A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Fuzzy Art: Pattern Recognition of Wifi Detected Occupancy in Commercial Buildings
Research that predicts occupancy patterns in commercial buildings has gained in significance ever since the influence of occupants on building energy consumption became evident. Studies have employed a variety of sensory systems to collect the occupancy data and understand human behaviors throughout buildings. However, establishing a dedicated sensor network to collect occupancy data can become expensive for building owners. In this context, obtaining occupancy data from an existing WiFi network could eliminate the cost concerns. Data within the WiFi routers provide sufficient information for accurate estimates of occupancy. To estimate occupancy levels, this work proposes to learn and recognize WiFi connection using an Adaptive Resonance Theory (ART) artificial neural network. A detailed understanding of occupancy patterns using the WiFi data is helpful for developing heating and cooling schedules that optimize HVAC energy consumption. For this study, occupancy data was collected over a 17-week semester at the University of New Mexico using existing WiFi routers located in a large lecture hall used by multiple classes. This data was used to learn patterns of repetition using the neural network. The results show that if the 24-h occupancy profiles can be subdivided into smaller time segments defined by external schedules such as lecture start and end times or other constraints, significant patterns can be detected. A detailed understanding of these patterns can greatly facilitate occupancy load forecasting for effective building management (e.g. HVAC operation).
Fuzzy Art: Pattern Recognition of Wifi Detected Occupancy in Commercial Buildings
Research that predicts occupancy patterns in commercial buildings has gained in significance ever since the influence of occupants on building energy consumption became evident. Studies have employed a variety of sensory systems to collect the occupancy data and understand human behaviors throughout buildings. However, establishing a dedicated sensor network to collect occupancy data can become expensive for building owners. In this context, obtaining occupancy data from an existing WiFi network could eliminate the cost concerns. Data within the WiFi routers provide sufficient information for accurate estimates of occupancy. To estimate occupancy levels, this work proposes to learn and recognize WiFi connection using an Adaptive Resonance Theory (ART) artificial neural network. A detailed understanding of occupancy patterns using the WiFi data is helpful for developing heating and cooling schedules that optimize HVAC energy consumption. For this study, occupancy data was collected over a 17-week semester at the University of New Mexico using existing WiFi routers located in a large lecture hall used by multiple classes. This data was used to learn patterns of repetition using the neural network. The results show that if the 24-h occupancy profiles can be subdivided into smaller time segments defined by external schedules such as lecture start and end times or other constraints, significant patterns can be detected. A detailed understanding of these patterns can greatly facilitate occupancy load forecasting for effective building management (e.g. HVAC operation).
Fuzzy Art: Pattern Recognition of Wifi Detected Occupancy in Commercial Buildings
Lecture Notes in Civil Engineering
Walbridge, Scott (editor) / Nik-Bakht, Mazdak (editor) / Ng, Kelvin Tsun Wai (editor) / Shome, Manas (editor) / Alam, M. Shahria (editor) / el Damatty, Ashraf (editor) / Lovegrove, Gordon (editor) / Simma, Krishna Chaitanya Jagadeesh (author) / Caudell, Thomas P. (author) / Bogus, Susan M. (author)
Canadian Society of Civil Engineering Annual Conference ; 2021
Proceedings of the Canadian Society of Civil Engineering Annual Conference 2021 ; Chapter: 42 ; 517-529
2022-06-01
13 pages
Article/Chapter (Book)
Electronic Resource
English
Non-intrusive occupancy sensing in commercial buildings
| Elsevier | 2017
Modeling regular occupancy in commercial buildings using stochastic models
| Online Contents | 2015
| Taylor & Francis Verlag | 2017