Nonlinear combination method of forecasters applied to PM time series

被引:28
作者
de Mattos Neto, Paulo S. G. [1 ]
Cavalcanti, George D. C. [1 ]
Madeiro, Francisco [2 ]
机构
[1] Univ Fed Pernambuco UFPE, Ctr Informat CIn, Av Jornalista Anibal Fernandes S-N, Recife, PE, Brazil
[2] Univ Catolica Pernambuco UNICAP, CCT, Rua Principe 526, Recife, PE, Brazil
关键词
Forecasting; Combination; Residual analysis; Air pollution; Hybrid system; NEURAL-NETWORK; AIR-POLLUTION; MODELING SYSTEM; PREDICTION; ARIMA;
D O I
10.1016/j.patrec.2017.06.008
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Hybrid systems that combine Artificial Neural Networks with other forecasters have been widely employed for time series forecasting. In this context, some architectures use temporal patterns extracted from the error series (residuals), i.e., the difference between the time series and the forecasting of this time series. These architectures have reached relevant theoretical and practical results. However, in the learning process of complex time series using these hybrid systems two open questions arise: it is hard to ensure that the linear and nonlinear patterns, underlying the time series, are properly modeled; and the best function to combine the time series forecaster and error series forecaster is unknown. In this context, this work proposes a Nonlinear Combination (NoLiC) method to combine forecasters. The NoLiC method is a hybrid system that is composed of two steps: i) estimation of the models' parameters for the time series and their respective residuals, and ii) search for the best function that combines these models using a multi-layer perceptron. Experimental simulations are conducted using four real-world complex time series of great importance for public health and evaluated using six performance measures. The results show that the NoLiC method reaches superior results when compared with literature works. (C) 2017 Elsevier B.V. All rights reserved.
引用
收藏
页码:65 / 72
页数:8
相关论文
共 35 条
  • [21] Extensive evaluation of neural network models for the prediction of NO2 and PM10 concentrations, compared with a deterministic modelling system and measurements in central Helsinki
    Kukkonen, J
    Partanen, L
    Karppinen, A
    Ruuskanen, J
    Junninen, H
    Kolehmainen, M
    Niska, H
    Dorling, S
    Chatterton, T
    Foxall, R
    Cawley, G
    [J]. ATMOSPHERIC ENVIRONMENT, 2003, 37 (32) : 4539 - 4550
  • [22] A review of unsupervised feature learning and deep learning for time-series modeling
    Langkvist, Martin
    Karlsson, Lars
    Loutfi, Amy
    [J]. PATTERN RECOGNITION LETTERS, 2014, 42 : 11 - 24
  • [23] Air pollution-related illness: Effects of particles
    Nel, A
    [J]. SCIENCE, 2005, 308 (5723) : 804 - 806
  • [24] Evaluation of an integrated modelling system containing a multi-layer perceptron model and the numerical weather prediction model HIRLAM for the forecasting of urban airborne pollutant concentrations
    Niska, H
    Rantamäki, M
    Hiltunen, T
    Karppinen, A
    Kukkonen, J
    Ruuskanen, J
    Kolehmainen, M
    [J]. ATMOSPHERIC ENVIRONMENT, 2005, 39 (35) : 6524 - 6536
  • [25] Coarse particulate matter air pollution and hospital admissions for cardiovascular and respiratory diseases among medicare patients
    Peng, Roger D.
    Chang, Howard H.
    Bell, Michelle L.
    McDermott, Aidan
    Zeger, Scott L.
    Samet, Jonathan M.
    Dominici, Francesca
    [J]. JAMA-JOURNAL OF THE AMERICAN MEDICAL ASSOCIATION, 2008, 299 (18): : 2172 - 2179
  • [26] Measurement of Fitness Function efficiency using Data Envelopment Analysis
    Silva, David A.
    Alves, Gabriela I.
    de Mattos Neto, Paulo S. G.
    Ferreira, Tiago A. E.
    [J]. EXPERT SYSTEMS WITH APPLICATIONS, 2014, 41 (16) : 7147 - 7160
  • [27] Evaluation of a multiple regression model for the forecasting of the concentrations of NOx and PM10 in Athens and Helsinki
    Vlachogianni, A.
    Kassomenos, P.
    Karppinen, Ari
    Karakitsios, S.
    Kukkonen, Jaakko
    [J]. SCIENCE OF THE TOTAL ENVIRONMENT, 2011, 409 (08) : 1559 - 1571
  • [28] Intercomparison of air quality data using principal component analysis, and forecasting of PM10 and PM2.5 concentrations using artificial neural networks, in Thessaloniki and Helsinki
    Voukantsis, Dimitris
    Karatzas, Kostas
    Kukkonen, Jaakko
    Rasanen, Teemu
    Karppinen, Ari
    Kolehmainen, Mikko
    [J]. SCIENCE OF THE TOTAL ENVIRONMENT, 2011, 409 (07) : 1266 - 1276
  • [29] Application of a New Hybrid Model with Seasonal Auto-Regressive Integrated Moving Average (ARIMA) and Nonlinear Auto-Regressive Neural Network (NARNN) in Forecasting Incidence Cases of HFMD in Shenzhen, China
    Yu, Lijing
    Zhou, Lingling
    Tan, Li
    Jiang, Hongbo
    Wang, Ying
    Wei, Sheng
    Nie, Shaofa
    [J]. PLOS ONE, 2014, 9 (06):
  • [30] Time series forecasting using a hybrid ARIMA and neural network model
    Zhang, GP
    [J]. NEUROCOMPUTING, 2003, 50 : 159 - 175