Machine learning-based building environment control system development via human physiological signal: Focusing on building energy efficiency and the occupants productivity Machine learning-based building environment control system development via human physiological signal: Focusing on building energy efficiency and the occupants productivity Project title Machine learning-based building environment control system development via human physiological signal: Focusing on building energy efficiency and the occupants productivity Research Objective and Goals The purpose of the research is to investigate the relationship between indoor thermal environment, physiological signals, and cognitive response, and to develop reinforcement-learning-based prediction model of the occupants optimum thermal environment as a function of the human physiological signal. To achieve this goal, the following specific research objectives were established: 1) Understand the relationship between indoor thermal environment, human physiological signals, and cognitive responses through the series of human experiments 2) Develop a reinforcement-learning-based prediction model of the occupants thermal comfort as a function of participants physiological signals for personalized temperature control and optimum building energy control Funding Source and Collaborator This project is US-Korea joint research project, funded by the Institute of Information and Communication Technology Planning and Evaluation (IITP) in Korea. This project is to achieve a common research goal between Korean university and foreign institutes, and students will be sent to foreign institute (ASU) to research abroad for 6~12 months during the whole research period (12 months). The collaborator of this project is Dr. Sung-guk Yoon, Associate professor of Electrical Engineering at in Korea. Dr. Yoon will work as a PI in Korea and hi team will provide knowledges in machine-learning and energy system control as a multidisciplinary collaborator. Methods A series of human experiments will be conducted to collect human physiological signal data in various temperature conditions. Thermal sensation and comfort will be surveyed as a participants subjective perception to compare with the physiological signals, and participants productivity will be measured by the cognitive tests, such as OSPAN and vigilance test. Collected data will be analyzed by the data-mining software, and the thermal comfort and productivity prediction model will be established, and building energy control algorithm will be developed via reinforced-learning.
|Effective start/end date||5/1/21 → 4/30/22|
- OTHER: Foreign Government: $48,000.00
Explore the research topics touched on by this project. These labels are generated based on the underlying awards/grants. Together they form a unique fingerprint.