
Designing learned CO 2 ‐based occupancy estimation in smart buildings
Author(s) -
Brennan Colin,
Taylor Graham W.,
Spachos Petros
Publication year - 2018
Publication title -
iet wireless sensor systems
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.433
H-Index - 27
eISSN - 2043-6394
pISSN - 2043-6386
DOI - 10.1049/iet-wss.2018.5027
Subject(s) - occupancy , computer science , scalability , random forest , machine learning , artificial intelligence , gradient boosting , boosting (machine learning) , data mining , engineering , architectural engineering , database
Many applications, such as smart buildings, crowd flow, action recognition, and assisted living, rely on occupancy information. Although the use of smart cameras and computer vision can assist with these tasks and provide accurate occupancy information, it can be cost prohibitive, invasive, and difficult to scale or generalise to different environments. An alternative solution should bring similar accuracy while minimising the listed problems. This work demonstrates that a scalable wireless sensor network with CO 2 ‐based estimation is a viable alternative. To support many applications, a solution must be transferable and must handle not knowing the physical system model; instead, it must learn to model CO 2 dynamics. This work presents a viable prototype and uses the captured data to train machine learning‐based occupancy estimation systems. Models are trained under varying conditions to assess the consequences of design decisions on performance. Four different learning models were compared: gradient boosting, k‐nearest neighbours (KNN), linear discriminant analysis, and random forests. With sufficient labelled data, the KNN model produced peak results with a root‐mean‐square error value of 1.021.