SMART CARBON MONOXIDE PREDICTION MODEL FOR BETTER URBAN AIR QUALITY MANAGEMENT
INTERIM SEMESTER 2020/2021
Saved in:
| Main Author: | |
|---|---|
| Format: | text::Final Year Project |
| Published: |
2023
|
| Subjects: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1852709596851863552 |
|---|---|
| author | ALMALAYIH MUSTAFA YASIR MOHSIN |
| author_facet | ALMALAYIH MUSTAFA YASIR MOHSIN |
| author_sort | ALMALAYIH MUSTAFA YASIR MOHSIN |
| building | UNITEN Library |
| collection | Institutional Repository |
| content_provider | Universiti Tenaga Nasional |
| content_source | UNITEN Institutional Repository |
| continent | Asia |
| country | Malaysia |
| description | INTERIM SEMESTER 2020/2021 |
| format | Resource Types::text::Final Year Project |
| id | my.uniten.dspace-20468 |
| institution | Universiti Tenaga Nasional |
| publishDate | 2023 |
| record_format | dspace |
| spelling | my.uniten.dspace-204682025-12-17T09:31:58Z SMART CARBON MONOXIDE PREDICTION MODEL FOR BETTER URBAN AIR QUALITY MANAGEMENT ALMALAYIH MUSTAFA YASIR MOHSIN ANN CARBONE MONOXIDE PREDICTION INTERIM SEMESTER 2020/2021 Carbone monoxide concertation has been exceeding the allowable levels in Malaysia. For this reason, the main objective of this study is to propose carbon monoxide (CO) prediction model based on support vector machine to replace statistical model-based techniques. Three years of historical data were used as an input to develop the proposed models to predict 24-hour and 12-hour of tropospheric Carbone monoxide concentrations. Four different models were used to predict Carbone monoxide concentrations which is Automated neural network, Random forest, decision tree model and Support vector machine (SVM) and the input parameters used are wind speed, humidity, ozone, Nitric oxide (NOx), Sulfur dioxide (SO2) and Nitrogen Dioxide (NO2). For each location we made ten different scenarios with different input. The selection of the input parameters was based on the correlation of each input parameter to the output which the CO. After that we used STATISTICA software to predict the CO levels using the four models. The ANN-MLP outperformed the other models and showed efficiency in predicting Carbone monoxide at three different locations which is Kelang, KL and PJ, and it was similar with the results of other researchers. Great coefficients of correlations were calculated between the measured and predicted values 0.7190 and 0.7490 for Kelang 24hr&12hr period, 0.9140 and 0.8942 for KL 24hr&12hr period and 0.8127 and 0.7441 for PJ 24hr&12hr. 2023-05-03T15:01:52Z 2023-05-03T15:01:52Z 2020-09 Resource Types::text::Final Year Project https://irepository.uniten.edu.my/handle/123456789/20468 application/pdf |
| spellingShingle | ANN CARBONE MONOXIDE PREDICTION ALMALAYIH MUSTAFA YASIR MOHSIN SMART CARBON MONOXIDE PREDICTION MODEL FOR BETTER URBAN AIR QUALITY MANAGEMENT |
| title | SMART CARBON MONOXIDE PREDICTION MODEL FOR BETTER URBAN AIR QUALITY MANAGEMENT |
| title_full | SMART CARBON MONOXIDE PREDICTION MODEL FOR BETTER URBAN AIR QUALITY MANAGEMENT |
| title_fullStr | SMART CARBON MONOXIDE PREDICTION MODEL FOR BETTER URBAN AIR QUALITY MANAGEMENT |
| title_full_unstemmed | SMART CARBON MONOXIDE PREDICTION MODEL FOR BETTER URBAN AIR QUALITY MANAGEMENT |
| title_short | SMART CARBON MONOXIDE PREDICTION MODEL FOR BETTER URBAN AIR QUALITY MANAGEMENT |
| title_sort | smart carbon monoxide prediction model for better urban air quality management |
| topic | ANN CARBONE MONOXIDE PREDICTION |
| url_provider | http://dspace.uniten.edu.my/ |