Air pollution index prediction using multiple neural networks
Air quality monitoring and forecasting tools are necessary for the purpose of taking precautionary measures against air pollution, such as reducing the effect of a predicted air pollution peak on the surrounding population and ecosystem. In this study a single Feed-forward Artificial Neural Network...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IIUM Press, International Islamic University Malaysia
2017
|
| Subjects: | |
| Online Access: | http://eprints.usm.my/38274/ http://eprints.usm.my/38274/1/AIR_POLLUITON_INDEX_PREDICTION_USING_MULTIPLE_NEURAL_NETWORKS.pdf |
| _version_ | 1848878422674112512 |
|---|---|
| author | Ahmad, Zainal Rahim, Nazira Aniza Bahadori, Alireza Jie, Zhang |
| author_facet | Ahmad, Zainal Rahim, Nazira Aniza Bahadori, Alireza Jie, Zhang |
| author_sort | Ahmad, Zainal |
| building | USM Institutional Repository |
| collection | Online Access |
| description | Air quality monitoring and forecasting tools are necessary for the purpose of taking precautionary measures against air pollution, such as reducing the effect of a predicted air pollution peak on the surrounding population and ecosystem. In this study a single Feed-forward Artificial Neural Network (FANN) is shown to be able to predict the Air Pollution Index (API) with a Mean Squared Error (MSE) and coefficient determination, R2, of 0.1856 and 0.7950 respectively. However, due to the non-robust nature of single FANN, a selective combination of Multiple Neural Networks (MNN) is introduced using backward elimination and a forward selection method. The results show that both selective combination methods can improve the robustness and performance of the API prediction with the MSE and R2 of 0.1614 and 0.8210 respectively. This clearly shows that it is possible to reduce the number of networks combined in MNN for API prediction, without losses of any information in terms of the performance of the final API prediction model. |
| first_indexed | 2025-11-15T17:31:05Z |
| format | Article |
| id | usm-38274 |
| institution | Universiti Sains Malaysia |
| institution_category | Local University |
| language | English |
| last_indexed | 2025-11-15T17:31:05Z |
| publishDate | 2017 |
| publisher | IIUM Press, International Islamic University Malaysia |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | usm-382742018-01-08T02:08:49Z http://eprints.usm.my/38274/ Air pollution index prediction using multiple neural networks Ahmad, Zainal Rahim, Nazira Aniza Bahadori, Alireza Jie, Zhang TP155-156 Chemical engineering Air quality monitoring and forecasting tools are necessary for the purpose of taking precautionary measures against air pollution, such as reducing the effect of a predicted air pollution peak on the surrounding population and ecosystem. In this study a single Feed-forward Artificial Neural Network (FANN) is shown to be able to predict the Air Pollution Index (API) with a Mean Squared Error (MSE) and coefficient determination, R2, of 0.1856 and 0.7950 respectively. However, due to the non-robust nature of single FANN, a selective combination of Multiple Neural Networks (MNN) is introduced using backward elimination and a forward selection method. The results show that both selective combination methods can improve the robustness and performance of the API prediction with the MSE and R2 of 0.1614 and 0.8210 respectively. This clearly shows that it is possible to reduce the number of networks combined in MNN for API prediction, without losses of any information in terms of the performance of the final API prediction model. IIUM Press, International Islamic University Malaysia 2017 Article PeerReviewed application/pdf en http://eprints.usm.my/38274/1/AIR_POLLUITON_INDEX_PREDICTION_USING_MULTIPLE_NEURAL_NETWORKS.pdf Ahmad, Zainal and Rahim, Nazira Aniza and Bahadori, Alireza and Jie, Zhang (2017) Air pollution index prediction using multiple neural networks. International Islamic University Malaysia Engineering Journal, 18 (1). pp. 1-12. ISSN 1511-788X http://journals.iium.edu.my/ejournal/index.php/iiumej/article/view/684 |
| spellingShingle | TP155-156 Chemical engineering Ahmad, Zainal Rahim, Nazira Aniza Bahadori, Alireza Jie, Zhang Air pollution index prediction using multiple neural networks |
| title | Air pollution index prediction using multiple neural networks |
| title_full | Air pollution index prediction using multiple neural networks |
| title_fullStr | Air pollution index prediction using multiple neural networks |
| title_full_unstemmed | Air pollution index prediction using multiple neural networks |
| title_short | Air pollution index prediction using multiple neural networks |
| title_sort | air pollution index prediction using multiple neural networks |
| topic | TP155-156 Chemical engineering |
| url | http://eprints.usm.my/38274/ http://eprints.usm.my/38274/ http://eprints.usm.my/38274/1/AIR_POLLUITON_INDEX_PREDICTION_USING_MULTIPLE_NEURAL_NETWORKS.pdf |