Flow injection analysis of fluoride: optimization of experimental conditions and non-linear calibration using artificial neural networks

Zhou, Yongyao; Yan, Aixia; Xu, Haidong; Wang, Ketai; Chen, Xingguo; Hu, Zhide

doi:10.1039/b005287f

Cited by 11 publications

(4 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Zhou et al [38] established a linear combination of two variables, the peak height (H) and the residence time (T) as the response function (R F ). The aim is to maximize the peak height and minimize the residence time.…”

Section: Selection Of the Responsementioning

confidence: 99%

“…The objective function is a linear combination of different individual response variables and relies on three normalized factors. Zhou et al [38] used a linear combination of the peak height and the residence time as response function and a three-layer neural network for the optimisation of the spectrophotometric determination of fluoride. The optimisation performance of the artificial neural network was compared with that of a central composite design; the result showed that the artificial neural network provided better results that the central composite design for optimisation purposes.…”

Section: Natural Intelligence Techniquesmentioning

confidence: 99%

“…This four-factorial central composite design included 24 experiments plus six central point experiments [38].…”

Section: Multi-level Designsmentioning

confidence: 99%

See 2 more Smart Citations

An overview of qualimetric strategies for optimisation and calibration in pharmaceutical analysis using flow injection techniques

Bosque-Sendra

Gámiz‐Gracia

Garcı́a-Campaña

2003

Analytical and Bioanalytical Chemistry

View full text Add to dashboard Cite

Flow Injection analysis represents an attractive tool because of its great advantages, such as versatility, speed, high sampling rate and wide applicability in the field of pharmaceutical analysis. However, due to the inherent characteristics of the technique, the choice of the best set of operational and chemical conditions is complicated and the conventional univariate optimisation method present some limitations, mainly due to fact that the interdependence of variables is not considered. In relation to the calibration process, because of the transient character of the signals obtained using FIA manifolds coupled with different detection techniques, different strategies can be used in calibration to solve some problems related to the nature of the signal thereby improving the performance characteristics of the method. This paper offers an overview of different methodologies used in optimisation based on the use of statistically designed experiments and some strategies developed for calibration applied to the analysis of pharmaceuticals.

show abstract

Section: Selection Of the Responsementioning

confidence: 99%

Section: Natural Intelligence Techniquesmentioning

confidence: 99%

See 1 more Smart Citation

An overview of qualimetric strategies for optimisation and calibration in pharmaceutical analysis using flow injection techniques

Bosque-Sendra

Gámiz‐Gracia

Garcı́a-Campaña

2003

Analytical and Bioanalytical Chemistry

View full text Add to dashboard Cite

show abstract

“…Therefore, on a first approximation, they could be used for modeling the behavior of calibration curves in atomic absorption spectrometry. Even though ANNs have received significant attention for spectrophotometric applications [19][20][21][22], their use in atomic spectrometry is relatively scarce [23][24][25].…”

Section: Introductionmentioning

confidence: 99%

Increasing the working calibration range by means of artificial neural networks for the determination of cadmium by graphite furnace atomic absorption spectrometry

Hernández-Caraballo¹,

Avila-Gómez²,

Rivas

et al. 2004

Talanta

View full text Add to dashboard Cite

Feed-forward artificial neural networks (ANNs), trained with the generalized delta rule, were evaluated for modeling the non-linear behavior of calibration curves and increasing the working range for the determination of cadmium by graphite furnace atomic absorption spectrometry (GFAAS). Selection of this analyte was made on the basis of its short linear range (up to 4.0 g l −1 ). Two-layer neural networks, comprising one node in the input layer (linear transfer function); a variable number of neurons in the hidden layer (sigmoid transfer functions), and a single neuron (linear transfer function) in the output layer were assessed for such a purpose. The (1:2:1) neural network was selected on the basis of its capacity to adequately model the working calibration curve in the range of study (0-22.0 g l −1 Cd). The latter resulted in a nearly six fold increase in the working range. Cadmium was determined in the certified reference material "Trace Elements in Drinking Water" (High Purity Standards, Lot No. 490915) at four concentration levels (2.0, 4.0, 8.0 and 12.0 g l −1 Cd), which were experimentally within and above the linear dynamic range (LDR). No significant differences (P < 0.05) were found between the expected concentrations and the results obtained by means of the neural network. The proposed method was compared with the conventional "dilution" approach, and with fitting the working calibration curve by means of a second-order polynomial. Modeling by means of an ANN represents an alternative calibration technique, for its use helps in reducing sample manipulation (due to the extension of the working calibration range), and may provide higher accuracy of the determinations in the non-linear portion of the curve (as a result of the better fitness of the model).

show abstract

Future Aspects of Bioprocess Monitoring

Becker

Hitzmann

Muffler

et al. 2006

Advances in Biochemical Engineering/Biotechnology

View full text Add to dashboard Cite

Nature has the impressive ability to efficiently and precisely control biological processes by applying highly evolved principles and using minimal space and relatively simple building blocks. The challenge is to transfer these principles into technically applicable and precise analytical systems that can be used for many applications. This article summarizes some of the new approaches in sensor technology and control strategies for different bioprocesses such as fermentations, biotransformations, and downstream processes. It focuses on bio- and chemosensors, optical sensors, DNA and protein chip technology, software sensors, and modern aspects of data evaluation for improved process monitoring and control.

show abstract

Flow injection analysis of fluoride: optimization of experimental conditions and non-linear calibration using artificial neural networks

Cited by 11 publications

References 20 publications

An overview of qualimetric strategies for optimisation and calibration in pharmaceutical analysis using flow injection techniques

An overview of qualimetric strategies for optimisation and calibration in pharmaceutical analysis using flow injection techniques

Increasing the working calibration range by means of artificial neural networks for the determination of cadmium by graphite furnace atomic absorption spectrometry

Future Aspects of Bioprocess Monitoring

Contact Info

Product

Resources

About