The learning machine in quantitative chemical analysis: Part I. Anodic Stripping Voltammetry of Cadmium, Lead and Thallium

The linear learning machine method was applied to the determination of cadmium, lead and thallium down to 10-8 M by anodic stripping voltammetry at a hanging mercury drop electrode. With a total of three trained multicategory classifiers, concentrations of Cd, Pb and Tl could be predicted with an accuracy of ±10%. The classifiers were trained with the use of least-squares minimization. Numerical problems in the data matrix inversion were overcome by using singular value decomposition.

[1]  James Hardy Wilkinson,et al.  Linear algebra , 1971, Handbook for automatic computation.

[2]  Charles L. Wilkins,et al.  Classification of binary carbon-13 nuclear magnetic resonance spectra , 1977 .

[3]  G. Stewart,et al.  On the Numerical Properties of an Iterative Method for Computing the Moore–Penrose Generalized Inverse , 1974 .

[4]  Folke Ingman,et al.  Titration of mixtures of acids of nearly equal strengths , 1973 .

[5]  B. Kowalski,et al.  Computerized learning machines applied to chemical problems. Interpretation of infrared spectrometry data , 1969 .

[6]  Thomas L. Isenhour,et al.  Computerized learning machines applied to chemical problems. Molecular formula determination from low resolution mass spectrometry , 1969 .

[7]  A. Savitzky,et al.  Smoothing and Differentiation of Data by Simplified Least Squares Procedures. , 1964 .

[8]  J. Dolezal,et al.  Effect of the cathodic current of oxygen on oxidationcurrent-potential curves in anodic stripping polarography , 1970 .

[9]  S. P. Perone,et al.  Application of pattern recognition techniques to the interpretation of severely overlapped voltammetric data: studies with experimental data , 1977 .

[10]  D. D. Tunnicliff,et al.  Application of pattern separation techniques to mass spectrometric data. Determination of hydrocarbon types and the average molecular structure of gasoline , 1973 .

[11]  M. Bos.  An online computer method for the potentiometric titration of mixtures of a strong and a weak acid , 1977 .

[12]  Stephen R. Lowry,et al.  Comparison of various K-nearest neighbor voting schemes with the self-training interpretive and retrieval system for identifying molecular substructures from mass spectral data , 1977 .

[13]  B. H. Campbell,et al.  Titrimetric applications of multiparametric curve-fitting: Part II. Potentiometric titration with an unstandardized reagent , 1974 .

[14]  Thomas L. Isenhour,et al.  Computerized learning machines applied to chemical problems. Multicategory pattern classification by least squares , 1969 .