Potential assessment of the “support vector machine” method in forecasting ambient air pollutant trends

Lu, Wen-Hsiang; Wang, Wenjian

doi:10.1016/j.chemosphere.2004.10.032

Cited by 196 publications

(80 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…A back-propagation feed-forward neural network based algorithm (Cai et al, 2009) and a SVR algorithm using spline kernel (loss function: ε-insensitive) (Lu and Wang, 2005) have been employed for this purpose. The prediction results from all three models are plotted in Fig.…”

Section: Accepted Manuscriptmentioning

confidence: 99%

Prediction of traffic-related nitrogen oxides concentrations using Structural Time-Series models

Lawson

Ghosh

Broderick

2011

Atmospheric Environment

View full text Add to dashboard Cite

Ambient air quality monitoring, modeling and compliance to the standards set by European Union (EU) directives and World Health Organization (WHO) guidelines are required to ensure the protection of human and environmental health. Congested urban areas are most susceptible to traffic related air pollution which is the most problematic source of air pollution in Ireland. Longterm continuous real-time monitoring of ambient air quality at such urban centers is essential but often not realistic due to financial and operational constraints. Hence, the development of a resource-conservative ambient air quality monitoring technique is essential to ensure compliance with the threshold values set by the standards. As an intelligent and advanced statistical methodology, a Structural Time Series (STS) based approach has been introduced in this paper to develop a parsimonious and computationally simple air quality model. In STS methodology, the different components of a time-series dataset such as the trend, seasonal, cyclical and calendar variations can be modeled separately. To test the effectiveness of the proposed modeling strategy, average hourly concentrations of nitrogen dioxide and nitrogen oxides from a congested urban arterial in Dublin city centre were modeled using STS methodology. The prediction error estimates from the developed air quality model indicate that the STS model can be a useful tool in predicting nitrogen dioxide and nitrogen oxides concentrations in urban areas and will be particularly useful in situations where the information on external variables such as meteorology or traffic volume is not available.

show abstract

Section: Accepted Manuscriptmentioning

confidence: 99%

Prediction of traffic-related nitrogen oxides concentrations using Structural Time-Series models

Lawson

Ghosh

Broderick

2011

Atmospheric Environment

View full text Add to dashboard Cite

show abstract

“…Support vector machines (SVM), developed by Vapnik [13], can provide an effective novel approach to improve generalization performance of neural networks and achieve global solutions simultaneously. SVM can overcome most drawbacks of ANN and has been reported to show promising results [14][15][16]. However, the performance of the resulting SVM is often hinged on the appropriate choice of the kernel.…”

Section: Introductionmentioning

confidence: 99%

Short-Term Prediction of Air Pollution in Macau Using Support Vector Machines

Vong

Wong

et al. 2012

Journal of Control Science and Engineering

View full text Add to dashboard Cite

Forecasting of air pollution is a popular and important topic in recent years due to the health impact caused by air pollution. It is necessary to build an early warning system, which provides forecast and also alerts health alarm to local inhabitants by medical practitioners and the local government. Meteorological and pollutions data collected daily at monitoring stations of Macau can be used in this study to build a forecasting system. Support vector machines (SVMs), a novel type of machine learning technique based on statistical learning theory, can be used for regression and time series prediction. SVM is capable of good generalization while the performance of the SVM model is often hinged on the appropriate choice of the kernel.

show abstract

“…Various techniques like linear regression, auto regression, Multi Layer Perceptron, Radial Basis Function networks are applied to predict atmospheric parameters like temperature, wind speed, rainfall, meteorological pollution, etc. [5], [6], [7], [8], [9], [10], [11]. Recently, various soft computing techniques such as ANN, Fuzzy logic and Genetic algorithm are acquiring importance in predicting air temperature as these techniques can handle noisy, nonlinearity and uncertainty elements satisfactorily which placed as superior to the existing traditional methods.…”

Section: Introductionmentioning

confidence: 99%

Modeling of Air Temperature using ANFIS by Wavelet Refined Parameters

S¹,

Deka²

2016

IJISA

View full text Add to dashboard Cite

Abstract-The precise modeling of average air temperature is a significant and much essential parameter in frame of reference for decision-making in agriculture field, drought detection and environmental related issues. The aim of this research is to construct an accurate model to modeling average air temperature using hybrid Wavelet-ANFIS techniques. Being cognizant of the fact, uncertainty handling capability is achieved with ANFIS technique; a cognitive approach to integrate ANFIS technique along with pre-processed data by using Wavelet transformation. Detailing on approach, in this work utilized Discrete Wavelet transform under Daubechies mother Wavelet up to 3rd level of decomposition. This study extends up to seven station's meteorological data records. The following developed hybrid model's performance is compared with single ANFIS models for all seven stations. The obtained results were evaluated using correlation coefficient, root mean square error and scatter index These results confirmed that the proposed hybridized Wavelet-ANFIS model has estimable potential in terms of modeling temperature than ANFIS model alone.

show abstract

Potential assessment of the “support vector machine” method in forecasting ambient air pollutant trends

Cited by 196 publications

References 22 publications

Prediction of traffic-related nitrogen oxides concentrations using Structural Time-Series models

Prediction of traffic-related nitrogen oxides concentrations using Structural Time-Series models

Short-Term Prediction of Air Pollution in Macau Using Support Vector Machines

Modeling of Air Temperature using ANFIS by Wavelet Refined Parameters

Contact Info

Product

Resources

About