首页 » 文章 » 文章详细信息
Scientific Programming Volume 2019 ,2019-07-25
A Novel Phase Space Reconstruction- (PSR-) Based Predictive Algorithm to Forecast Atmospheric Particulate Matter Concentration
Research Article
Syed Ahsin Ali Shah 1 Wajid Aziz 1 , 2 Malik Sajjad Ahmed Nadeem 1 Majid Almaraashi 2 Seong-O. Shim 2 Turki M. Habeebullah 3
Show affiliations
DOI:10.1155/2019/6780379
Received 2019-03-26, accepted for publication 2019-07-04, Published 2019-07-04
PDF
摘要

The prediction of atmospheric particulate matter (APM) concentration is essential to reduce adverse effects on human health and to enforce emission restrictions. The dynamics of APM are inherently nonlinear and chaotic. Phase space reconstruction (PSR) is one of the widely used methods for chaotic time series analysis. The APM mass concentrations are an outcome of complex anthropogenic contributors evolving with time, which may operate on multiple time scales. Thus, the traditional single-variable PSR-based prediction algorithm in which data points of last embedding dimension are used as a target set may fail to account for multiple time scales inherent in APM concentrations. To address this issue, we propose a novel PSR-based scientific solution that accounts for the information contained at multiple time scales. Different machine learning algorithms are used to evaluate the performance of the proposed and traditional PSR techniques for predicting mass concentrations of particulate matter up to 2.5 micron (PM2.5), up to 10 micron (PM10.0), and ratio of PM2.5/PM10.0. Hourly time series data of PM2.5 and PM10.0 mass concentrations are collected from January 2014 to September 2015 at the Masfalah air quality monitoring station (couple of kilometers from the Holy Mosque in Makkah, Saudi Arabia). The performances of various learning algorithms are evaluated using RMSE and MAE. The results demonstrated that prediction error of all the machine learning techniques is smaller for the proposed PSR approach compared to traditional approach. For PM2.5, FFNN leads to best results (both RMSE and MAE 0.04 μgm−3), followed by SVR-L (RMSE 0.01 μgm−3 and MAE 0.09 μgm−3) and RF (RMSE 1.27 μgm−3 and MAE 0.86 μgm−3). For PM10.0, SVR-L leads to best results (both RMSE and MAE 0.06 μgm−3), followed by FFNN (RMSE 0.13 μgm−3 and MAE 0.09 μgm−3) and RF (RMSE 1.60 μgm−3 and MAE 1.16 μgm−3). For PM2.5/PM10.0, FFNN is the best and accurate method for prediction (0.001 for both RMSE and MAE), followed by RF (0.02 for both RMSE and MAE) and SVR-L (RMSE 0.05 μgm−3 and MAE 0.04).

授权许可

Copyright © 2019 Syed Ahsin Ali Shah et al. 2019
This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

通讯作者

Wajid Aziz.Department of Computer Sciences and Information Technology, University of Azad Kashmir, 13100 Azad Kashmir, Pakistan, ajku.edu.pk;College of Computer Sciences and Engineering, University of Jeddah, Saudi Arabia, uj.edu.sa.kh_wajid@yahoo.com

推荐引用方式

Syed Ahsin Ali Shah,Wajid Aziz,Malik Sajjad Ahmed Nadeem,Majid Almaraashi,Seong-O. Shim,Turki M. Habeebullah. A Novel Phase Space Reconstruction- (PSR-) Based Predictive Algorithm to Forecast Atmospheric Particulate Matter Concentration. Scientific Programming ,Vol.2019(2019)

您觉得这篇文章对您有帮助吗?
分享和收藏
0

是否收藏?

