A clustering-based ensemble approach with improved pigeon-inspired optimization and extreme learning machine for air quality prediction

Feng Jiang, Jiaqi He, Tianhai Tian

Research output: Contribution to journalArticleResearchpeer-review

Abstract

In this paper, a novel hybrid learning method is carried out to forecast urban air quality index (AQI). Wavelet packet decomposition (WPD) is firstly performed to decompose the original AQI data into lower-frequency subseries. Then, we improve the pigeon-inspired optimization through using the particle swarm optimization algorithm. The improved pigeon-inspired optimization (IPIO) approach is applied to optimize the initial weights and thresholds of extreme learning machine (ELM) and then the modified ELM (MELM) is employed to forecast the subseries respectively. Moreover, multidimensional scaling and K-means (MSK) clustering methods are utilized to cluster the forecasting outcomes into high frequency, medium–high frequency, medium–low frequency and low frequency subseries. Finally, MELM, as an ensemble approach, is applied to ensemble the subseries together and achieve the final results. To test the predictive precision of the proposed hybrid WPD-MELM-MSK-MELM learning method, AQI of Harbin in China is adopted to make short-term, middle-term and long-term predictions separately. Different decomposition approaches are utilized to compare with WPD, and the non-clustering hybrid model is also compared with the proposed method. The forecasting outcomes indicate that WPD is more suitable for predicting AQI and the proposed WPD-MELM-MSK-MELM learning method has better predictive performance on horizontal precision, directional precision and robustness than some existing methods and benchmark models in this paper.

Original languageEnglish
Article number105827
Pages (from-to)1-14
Number of pages14
JournalApplied Soft Computing Journal
Volume85
DOIs
Publication statusPublished - 2019

Keywords

  • Extreme learning machine
  • K-means clustering
  • Multidimensional scaling
  • Pigeon-inspired optimization
  • Wavelet packet decomposition

Cite this

@article{096ad8c99de3428f92bc4979028c1054,
title = "A clustering-based ensemble approach with improved pigeon-inspired optimization and extreme learning machine for air quality prediction",
abstract = "In this paper, a novel hybrid learning method is carried out to forecast urban air quality index (AQI). Wavelet packet decomposition (WPD) is firstly performed to decompose the original AQI data into lower-frequency subseries. Then, we improve the pigeon-inspired optimization through using the particle swarm optimization algorithm. The improved pigeon-inspired optimization (IPIO) approach is applied to optimize the initial weights and thresholds of extreme learning machine (ELM) and then the modified ELM (MELM) is employed to forecast the subseries respectively. Moreover, multidimensional scaling and K-means (MSK) clustering methods are utilized to cluster the forecasting outcomes into high frequency, medium–high frequency, medium–low frequency and low frequency subseries. Finally, MELM, as an ensemble approach, is applied to ensemble the subseries together and achieve the final results. To test the predictive precision of the proposed hybrid WPD-MELM-MSK-MELM learning method, AQI of Harbin in China is adopted to make short-term, middle-term and long-term predictions separately. Different decomposition approaches are utilized to compare with WPD, and the non-clustering hybrid model is also compared with the proposed method. The forecasting outcomes indicate that WPD is more suitable for predicting AQI and the proposed WPD-MELM-MSK-MELM learning method has better predictive performance on horizontal precision, directional precision and robustness than some existing methods and benchmark models in this paper.",
keywords = "Extreme learning machine, K-means clustering, Multidimensional scaling, Pigeon-inspired optimization, Wavelet packet decomposition",
author = "Feng Jiang and Jiaqi He and Tianhai Tian",
year = "2019",
doi = "10.1016/j.asoc.2019.105827",
language = "English",
volume = "85",
pages = "1--14",
journal = "Applied Soft Computing Journal",
issn = "1568-4946",
publisher = "Elsevier",

}

A clustering-based ensemble approach with improved pigeon-inspired optimization and extreme learning machine for air quality prediction. / Jiang, Feng; He, Jiaqi; Tian, Tianhai.

In: Applied Soft Computing Journal, Vol. 85, 105827, 2019, p. 1-14.

Research output: Contribution to journalArticleResearchpeer-review

TY - JOUR

T1 - A clustering-based ensemble approach with improved pigeon-inspired optimization and extreme learning machine for air quality prediction

AU - Jiang, Feng

AU - He, Jiaqi

AU - Tian, Tianhai

PY - 2019

Y1 - 2019

N2 - In this paper, a novel hybrid learning method is carried out to forecast urban air quality index (AQI). Wavelet packet decomposition (WPD) is firstly performed to decompose the original AQI data into lower-frequency subseries. Then, we improve the pigeon-inspired optimization through using the particle swarm optimization algorithm. The improved pigeon-inspired optimization (IPIO) approach is applied to optimize the initial weights and thresholds of extreme learning machine (ELM) and then the modified ELM (MELM) is employed to forecast the subseries respectively. Moreover, multidimensional scaling and K-means (MSK) clustering methods are utilized to cluster the forecasting outcomes into high frequency, medium–high frequency, medium–low frequency and low frequency subseries. Finally, MELM, as an ensemble approach, is applied to ensemble the subseries together and achieve the final results. To test the predictive precision of the proposed hybrid WPD-MELM-MSK-MELM learning method, AQI of Harbin in China is adopted to make short-term, middle-term and long-term predictions separately. Different decomposition approaches are utilized to compare with WPD, and the non-clustering hybrid model is also compared with the proposed method. The forecasting outcomes indicate that WPD is more suitable for predicting AQI and the proposed WPD-MELM-MSK-MELM learning method has better predictive performance on horizontal precision, directional precision and robustness than some existing methods and benchmark models in this paper.

AB - In this paper, a novel hybrid learning method is carried out to forecast urban air quality index (AQI). Wavelet packet decomposition (WPD) is firstly performed to decompose the original AQI data into lower-frequency subseries. Then, we improve the pigeon-inspired optimization through using the particle swarm optimization algorithm. The improved pigeon-inspired optimization (IPIO) approach is applied to optimize the initial weights and thresholds of extreme learning machine (ELM) and then the modified ELM (MELM) is employed to forecast the subseries respectively. Moreover, multidimensional scaling and K-means (MSK) clustering methods are utilized to cluster the forecasting outcomes into high frequency, medium–high frequency, medium–low frequency and low frequency subseries. Finally, MELM, as an ensemble approach, is applied to ensemble the subseries together and achieve the final results. To test the predictive precision of the proposed hybrid WPD-MELM-MSK-MELM learning method, AQI of Harbin in China is adopted to make short-term, middle-term and long-term predictions separately. Different decomposition approaches are utilized to compare with WPD, and the non-clustering hybrid model is also compared with the proposed method. The forecasting outcomes indicate that WPD is more suitable for predicting AQI and the proposed WPD-MELM-MSK-MELM learning method has better predictive performance on horizontal precision, directional precision and robustness than some existing methods and benchmark models in this paper.

KW - Extreme learning machine

KW - K-means clustering

KW - Multidimensional scaling

KW - Pigeon-inspired optimization

KW - Wavelet packet decomposition

UR - http://www.scopus.com/inward/record.url?scp=85073947720&partnerID=8YFLogxK

U2 - 10.1016/j.asoc.2019.105827

DO - 10.1016/j.asoc.2019.105827

M3 - Article

VL - 85

SP - 1

EP - 14

JO - Applied Soft Computing Journal

JF - Applied Soft Computing Journal

SN - 1568-4946

M1 - 105827

ER -