The Application Of Support Vector Machine In Multivariate Cablibration, Quantitative Structure-Activity Relationships And Chemical Pattern Recognition

Chemometrics, combines mathmatics,statistics and computer sciences, has stronge ability of dealing with the data of chemical experiment. Support vector machine (SVM) has solid theoretical foundation and can deal with small dataset, nonlinear optimization, high-dimensional feature space, local minimization and other realistic problems. So it was an area of intense research in late 1990s. Along with the development of SVM, some derived algorithms have been put forward and the application of SVM has gradually been the hot point for researchers in the world. Today, SVM has been successfully applied in face recognition, voice identification, handwritten digit recognition, text classification, risk assessment, protein structure recognition, gene recognition and other pattern recognition domains and achieves equivalent or superior results compared to those obtained by some other methods, such as Artificial neutral networks (ANNs) which have been widely used in chemometrics and analytical chemistry. It is very exciting that their capability to generalize input-output mapping from a limited set of training examples is great. In this paper, we use SVM to solve the problems of determining mixture, to establish relations of quantity and to classify the spectrums of heavy metal atom:We use SVM to determing mixtures, such as metal element, rutin and ascorbic, amino-acids simultaneously by informations from the mix spectrograms of Spectrophotometry and Raman without pre-separation. The results are that SVM can well deal with such mixture and it gains more accuracy information than BPN.We use SVM to classify the unknown energy levels of heavy metal, such as Cm II,Pu I,U I which can not be classified by experiment. Although some people have tried to use traditional chemometric techniques to predict the unknown energy levels, there still have some samples which can not be predicted. So we use SVM to deal with such heavy metal to gain the energy levels. The results show that SVM predict more accuracy and completely than traditional methods of chemometrics.We use SVM to build relationship between inhibition performace of amino-acids and quantum chemical parameter of amino-acids. The results show the new way to explain the principle of inhibition of amino-acid, and show people a easier technique to choose a better corrosion inhibitor from large number of amino-acids.