参考文献
[1] A. B. Chelani, D. G. Gajghate, S. M. Tamhane, M. Z. Hasan. et al.(2001). Statistical modeling of ambient air pollutants in Delhi. Water, Air, and Soil Pollution.132(3-4):315-331. DOI: 10.15406/ijbsbe.2017.02.00007.
[2] B. Çığşar, D. Ünal. (2019). Comparison of data mining classification algorithms determining the default risk. Scientific Programming.2019-8. DOI: 10.15406/ijbsbe.2017.02.00007.
[3] B. Efron, R. J. Tibshirani. (1994). An Introduction to the Bootstrap. DOI: 10.15406/ijbsbe.2017.02.00007.
[4] P. Pérez, A. Trier, J. Reyes. (2000). Prediction of PM concentrations several hours in advance using neural networks in Santiago, Chile. Atmospheric Environment.34(8):1189-1196. DOI: 10.15406/ijbsbe.2017.02.00007.
[5] A. M. Fraser, H. L. Swinney. (1986). Independent coordinates for strange attractors from mutual information. Physical Review A.33(2):1134-1140. DOI: 10.15406/ijbsbe.2017.02.00007.
[6] H. Zhang, L. Zhou, J. Zhu. (2015). Study on financial time series prediction based on phase space reconstruction and support vector machine (SVM). American Journal of Applied Mathematics.3(3):112-117. DOI: 10.15406/ijbsbe.2017.02.00007.
[7] A. B. Chelani, D. G. Gajghate, M. Z. Hasan. (2002). Prediction of ambient PM and toxic metals using artificial neural networks. Journal of the Air & Waste Management Association.52(7):805-810. DOI: 10.15406/ijbsbe.2017.02.00007.
[8] M. B. Kennel, R. Brown, H. D. I. Abarbanel. (1992). Determining embedding dimension for phase-space reconstruction using a geometrical construction. Physical Review A.45(6):3403-3411. DOI: 10.15406/ijbsbe.2017.02.00007.
[9] H. Drucker, C. J. Burges, L. Kaufman, A. J. Smola. et al.(1997). Support vector regression machines. Advances in Neural Information Processing Systems.9:155-161. DOI: 10.15406/ijbsbe.2017.02.00007.
[10] M. Costa, A. L. Goldberger, C. K. Peng. (2005). Multiscale entropy analysis of biological signals. Physical Review E.71(2). DOI: 10.15406/ijbsbe.2017.02.00007.
[11] U. Schlink, O. Herbarth, G. Tetzlaff. (1997). A component time-series model for SO data: forecasting, interpretation and modification. Atmospheric Environment.31(9):1285-1295. DOI: 10.15406/ijbsbe.2017.02.00007.
[12] U. Kumar, A. Prakash, V. K. Jain. (2008). Characterization of chaos in air pollutants: a Volterra-Wiener-Korenberg series and numerical titration approach. Atmospheric Environment.42(7):1537-1551. DOI: 10.15406/ijbsbe.2017.02.00007.
[13] E. Harnandez, F. Martin, F. Valero. (1992). Statistical forecast models for daily air particulate iron and lead concentrations for Madrid, Spain. Atmos. Environ.26(1):107-116. DOI: 10.15406/ijbsbe.2017.02.00007.
[14] G. A. Salini, P. Pérez. (2015). A study of the dynamic behaviour of fine particulate matter in Santiago, Chile. Aerosol and Air Quality Research.15(1):154-165. DOI: 10.15406/ijbsbe.2017.02.00007.
[15] H. Z. Liu, S. L. Wang, J. Y. Liu. (2013). LS-SVM prediction model based on phase space reconstruction for dam deformation. Advanced Materials Research.663:55-59. DOI: 10.15406/ijbsbe.2017.02.00007.
[16] A. B. Chelani, S. Devotta. (2006). Nonlinear analysis and prediction of coarse particulate matter concentration in ambient air. Journal of the Air & Waste Management Association.56(1):78-84. DOI: 10.15406/ijbsbe.2017.02.00007.
[17] A. Chelani, S. Devotta. (2006). Air quality forecasting using a hybrid autoregressive and nonlinear model. Atmospheric Environment.40(10):1774-1780. DOI: 10.15406/ijbsbe.2017.02.00007.
[18] I. Awan, W. Aziz, I. H. Shah. (2018). Studying the dynamics of interbeat interval time series of healthy and congestive heart failure subjects using scale based symbolic entropy analysis. PLoS One.13(5). DOI: 10.15406/ijbsbe.2017.02.00007.
[19] B. Yu, C. Huang, Z. Liu, H. Wang. et al.(2011). A chaotic analysis on air pollution index change over past 10 years in Lanzhou, northwest China. Stochastic Environmental Research and Risk Assessment.25(5):643-653. DOI: 10.15406/ijbsbe.2017.02.00007.
[20] M. Costa, C. K. Peng, A. L. Goldberger, J. M. Hausdorff. et al.(2003). Multiscale entropy analysis of human gait dynamics. Physica A: Statistical Mechanics and its Applications.330(1-2):53-60. DOI: 10.15406/ijbsbe.2017.02.00007.
[21] WHO. Ambient (Outdoor) Air Quality and Health. DOI: 10.15406/ijbsbe.2017.02.00007.
[22] T. M. Habeebullah. (2013). Health impacts of PM using AirQ2. 2.3 model in Makkah. Journal of Basic and Applied Sciences.8:259-268. DOI: 10.15406/ijbsbe.2017.02.00007.
[23] A. M. F. Mohammed, O. A. Attala, T. M. Habeebullah. (2017). PM and their bio-contamination in Makkah Saudi Arabia- case study. International Journal of Biosensors & Bioelectronics.2(1):1-6. DOI: 10.15406/ijbsbe.2017.02.00007.
[24] M. Costa, A. A. Priplata, L. A. Lipsitz. (2007). Noise and poise: enhancement of postural complexity in the elderly with a stochastic-resonance-based therapy. Europhysics Letters (EPL).77(6). DOI: 10.15406/ijbsbe.2017.02.00007.
[25] P. Kline. (1998). The New Psychometrics: Science, Psychology and Measurement. DOI: 10.15406/ijbsbe.2017.02.00007.
[26] S. Munir, T. M. Habeebullah, A. M. F. Mohammed, E. A. Morsy. et al.(Feb 2017). Analysing PM and its association with PM and meteorology in the arid climate of Makkah, Saudi Arabia. Aerosol and Air Quality Research.17(2):453-464. DOI: 10.15406/ijbsbe.2017.02.00007.
[27] G. P. Zhang. (2012). Neural Networks for Time-Series Forecasting. DOI: 10.15406/ijbsbe.2017.02.00007.
[28] N. Othman, M. Z. Mat-Jafri, L. H. San. (2010). Estimating particulate matter concentration over arid region using satellite remote sensing: a case study in Makkah, Saudi Arabia. Modern Applied Science.4(11). DOI: 10.15406/ijbsbe.2017.02.00007.
[29] S. Munir, T. M. Habeebullah, A. R. Seroji, S. S. Gabr. et al.(2013). Quantifying temporal trends of atmospheric pollutants in Makkah (1997–2012). Atmospheric Environment.77:647-655. DOI: 10.15406/ijbsbe.2017.02.00007.
[30] J. Colls. (2002). Air Pollution. DOI: 10.15406/ijbsbe.2017.02.00007.
[31] Q. Yan, S. Wang, B. Li. (2014). Forecasting uranium resource price prediction by extreme learning machine with empirical mode decomposition and phase space reconstruction. Discrete Dynamics in Nature and Society.2014-10. DOI: 10.15406/ijbsbe.2017.02.00007.
[32] L. Breiman. (2001). Random forests. Machine Learning.45(1):5-32. DOI: 10.15406/ijbsbe.2017.02.00007.
[33] F. Takens. (1981). Detecting strange attractors in turbulence. Dynamical Systems and Turbulence.898:366-381. DOI: 10.15406/ijbsbe.2017.02.00007.
[34] S. Saeed, W. Aziz, M. Rafique, I. Ahmad. et al.(Mar 2017). Quantification of non-linear dynamics and chaos of ambient particulate matter concentrations in Muzaffarabad city. Aerosol and Air Quality Research.17(3):849-856. DOI: 10.15406/ijbsbe.2017.02.00007.
[35] S. K. M. Hassan. (2006). Atmospheric polycyclic aromatic hydrocarbons and some heavy metals in suspended particulate matter in urban, industrial and residential areas in Greater Cairo. . DOI: 10.15406/ijbsbe.2017.02.00007.
[36] C. Frazier, K. M. Kockelman. (2004). Chaos theory and transportation systems: instructive example. Transportation Research Record: Journal of the Transportation Research Board.1897(1):9-17. DOI: 10.15406/ijbsbe.2017.02.00007.
[37] I.-F. Li, P. Biswas, S. Islam. (1994). Estimation of the dominant degrees of freedom for air pollutant concentration data: applications to ozone measurements. Atmospheric Environment.28(9):1707-1714. DOI: 10.15406/ijbsbe.2017.02.00007.
[38] K. Koçak, L. Şaylan, O. Şen. (2000). Nonlinear time series prediction of O concentration in Istanbul. Atmospheric Environment.34(8):1267-1271. DOI: 10.15406/ijbsbe.2017.02.00007.
[39] J.-L. Chen, S. Islam, P. Biswas. (1998). Nonlinear dynamics of hourly ozone concentrations. Atmospheric Environment.32(11):1839-1848. DOI: 10.15406/ijbsbe.2017.02.00007.
[40] L. Shen, Y. Wen, X. Li. (2017). Improving prediction accuracy of cooling load using EMD, PSR and RBFNN. Journal of Physics: Conference Series.887(1). DOI: 10.15406/ijbsbe.2017.02.00007.
[41] A. B. Chelani, R. N. Singh, S. Devotta. (2005). Nonlinear dynamical characterization and prediction of ambient nitrogen dioxide concentration. Water, Air, and Soil Pollution.166(1–4):121-138. DOI: 10.15406/ijbsbe.2017.02.00007.
[42] E. Bradley, H. Kantz. (2015). Nonlinear time-series analysis revisited. Chaos: An Interdisciplinary Journal of Nonlinear Science.25(9):097610. DOI: 10.15406/ijbsbe.2017.02.00007.
[43] J. Han, J. Pei, M. Kamber. (2011). Data Mining: Concepts and Techniques. DOI: 10.15406/ijbsbe.2017.02.00007.
[44] A. Olinsky, S. Chen, L. Harlow. (2003). The comparative efficacy of imputation methods for missing data in structural equation modeling. European Journal of Operational Research.151(1):53-79. DOI: 10.15406/ijbsbe.2017.02.00007.
文献评价指标
浏览 4次
下载全文 0次
评分次数 0次
用户评分 0.0分
分享 0次