Discrimination of Venezuelan spirituous beverages by a trace element-radial basis neural network approach.

Radial basis neural networks (RBNNs) were developed and evaluated for discrimination of specimens of 'aguardiente de Cocuy', a spirituous beverage produced in the northwestern region of Venezuela. The beverage is distilled from the must of Agave cocui Trelease in an artisanship fashion with little quality control. Forty specimens, with known concentrations of copper, iron, and zinc, were used in this study. The specimens were previously collected in various locations around Sucre Municipality (Falcón State) and Urdaneta Municipality (Lara State). The normalized concentrations of these elements served as indirect descriptors of origin (input data). They were presented to the neural networks through 1-3 input nodes in seven different combinations. In addition, two categories (two collection sites) and four categories (two collection sites+two manufacturing conditions) were designated as output data, in order to assess the impact of such selection on the discrimination performance. The overall performance of the four-category RBNNs was as follows (the input data is indicated in parentheses): (Cu-Fe)>(Cu-Zn)>(Cu)>(Zn)>(Fe-Zn)>(Cu-Fe-Zn)>(Fe). In this case, the highest percentage of correct hits was 82.5%. For the two-category RBNNs, the performance decreased as indicated below: (Cu)>(Cu-Fe)>(Cu-Zn)>(Fe-Zn)>(Zn) approximately (Cu-Fe-Zn)>(Fe). The reduction in the number of categories led to an increase in the discrimination performance of all the RBNNs, the best of which was 90.0%. The possibility of discriminating specimens of 'aguardiente de Cocuy' with such an accuracy, based on a single-element determination, is particularly attractive as it would result in a reduction of analysis' costs and laboratory's response time.

Evaluation of a generalized regression artificial neural network for extending cadmium's working calibration range in graphite furnace atomic absorption spectrometry.

A generalized regression artificial neural network (GRANN) was developed and evaluated for modeling cadmium's nonlinear calibration curve in order to extend its upper concentration limit from 4.0 microg L-1 up to 22.0 microg L-1. This type of neural network presents important advantages over the more popular backpropagation counterpart which are worth exploiting in analytical applications, namely, (1) a smaller number of variables have to be optimized, with the subsequent reduction in "development hassle"; and, (2) shorter development times, thanks to the fact that the adjustment of the weights (the artificial synapses) is a non-iterative, one-pass process. A backpropagation artificial neural network (BPANN), a second-order polynomial, and some less frequently employed polynomial and exponential functions (e.g., Gaussian, Lorentzian, and Boltzmann), were also evaluated for comparison purposes. The quality of the fit of the various models, assessed by calculating the root mean square of the percentage deviations, was as follows: GRANN>Boltzmann>second-order polynomial>BPANN>Gauss>Lorentz. The accuracy and precision of the models were further estimated through the determination of cadmium in the certified reference material "Trace Metals in Drinking Water" (High Purity Standards, Lot No. 490915), which has a cadmium certified concentration (12.00+/-0.06 microg L-1) that lies in the nonlinear regime of the calibration curve. Only the models generated by the GRANN and BPANN accurately predicted the concentrations of a series of solutions, prepared by serial dilution of the CRM, with cadmium concentrations below and above the maximum linear calibration limit (4.0 microg L-1). Extension of the working range by using the proposed methodology represents an attractive alternative from the analytical point of view, since it results in less specimen manipulation and consequently reduced contamination risks without compromising either the accuracy or the precision of the analyses. The implementation of artificial neural networks also helps to reduce the trial-and-error task of looking for the right mathematical model from among the many possibilities currently available in the various scientific and statistic software packages.

Determination of cadmium in urine specimens by graphite furnace atomic absorption spectrometry using a fast atomization program.

