An Application of Principal Component Analysis - Artificial Neural Network for the Simultaneous Quantitative Analysis of a Binary Mixture System

DİNÇ E., Sen Koktas N., BALEANU D.

REVISTA DE CHIMIE, cilt.60, sa.7, ss.662-665, 2009 (SCI-Expanded) identifier identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 60 Sayı: 7
  • Basım Tarihi: 2009
  • Dergi Adı: REVISTA DE CHIMIE
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Sayfa Sayıları: ss.662-665
  • Anahtar Kelimeler: artificial neural networks, principal component analysis, atorvastatin, amlodipine, CONTINUOUS WAVELET TRANSFORM, DIVISOR-RATIO SPECTRA, SPECTROPHOTOMETRIC DETERMINATION, ACETYLSALICYLIC-ACID, ASCORBIC-ACID, ATORVASTATIN, AMLODIPINE, PARACETAMOL, REGRESSION, TABLETS
  • Ankara Üniversitesi Adresli: Evet

Özet

Artificial neural networks (ANNs) based on the use of principal components and the original absorbance data were proposed for the simultaneous quantitative analysis of amlodipine (AML) and atorvastatin (ATO) in tablets. A concentration set of mixtures containing ATO and AML in different concentration composition between 0.0-20.0 mu g/mL was prepared in methanol. The measured absorbance data matrix for the concentration data set was obtained and the principal components were extracted. In the next step five principal components were selected as an input data for the artificial neural network. This combined approach was named principal components-artificial neural network (PCA-ANN). The same problem was solved by using the application of the artificial neural network to the original absorbance data matrix. This approach was denoted as ANN. The classical ANN approach was used as a comparison method. Both PCA-ANN and ANN methods were tested by analyzing various synthetic mixtures corresponding to the validation set of AML and ATO compounds. The proposed methods were successfully applied to the quantitative analysis of the commercial tablets and a coincidence was reported between the proposed methods.