Comfort and living environment analysis in smart living environment
In thermal comfort measurements, commonly uses indices like Predictive Mean Vote (PMV) to measure the thermal comfort of a given environment has brought about the creation of the ASHRAE global thermal Comfort Database II. However, despite it being the main indices to be used globally for thermal com...
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project |
| Language: | English |
| Published: |
Nanyang Technological University
2023
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/167054 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Nanyang Technological University |
| Language: | English |
| Summary: | In thermal comfort measurements, commonly uses indices like Predictive Mean Vote (PMV) to measure the thermal comfort of a given environment has brought about the creation of the ASHRAE global thermal Comfort Database II. However, despite it being the main indices to be used globally for thermal comfort evaluation. The accuracy of predicting the thermal comfort by the PMV model is considered to be quite low. In order to reinforce the prediction accuracy of PMV, the use of machine learning (ML) techniques to predict the thermal comfort will be used on the ASHRAE global thermal Comfort Database II. Such machine learning techniques that will be evaluated on are Artificial Neural Network (ANN), Support Vector Machine (SVM), K-Nearest Neighbor (KNN) and Naïve Bayes Classifiers. The objective of this project is to evaluate which ML techniques will be best suited in a thermal comfort prediction application and implement the proposed model in a mobile application for thermal comfort feedback that can display the model performance in thermal comfort prediction. |
|---|