Multi-layer perceptron model for air quality prediction

This study trained two MLP models with dierent activation functions in assessing the capability of the model for the prediction of air quality. The daily air quality data and meteorological variables from year 2010-2014 were assembled in training and testing the models. The MLP model with the combin...

Full description

Saved in:
Bibliographic Details
Main Authors: Abdullah S., Ismail M., Ahmed A.N.
Other Authors: 56509029800
Format: Article
Published: Universiti Putra Malaysia 2023
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.uniten.dspace-24261
record_format dspace
spelling my.uniten.dspace-242612023-05-29T15:22:29Z Multi-layer perceptron model for air quality prediction Abdullah S. Ismail M. Ahmed A.N. 56509029800 57210403363 57214837520 This study trained two MLP models with dierent activation functions in assessing the capability of the model for the prediction of air quality. The daily air quality data and meteorological variables from year 2010-2014 were assembled in training and testing the models. The MLP model with the combination of tansig and purelin activation function revealed 69.0% of variance in data with 5.58 ?g/m3 (RMSE) and 80.0% of variance in data with 8.14 ?g/m3 (RMSE), during training and testing phase, respectively. This model is appropriate for operational used by respected authorities in managing air quality and as early warning during unhealthy level of air quality. � 2019, Universiti Putra Malaysia. Final 2023-05-29T07:22:29Z 2023-05-29T07:22:29Z 2019 Article 2-s2.0-85078661071 https://www.scopus.com/inward/record.uri?eid=2-s2.0-85078661071&partnerID=40&md5=32d4fa96a02de33e78449203a53b5e85 https://irepository.uniten.edu.my/handle/123456789/24261 13 S 85 95 Universiti Putra Malaysia Scopus
institution Universiti Tenaga Nasional
building UNITEN Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Tenaga Nasional
content_source UNITEN Institutional Repository
url_provider http://dspace.uniten.edu.my/
description This study trained two MLP models with dierent activation functions in assessing the capability of the model for the prediction of air quality. The daily air quality data and meteorological variables from year 2010-2014 were assembled in training and testing the models. The MLP model with the combination of tansig and purelin activation function revealed 69.0% of variance in data with 5.58 ?g/m3 (RMSE) and 80.0% of variance in data with 8.14 ?g/m3 (RMSE), during training and testing phase, respectively. This model is appropriate for operational used by respected authorities in managing air quality and as early warning during unhealthy level of air quality. � 2019, Universiti Putra Malaysia.
author2 56509029800
author_facet 56509029800
Abdullah S.
Ismail M.
Ahmed A.N.
format Article
author Abdullah S.
Ismail M.
Ahmed A.N.
spellingShingle Abdullah S.
Ismail M.
Ahmed A.N.
Multi-layer perceptron model for air quality prediction
author_sort Abdullah S.
title Multi-layer perceptron model for air quality prediction
title_short Multi-layer perceptron model for air quality prediction
title_full Multi-layer perceptron model for air quality prediction
title_fullStr Multi-layer perceptron model for air quality prediction
title_full_unstemmed Multi-layer perceptron model for air quality prediction
title_sort multi-layer perceptron model for air quality prediction
publisher Universiti Putra Malaysia
publishDate 2023
_version_ 1806427985354424320
score 13.214268