A hybrid neuro-fuzzy prediction system with butterfly optimization algorithm for PM2.5 forecasting

Bhanja, S; Metia, S; Das, A

A hybrid neuro-fuzzy prediction system with butterfly optimization algorithm for PM2.5 forecasting

Bhanja, S Metia, S

Das, A

Permalink

Publisher:: SPRINGER HEIDELBERG
Publication Type:: Journal Article
Citation:: Microsystem Technologies, 2022, 28, (12), pp. 2577-2592
Issue Date:: 2022-12-01

Closed Access

	Filename	Description	Size
	s00542-022-05252-5.pdf	Published version	2.56 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Bhanja, S
dc.contributor.author	Metia, S https://orcid.org/0000-0002-5676-1146
dc.contributor.author	Das, A
dc.date.accessioned	2023-07-26T22:52:13Z
dc.date.available	2023-07-26T22:52:13Z
dc.date.issued	2022-12-01
dc.identifier.citation	Microsystem Technologies, 2022, 28, (12), pp. 2577-2592
dc.identifier.issn	0946-7076
dc.identifier.issn	1432-1858
dc.identifier.uri	http://hdl.handle.net/10453/171660
dc.description.abstract	With the rapid increase of urbanization and industrialization, particulate matter (PM2.5) concentration has increased significantly. PM2.5 profile forecasting has become one of the critical research areas in environmental control and protection. The early detection of PM2.5 as a pollutant is vital because PM2.5 has a significant impact on human health than other pollutants. This paper proposes a deep neuro-fuzzy prediction system (DNFPS) by amalgamating the deep learning and the fuzzy time series algorithm to forecast the PM2.5 concentration. The proposed predictive model consists of three phases; a data preprocessing algorithm to generate a high-quality dataset, a denoising autoencoder using fully convolutional neural networks (FCNNs) to extract the features from the pollutant time series profile as well as reduce the dimension of the time series dataset, and the type-2 fuzzy time series forecasting (FTSF) method to forecast PM2.5 concentration. The butterfly optimization algorithm (BOA) is integrated with the type-2 FTSF method to improve the prediction accuracy of the proposed method. FTSF-BOA is implemented to fine-tune the length of type-2 fuzzy intervals. Experiments employing Sydney data sets to analyze the performance of DNFPS. DNFPS shows that the proposed model achieves an excellent performance than other standard baseline models. It has lower computational time (training time) than the other traditional baseline deep learning models.
dc.language	English
dc.publisher	SPRINGER HEIDELBERG
dc.relation.ispartof	Microsystem Technologies
dc.relation.isbasedon	10.1007/s00542-022-05252-5
dc.rights	info:eu-repo/semantics/closedAccess
dc.subject	1005 Communications Technologies, 1007 Nanotechnology
dc.subject.classification	Mechanical Engineering & Transports
dc.subject.classification	Nanoscience & Nanotechnology
dc.subject.classification	4009 Electronics, sensors and digital hardware
dc.title	A hybrid neuro-fuzzy prediction system with butterfly optimization algorithm for PM2.5 forecasting
dc.type	Journal Article
utslib.citation.volume	28
utslib.for	1005 Communications Technologies
utslib.for	1007 Nanotechnology
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
utslib.copyright.status	closed_access	*
dc.date.updated	2023-07-26T22:52:12Z
pubs.issue	12
pubs.publication-status	Published
pubs.volume	28
utslib.citation.issue	12

Abstract:

With the rapid increase of urbanization and industrialization, particulate matter (PM2.5) concentration has increased significantly. PM2.5 profile forecasting has become one of the critical research areas in environmental control and protection. The early detection of PM2.5 as a pollutant is vital because PM2.5 has a significant impact on human health than other pollutants. This paper proposes a deep neuro-fuzzy prediction system (DNFPS) by amalgamating the deep learning and the fuzzy time series algorithm to forecast the PM2.5 concentration. The proposed predictive model consists of three phases; a data preprocessing algorithm to generate a high-quality dataset, a denoising autoencoder using fully convolutional neural networks (FCNNs) to extract the features from the pollutant time series profile as well as reduce the dimension of the time series dataset, and the type-2 fuzzy time series forecasting (FTSF) method to forecast PM2.5 concentration. The butterfly optimization algorithm (BOA) is integrated with the type-2 FTSF method to improve the prediction accuracy of the proposed method. FTSF-BOA is implemented to fine-tune the length of type-2 fuzzy intervals. Experiments employing Sydney data sets to analyze the performance of DNFPS. DNFPS shows that the proposed model achieves an excellent performance than other standard baseline models. It has lower computational time (training time) than the other traditional baseline deep learning models.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/171660