AUTOMATED CLEANING AND WEB-BASED DATA VISUALIZATION FOR URBAN HEAT ISLAND MONITORING IN BANDUNG CITY
Urban Heat Island (UHI) is a phenomenon where the temperature in urban areas is higher than in rural areas. Previous research has designed a low-cost sensor called Heat Island Electric or HIEL to measure UHI in Bandung using the fixed station method. Based on the results of HIEL data exploration,...
Saved in:
| Main Author: | |
|---|---|
| Format: | Theses |
| Language: | Indonesia |
| Subjects: | |
| Online Access: | https://digilib.itb.ac.id/gdl/view/71337 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Institut Teknologi Bandung |
| Language: | Indonesia |
| Summary: | Urban Heat Island (UHI) is a phenomenon where the temperature in urban areas is
higher than in rural areas. Previous research has designed a low-cost sensor called
Heat Island Electric or HIEL to measure UHI in Bandung using the fixed station
method. Based on the results of HIEL data exploration, the data still found dirty data,
so data cleaning actions need to be carried out to obtain accurate UHI analysis results.
The data cleaning process aims to analyze the UHI phenomenon in the city of
Bandung based on the data owned and adjusted to the existing data conditions. The
method of cleaning the data in this study is done automatically by using a cronjob.
So that the analyzed UHI data can be seen by the people of Bandung City, a websitebased
application is made as a visualization of UHI data. On the website, the UHI
phenomenon can be observed from time to time. In addition, the website can be used
for further research because there is a feature to download UHI data and HIEL sensor
data. This study tested a website-based data cleaning and visualization program to
measure its accuracy and feasibility. Based on the test results, the data cleaning
program has an MSE value of 0.00552 and an RMSE of 0.02038. The website-based
UHI data visualization gets a SUS value of 71.65. So it can be concluded that the
website-based UHI data visualization is feasible. |
|---|