Description

Information on occupant counts has wide applications in operation, control optimization and retrospective analysis of buildings. In this study, we propose a novel method utilizing data from widely deployed Wi-Fi infrastructure to infer occupant counts through a machine learning approach. Compared with the currently available indirect measurement methods, our method improves the performance of estimating people count: (1) we avoid privacy concerns by anonymizing and reshuffling the MAC addresses on a daily basis; (2) we adopted a heuristic approach to cluster connected devices into different types based on their daily connection duration. We tested the method in an office building located in California, demonstrating a relatively high accuracy compared with existing methods. The proposed technique is generic and can be applied to other buildings or spaces with recorded Wi-Fi data.

Citation: 2019 Annual Conference, Kansas City, MO, Extended Abstracts

Product Details

Published:

2019

Number of Pages:

3

Units of Measure:

Dual

File Size:

1 file , 1.5 MB

Product Code(s):

D-KC-19-A041