ARTIFICIAL NEURAL NETWORK FOR THE QUANTITATIVE ANALYSIS OF AIR TOXIC VOCs

Li, Yan; Wang, Junde; Chen, Zuoru; Zhou, Xue-tie

doi:10.1081/al-100106851

Cited by 10 publications

(8 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Li Yan et al [22] have proved that absorbance data obtained from the characteristic wavenumbers contain more representative information than those from equi-spaced wavenumbers. So, in this work, the number of input cells was set to 9, which equalled the number of characteristic peaks at 1219 cm 21 …”

Section: Data Preparationmentioning

confidence: 99%

Combination of Neural Network and SBFM Algorithm for Monitoring VOCs Distribution by Open Path FTIR Spectrometry

Ren¹,

Li²,

Yu³

et al. 2007

Instrumentation Science & Technology

Self Cite

View full text Add to dashboard Cite

In this research, the combination of artificial neural network (ANN) modeling and smooth basis function minimization (SBFM) algorithm were applied to Open Path Fourier transform infrared spectroscopy (OP-FTIR) for monitoring volatile organic compounds' concentration distribution in the air. ANN was utilized to analyze the measured mixture spectra containing chloroform, methanol, and methylene chloride; Then, SBFM was used to reconstruct each component's concentration distribution. The peak concentration locations and maximum concentration for three components are reconstructed accurately. The methodology presented in this paper has significant importance in detecting leaking source spot and monitoring airborne VOCs transport in chemical industrial workplaces.

show abstract

Section: Data Preparationmentioning

confidence: 99%

Combination of Neural Network and SBFM Algorithm for Monitoring VOCs Distribution by Open Path FTIR Spectrometry

Ren¹,

Li²,

Yu³

et al. 2007

Instrumentation Science & Technology

Self Cite

View full text Add to dashboard Cite

show abstract

“…Also, different integrated modeling systems for simulation and prediction of atmospheric pollution dispersion (Karppinen et al 2000;Owen et al 2000;Carruthers, Sheng, and Vanvyve 2008;Macintosh et al 2010;Zou et al 2010) or for air quality simulation have been constructed (Paatero 2000;Matthias 2008;Pay et al 2010;Appel et al 2011). In this context, the interest in monitoring and modeling the dispersion of volatile organic compounds in the atmosphere is increasing (Li et al 2001;Kabir and Kim 2010;Bereznicki et al 2012;Wei et al 2014).…”

Section: Introductionmentioning

confidence: 99%

Characterization of the Concentrations of Volatile Organic Compounds in the Romanian Littoral using General Regression Neural Networks: A Case Study

Bărbulescu

Barbeș

2015

Analytical Letters

View full text Add to dashboard Cite

In the last decade, preserving air quality in the northern Romanian Littoral has become a national priority. In order to monitor pollution, benzene, toluene, ortho-, meta-, and para-xylene, ethylbenzene, and styrene were determined at six monitoring sites in three industrial and three urban areas. The sampling was done by an active method and the analysis by gas chromatography. The statistical analysis demonstrated that the concentrations of the volatile organic compounds were under the limits established by the European Union's laws and that the pollutant distributions were asymmetric. Models were proposed for the concentrations of the volatile organic Downloaded by [New York University] at 09:48 07 June 20152 compounds, using the general regression neural network, with wind speed, air temperature, and humidity as regressors. The theoretical fit well with the experimental results, showing that the model is an effective alternative to conventional approaches.

show abstract

“…For the purpose of multivariate spectroscopic calibration, subagging has already been applied to linear methods as PLS and MLR with variable selection [37]; yet its role in improving non-linear calibration methods (such as ANN and GPR) has been under-explored. Previous studies demonstrated that non-linear regression for spectroscopic calibration can achieve accurate prediction of analyte properties [15][16][17][18]. However, their prediction performance may be sensitive to small change in calibration data and/or model parameters.…”

Section: Introductionmentioning

confidence: 99%

“…In the 1990s, ANN was introduced in the chemometrics community for spectroscopic calibration [16][17]. A typical feed-forward ANN model consists of three layers (input, hidden and output layer), each layer comprising multiple neurons.…”

Section: Artificial Neural Network (Ann)mentioning

confidence: 99%

“…Several strategies have been proposed to deal with the non-linearity, such as pre-processing [12] (standard normal variate (SNV) [13], extended multiplicative signal correction (EMSC) [14], etc. ), non-linear calibration techniques (artificial neural network (ANN) [15][16][17], Gaussian processes regression (GPR) [18][19]), and variable selection [20][21]. However, these models may be non-robust in the sense that small change in the calibration data and/or model parameters can result in significant change in model predictions.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation