Nonlinear modelling of air pollution time series

R. J. Foxall; I. Krcmar; G. C. Cawley; S. R. Dorling; D. P. Mandic

doi:10.1109/ICASSP.2001.940597

Nonlinear modelling of air pollution time series

R. J. Foxall, I. Krcmar, G. C. Cawley, S. R. Dorling, D. P. Mandic

Research output: Contribution to conference › Paper

4 Citations (Scopus)

Abstract

An analysis of predictability of a nonlinear and nonstationary ozone time series is provided. For rigour, the deterministic versus stochastic (DVS) analysis is first undertaken to detect and measure inherent nonlinearity of the data. Based upon this, neural and linear adaptive predictors are compared on this time series for various filter orders, hence indicating the embedding dimension. Simulation results confirm the analysis and show that for this class of air pollution data, neural, especially recurrent neural predictors, perform best

Original language	English
Pages	3505-3508
Number of pages	4
DOIs	https://doi.org/10.1109/ICASSP.2001.940597
Publication status	Published - May 2001
Event	IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP-2001) - Salt Lake City, United States Duration: 7 May 2001 → 11 May 2001

Conference

Conference	IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP-2001)
Country/Territory	United States
City	Salt Lake City
Period	7/05/01 → 11/05/01

Access to Document

10.1109/ICASSP.2001.940597

Cite this

@conference{baebde1e0eae4f6caeb40c3c2f399d72,

title = "Nonlinear modelling of air pollution time series",

abstract = "An analysis of predictability of a nonlinear and nonstationary ozone time series is provided. For rigour, the deterministic versus stochastic (DVS) analysis is first undertaken to detect and measure inherent nonlinearity of the data. Based upon this, neural and linear adaptive predictors are compared on this time series for various filter orders, hence indicating the embedding dimension. Simulation results confirm the analysis and show that for this class of air pollution data, neural, especially recurrent neural predictors, perform best",

author = "Foxall, {R. J.} and I. Krcmar and Cawley, {G. C.} and Dorling, {S. R.} and Mandic, {D. P.}",

year = "2001",

month = may,

doi = "10.1109/ICASSP.2001.940597",

language = "English",

pages = "3505--3508",

note = "IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP-2001) ; Conference date: 07-05-2001 Through 11-05-2001",

}

TY - CONF

T1 - Nonlinear modelling of air pollution time series

AU - Foxall, R. J.

AU - Krcmar, I.

AU - Cawley, G. C.

AU - Dorling, S. R.

AU - Mandic, D. P.

PY - 2001/5

Y1 - 2001/5

N2 - An analysis of predictability of a nonlinear and nonstationary ozone time series is provided. For rigour, the deterministic versus stochastic (DVS) analysis is first undertaken to detect and measure inherent nonlinearity of the data. Based upon this, neural and linear adaptive predictors are compared on this time series for various filter orders, hence indicating the embedding dimension. Simulation results confirm the analysis and show that for this class of air pollution data, neural, especially recurrent neural predictors, perform best

AB - An analysis of predictability of a nonlinear and nonstationary ozone time series is provided. For rigour, the deterministic versus stochastic (DVS) analysis is first undertaken to detect and measure inherent nonlinearity of the data. Based upon this, neural and linear adaptive predictors are compared on this time series for various filter orders, hence indicating the embedding dimension. Simulation results confirm the analysis and show that for this class of air pollution data, neural, especially recurrent neural predictors, perform best

U2 - 10.1109/ICASSP.2001.940597

DO - 10.1109/ICASSP.2001.940597

M3 - Paper

SP - 3505

EP - 3508

T2 - IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP-2001)

Y2 - 7 May 2001 through 11 May 2001

ER -