Matematik Bölümü Yayın Koleksiyonu

Permanent URI for this collectionhttps://hdl.handle.net/20.500.12416/413

Browse

Filters

2001 - 200922020 - 20231

Settings

Subject: search.filters.subject.Principal Component Analysis

Search Results

Now showing 1 - 3 of 3
  • Article
    Citation - Scopus: 7
    COVID-19 Classification Using Hybrid Deep Learning and Standard Feature Extraction Techniques
    (Institute of Advanced Engineering and Science, 2023) El Shenbary, H. A.; Ebeid, Ebeid Ali; Baleanu, Dumitru I.
    There is no doubt that COVID-19 disease rapidly spread all over the world, and effected the daily lives of all of the people. Nowadays, the reverse transcription polymerase chain reaction is the most way used to detect COVID-19 infection. Due to time consumed in this method and material limitation in the hospitals, there is a need for developing a robust decision support system depending on artificial intelligence (AI) techniques to recognize the infection at an early stage from a medical images. The main contribution in this research is to develop a robust hybrid feature extraction method for recognizing the COVID-19 infection. Firstly, we train the Alexnet on the images database and extract the first feature matrix. Then we used discrete wavelet transform (DWT) and principal component analysis (PCA) to extract the second feature matrix from the same images. After that, the desired feature matrices were merged. Finally, support vector machine (SVM) was used to classify the images. Training, validating, and testing of the proposed method were performed. Experimental results gave (97.6%, 98.5%) average accuracy rate on both chest X-ray and computed tomography (CT) images databases. The proposed hybrid method outperform a lot of standard methods and deep learning neural networks like Alexnet, Googlenet and other related methods. © 2022 Elsevier B.V., All rights reserved.
  • Article
    Citation - WoS: 2
    Citation - Scopus: 3
    An Application of Principal Component Analysis - Artificial Neural Network for the Simultaneous Quantitative Analysis of a Binary Mixture System
    (Chiminform Data S A, 2009) Dinc, Erdal; Baleanu, Dumitru; Sen Koktas, Nigar; Köktaş, Nigar; Baleanu, Dumitru; Kökias, Nigar Şen; Matematik
    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.
  • Article
    Citation - WoS: 34
    Chemometric Quantitative Analysis of Pyridoxine Hcl and Thiamine Hcl in a Vitamin Combination by Principal Component Analysis, Classical Least Squares, and Inverse Least Squares Techniques
    (Marcel dekker inc, 2001) Baleanu, D; Onur, F; Dinç, E
    Three chemometric techniques were described for the analysis of pyridoxine hydrochloride and thiamine hydrochloride within a vitamin combination in the presence of spectral interferences. For these techniques, the training set was prepared by using synthetic mixtures containing two vitamins in multiple possible combinations for the range of 8-40 mu /mL in 0.1 M HCl. The absorbance values for the training set were obtained by direct measurements at 18 wavelengths in the region 222-305 nm for the zero order spectra. The numerical values were calculated by using the 'Maple V' software. Mean recoveries and relative standard deviations for the principal component analysis, classical least squares and inverse least squares techniques were found as 100.7% and 0.95%; 100.5% and 1.38% and, 99.3% and 1.04 for pyridoxine hydrochloride; and 99.7% and 1.03%; 99.1% and 1.05% and, 99.6% and 1.58% for thiamine hydrochloride, respectively. These three chemometric techniques were successfully applied to vitamin tablets marketed in Turkey. The results were compared with each other and good coincidence was observed.