Andrew Baldwin
Research Subjects
Andrew Baldwin has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Christos Efstratiou
University of Kent
1 shared publication - Chun Wai Chiu
School of Computing, University of Kent, Canterbury, Kent, UK
1 shared publication - Malcolm Clarke
Baxall Construction Ltd., Paddock Wood, Kent, UK
1 shared publication - Marialena Nikolopoulou
University of Kent
1 shared publication - Matthew Barker
Baxall Construction Ltd., Paddock Wood, Kent, UK
1 shared publication
Latest Publications
- Open Access
- 29 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 329-332
A Machine Learning Framework for Optimising Indoor Thermal Comfort and Air Quality through Sensor Data Streams
Optimising thermal comfort and air quality in indoor environments presents a complex, dynamic challenge that traditional static systems struggle to address effectively. We propose a novel real-time framework that tackles this multifaceted problem by leveraging stream clustering and time-series forecasting techniques. Our system continuously analyses sensor data to summarise comfort conditions and predict future indoor states. Simulations based on the stream clustering model indicate potential for significant improvements in indoor comfort, increasing comfort duration from 6% to 74%. Furthermore, the time-series forecasting model demonstrated strong performance, achieving mean absolute errors of 0.026 and 0.034 on test and demonstration datasets, respectively. This resource-efficient approach demonstrates promise for real-time indoor environment management, effectively balancing thermal comfort and air quality considerations.
- 29 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 329-332
Open AccessA Machine Learning Framework for Optimising Indoor Thermal Comfort and Air Quality through Sensor Data Streams
Optimising thermal comfort and air quality in indoor environments presents a complex, dynamic challenge that traditional static systems struggle to address effectively. We propose a novel real-time framework that tackles this multifaceted problem by leveraging stream clustering and time-series forecasting techniques. Our system continuously analyses sensor data to summarise comfort conditions and predict future indoor states. Simulations based on the stream clustering model indicate potential for significant improvements in indoor comfort, increasing comfort duration from 6% to 74%. Furthermore, the time-series forecasting model demonstrated strong performance, achieving mean absolute errors of 0.026 and 0.034 on test and demonstration datasets, respectively. This resource-efficient approach demonstrates promise for real-time indoor environment management, effectively balancing thermal comfort and air quality considerations.