PM2.5 Prediction Using Genetic Algorithm-Based Feature Selection and Encoder-Decoder Model

The concentration of fine particulate matter (PM2.5), which represents inhalable particles with diameters of 2.5 micrometers and smaller, is a vital air quality index. Such particles can penetrate deep into the human lungs and severely affect human health. This paper studies accurate PM2.5 predictio...

Full description

Saved in:
Bibliographic Details
Main Authors: Minh Hieu Nguyen, Phi Le Nguyen, Kien Nguyen, Van An Le, Thanh-Hung Nguyen, Yusheng Ji
Format: Article
Language:English
Published: IEEE 2021-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/9399408/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849223127299522560
author Minh Hieu Nguyen
Phi Le Nguyen
Kien Nguyen
Van An Le
Thanh-Hung Nguyen
Yusheng Ji
author_facet Minh Hieu Nguyen
Phi Le Nguyen
Kien Nguyen
Van An Le
Thanh-Hung Nguyen
Yusheng Ji
author_sort Minh Hieu Nguyen
collection DOAJ
description The concentration of fine particulate matter (PM2.5), which represents inhalable particles with diameters of 2.5 micrometers and smaller, is a vital air quality index. Such particles can penetrate deep into the human lungs and severely affect human health. This paper studies accurate PM2.5 prediction, which can potentially contribute to reducing or avoiding the negative consequences. Our approach’s novelty is to utilize the genetic algorithm (GA) and an encoder-decoder (E-D) model for PM2.5 prediction. The GA benefits feature selection and remove outliers to enhance the prediction accuracy. The encoder-decoder model with long short-term memory (LSTM), which relaxes the restrictions between the input and output of the model, can be used to effectively predict the PM2.5 concentration. We evaluate the proposed model on air quality datasets from Hanoi and Taiwan. The evaluation results show that our model achieves excellent performance. By merely using the E-D model, we can obtain more accurate (up to 53.7%) predictions than those of previous works. Moreover, the GA in our model has the advantage of obtaining the optimal feature combination for predicting the PM2.5 concentration. By combining the GA-based feature selection algorithm and the E-D model, our proposed approach further improves the accuracy by at least 13.7%.
format Article
id doaj-art-717688386c1944f6a2f92efb46d85f1c
institution Kabale University
issn 2169-3536
language English
publishDate 2021-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-717688386c1944f6a2f92efb46d85f1c2025-08-25T23:00:45ZengIEEEIEEE Access2169-35362021-01-019573385735010.1109/ACCESS.2021.30722809399408PM2.5 Prediction Using Genetic Algorithm-Based Feature Selection and Encoder-Decoder ModelMinh Hieu Nguyen0https://orcid.org/0000-0001-6547-7641Phi Le Nguyen1Kien Nguyen2https://orcid.org/0000-0003-0400-3084Van An Le3Thanh-Hung Nguyen4Yusheng Ji5https://orcid.org/0000-0003-4364-8491School of Information and Communication Technology, Hanoi University of Science and Technology, Hanoi, VietnamSchool of Information and Communication Technology, Hanoi University of Science and Technology, Hanoi, VietnamGraduate School of Engineering, Chiba University, Chiba, JapanDepartment of Informatics, The Graduate University for Advanced Studies, SOKENDAI, Tokyo, JapanSchool of Information and Communication Technology, Hanoi University of Science and Technology, Hanoi, VietnamDepartment of Informatics, The Graduate University for Advanced Studies, SOKENDAI, Tokyo, JapanThe concentration of fine particulate matter (PM2.5), which represents inhalable particles with diameters of 2.5 micrometers and smaller, is a vital air quality index. Such particles can penetrate deep into the human lungs and severely affect human health. This paper studies accurate PM2.5 prediction, which can potentially contribute to reducing or avoiding the negative consequences. Our approach’s novelty is to utilize the genetic algorithm (GA) and an encoder-decoder (E-D) model for PM2.5 prediction. The GA benefits feature selection and remove outliers to enhance the prediction accuracy. The encoder-decoder model with long short-term memory (LSTM), which relaxes the restrictions between the input and output of the model, can be used to effectively predict the PM2.5 concentration. We evaluate the proposed model on air quality datasets from Hanoi and Taiwan. The evaluation results show that our model achieves excellent performance. By merely using the E-D model, we can obtain more accurate (up to 53.7%) predictions than those of previous works. Moreover, the GA in our model has the advantage of obtaining the optimal feature combination for predicting the PM2.5 concentration. By combining the GA-based feature selection algorithm and the E-D model, our proposed approach further improves the accuracy by at least 13.7%.https://ieeexplore.ieee.org/document/9399408/PM 25genetic algorithmfeature selectionlong short-term memoryencoder-decoder model
spellingShingle Minh Hieu Nguyen
Phi Le Nguyen
Kien Nguyen
Van An Le
Thanh-Hung Nguyen
Yusheng Ji
PM2.5 Prediction Using Genetic Algorithm-Based Feature Selection and Encoder-Decoder Model
IEEE Access
PM 25
genetic algorithm
feature selection
long short-term memory
encoder-decoder model
title PM2.5 Prediction Using Genetic Algorithm-Based Feature Selection and Encoder-Decoder Model
title_full PM2.5 Prediction Using Genetic Algorithm-Based Feature Selection and Encoder-Decoder Model
title_fullStr PM2.5 Prediction Using Genetic Algorithm-Based Feature Selection and Encoder-Decoder Model
title_full_unstemmed PM2.5 Prediction Using Genetic Algorithm-Based Feature Selection and Encoder-Decoder Model
title_short PM2.5 Prediction Using Genetic Algorithm-Based Feature Selection and Encoder-Decoder Model
title_sort pm2 5 prediction using genetic algorithm based feature selection and encoder decoder model
topic PM 25
genetic algorithm
feature selection
long short-term memory
encoder-decoder model
url https://ieeexplore.ieee.org/document/9399408/
work_keys_str_mv AT minhhieunguyen pm25predictionusinggeneticalgorithmbasedfeatureselectionandencoderdecodermodel
AT philenguyen pm25predictionusinggeneticalgorithmbasedfeatureselectionandencoderdecodermodel
AT kiennguyen pm25predictionusinggeneticalgorithmbasedfeatureselectionandencoderdecodermodel
AT vananle pm25predictionusinggeneticalgorithmbasedfeatureselectionandencoderdecodermodel
AT thanhhungnguyen pm25predictionusinggeneticalgorithmbasedfeatureselectionandencoderdecodermodel
AT yushengji pm25predictionusinggeneticalgorithmbasedfeatureselectionandencoderdecodermodel