Please use this identifier to cite or link to this item:
https://hdl.handle.net/10356/64311
Title: | Occupancy estimation in indoor environments | Authors: | Chen, Constance Xiangxing | Keywords: | DRNTU::Engineering::Electrical and electronic engineering | Issue Date: | 2015 | Abstract: | Building energy efficiency is a rising issue that attracts many organisations to achieve sustainability in buildings. In order to achieve this goal, occupancy levels in rooms are detected to optimize the performance of HVAC systems. The effect of air quality, due to the presence of occupants, has a direct effect using indices such as humidity, temperature and CO2 levels. This report summarises the setup of the hardware and Raspberry Pi for data collection and storage. Incorporating with the sensor nodes, CO2 levels, temperature, pressure, humility, altitude and airflow for analysis of the data, as well as a camera to capture actual occupancy. The data collected will be analysed by training Extreme Learning Machine (ELM) and Multi-layer Perceptron (MLP) to provide an estimated occupancy in real time. By making comparison between the two machine learning techniques using distinct features, we will determine which method provides a better indicator in estimating occupancy level. | URI: | http://hdl.handle.net/10356/64311 | Schools: | School of Electrical and Electronic Engineering | Rights: | Nanyang Technological University | Fulltext Permission: | restricted | Fulltext Availability: | With Fulltext |
Appears in Collections: | EEE Student Reports (FYP/IA/PA/PI) |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
Final report-Occupancy estimation.pdf Restricted Access | 3.13 MB | Adobe PDF | View/Open |
Page view(s) 50
430
Updated on Mar 28, 2024
Download(s) 50
25
Updated on Mar 28, 2024
Google ScholarTM
Check
Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.