A simple, fast, and reliable method was developed for the determination of cadmium in urine specimens by graphite furnace atomic absorption spectrometry (GFAAS). The method involved dilution (1:1) of the specimens with a 4.0% HNO(3), direct injection of a 10mul aliquot of the corresponding solution into a hot transversely-heated graphite atomizer (110 degrees C), and application of a fast atomization program (42s) in which the conventional dry-pyrolysis sequence was substituted by a high-temperature (300 degrees C) drying step. The effect of the injection temperature (A), injection rate (B), pyrolysis' ramp (C) and hold (D) times over the analyte's integrated absorbance, peak-shape and repeatability of the measurements was evaluated by means of a 2(4-1) fractional factorial design. All those individual variables, as well as their first-order interactions (AB-, AC- and AD-type interactions) were found to exert a statistically significant effect (P<0.05). The lack of a chemical modifier other than the nitric acid itself benefited the overall methodology by allowing low-temperature atomization (1200 degrees C), enhanced atomic and background signals separation, and reduced blank values. A detection limit (3s, n=20) of 0.06mugl(-1) Cd, corresponding to 0.12mugl(-1) Cd in the urine specimen, and a characteristic mass of 1.78pg/0.0044s were obtained under the optimized conditions. The standard calibration technique (SCT) was used for quantitation. The successful determination of cadmium in Seronormtrade mark Trace Elements Urine Batch No. 115 (Nycomed Pharma AS) and in four urine specimens from volunteer donors (recoveries: 91.3-103.4%) attested to the robustness of the proposed method.

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

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 4.0mugl(-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 (0-22.0mugl(-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 12.0mugl(-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).

Determination of manganese in brain samples by slurry sampling graphite furnace atomic absorption spectrometry.

A simple procedure for the determination of manganese in different sections of human brain samples by graphite furnace atomic absorption spectrometry has been developed. Brain sections included cerebellum, hypothalamus, frontal cortex, vermix and encephalic trunk. Two sample preparation procedures were evaluated, namely, slurry sampling and microwave-assisted acid digestion. Brain slurries (2% w/v) could be prepared in distilled, de-ionized water, with good stability for up to 30 min. Brain samples were also digested in a domestic microwave oven using 5 ml of concentrated HNO(3). A mixed palladium+magnesium nitrate chemical modifier was used for thermal stabilization of the analyte in the electrothermal atomizer up to pyrolysis temperatures of 1300 degrees C, irrespective of the matrix. Quantitation of manganese was conducted in both cases by means of aqueous standards calibration. The detection limits were 0.3 and 0.4 ng ml(-1) for the slurry and the digested samples, respectively. The accuracy of the procedure was checked by comparing the results obtained in the analysis of slurries and digested brain samples, and by analysis of the NIST Bovine Liver standard reference material (SRM 1577a). The ease of slurry preparation, together with the conventional set of analytical and instrumental conditions selected for the determination of manganese make such methodology suitable for routine clinical applications.

Classification of Venezuelan spirituous beverages by means of discriminant analysis and artificial neural networks based on their Zn, Cu and Fe concentrations.

Copper, zinc and iron concentrations were determined in "aguardiente de Cocuy de Penca" (Cocuy de Penca firewater), a spirituous beverage very popular in the North-Western region of Venezuela, by flame atomic absorption spectrometry (FAAS). These elements were selected for their presence can be traced to the (illegal) manufacturing process of the aforementioned beverages. Linear and quadratic discriminant analysis (QDA), and artificial neural networks (ANNs) trained with the backpropagation algorithm were employed for estimating if such beverages can be distinguished based on the concentrations of these elements in the final product, and whether it is possible to assess the geographic location of the manufacturers (Lara or Falcón states) and the presence or absence of sugar in the end product. A linear discriminant analysis (LDA) performed poorly, overall estimation and prediction rates being 51.7% and 50.0%, respectively. A QDA showed a slightly better overall performance, yet unsatisfactory (estimation: 79.2%, prediction: 72.5%). Various ANNs, comprising a linear function (L) in the input layer, a sigmoid function (S) in the hidden layer(s) and a hyperbolic tangent function (T) in the output layer, were evaluated. Of the networks studied, the (3L:5S:7S:4T) gave the highest estimation (overall: 96.5%) and prediction rates (overall: 97.0%), demonstrating the superb performance of ANNs for classification purposes.