
Based on the data from U.S. Energy Information Administration (EIA), the total annual energy consumed by buildings in the United States has increased by 325% over the past 70 years. Many commercial buildings utilize a building management system (BMS) and occupancy sensors to better control heating, ventilation, and air conditioning (HVAC) systems. However, the complex and costly installation process of occupancy sensors prolongs the return on investment for the residential sector. This paper presents a cost effective approach to occupancy detection utilizing a two-layer detection scheme based on data obtained from multiple non-intrusive sensors (temperature and motion). The sensor data were consumed by multiple white-box detection models (lower layer) for recognizing a set of human activities (door handle touch, water usage, and motion near the door area). As non-intrusive sensors, such as temperature, may lead to less accurate occupancy information, machine learning based data fusion scheme (upper layer) is utilized to holistically validates any individual sensor, the proposed methodology enhances the validity and reliability of occupancy detection. The event data was used to train and test four machine learning models (Random Forest, Decision Tree, K-Nearest Neighbor, and Support Vector Machine). The proposed occupancy detection system was installed in a 62 m2 living lab. Four temperature sensors and one motion sensor were used to collect the environmental information for 54 days. The validity of the proposed detection system was verified by the accuracy and the F1-score of each model. In all machine learning models, the two-layer detection system showed significantly improvements to the accuracy and the F1-score over the current state-of-the-art approach with the same data. As such, the proposed work demonstrated similar or improved level of the accuracy (95%) and f1-score (95%) over other works, while using reducing sensor density.
, Jiang, J.
, Roth, T.
, Nguyen, C.
, Liu, Y.
and Lee, H.
Integrated Sensor Data Processing for Occupancy Detection in Residential Buildings, Energy and Buildings, [online], https://doi.org/10.1016/j.enbuild.2021.110810, https://tsapps.nist.gov/publication/get_pdf.cfm?pub_id=930542
(Accessed June 5, 2023)