Sampling Using Fuzzy and Crisp Clustering to Improve Recall of Building Comfort Feedback
- Resource Type
- Conference
- Authors
- MacDonald, Ross; Neveditsin, Nikita; Lingras, Pawan; Qin, Zheng; Hillard, Trent
- Source
- 2019 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE) Fuzzy Systems (FUZZ-IEEE), 2019 IEEE International Conference on. :1-6 Jun, 2019
- Subject
- Computing and Processing
Robotics and Control Systems
Signal Processing and Analysis
Predictive models
Buildings
Clustering algorithms
Machine learning
Euclidean distance
Sensitivity
Clustering methods
- Language
- ISSN
- 1558-4739
The primary objective of a building energy management system is to ensure the comfort of its occupants. This paper reports experiments with a user feedback system for a central temperature controlled building. Individual room temperatures are further adjusted based on occupant feedback. The number of feedback points are limited creating a data imbalance. The paper describes how crisp and fuzzy clustering can be used to sample the data points when there is no feedback from the users. The results of the proposed sampling is compared with other sampling strategies. The goal of the research is to maximize the recall of feedback through machine learning.