Browsing by Author "Halachev P."
Now showing 1 - 2 of 2
Results Per Page
Sort Options
Item Methods and algorithms of optimization in computer engineering: review and comparative analysis Métodos y algoritmos de optimización en ingeniería informática: revisión y análisis comparativo(2024-02-08) Yakhno V.; Kolumbet V.; Halachev P.; Khambir V.; Ivanenko R.Introduction: the main areas of application of artificial intelligence for algorithmic analysis and optimization of information flows in tasks of multiparametric diagnostics by means of computer engineering are considered. The issues of globalization of all areas of humanitarian, scientific, technical and engineering activities of human society are considered. It is noted that the common denominator of all directions is information flows. The main tools for their management and algorithmic analysis are multi-parametric methods of artificial intelligence. Method: one of its most relevant areas has been highlighted-the use of evolutionary algorithms in combination with modern diagnostic systems based on computer engineering. The possibility of using intelligent analysis of data from biophysical laser systems in assessing the state of “living matter”-the biological media of the human body-is considered. Results: through algorithmic optimization, a set of new cancer detection markers was determined: the statistical parameters of optical anisotropy maps wavelet coefficients linear distributions-the differences between these markers lie in the range from 4 to 20 times; the asymmetry of the wavelet coefficients autocorrelation function-the differences between these markers lie within two orders of magnitude; for normal state, the wavelet coefficients distributions are multifractal; for prostate cancer, the distributions of the wavelet amplitude coefficients are multifractal. Conclusions: a comparative study of the algorithmic optimization of differences of cancer through the use of multiparametric statistical, correlational, fractal and wavelet analysis of polarization tomograms of optical anisotropy of blood layers of donors and prostate cancer sicks is presented.Item Prediction of e-learning efficiency by neural networks(2012-01-01) Halachev P.A model for prediction of the outcome indicators of e-Learning, based on Balanced ScoreCard (BSC) by Neural Networks (NN) is proposed. In the development of NN models the problem of a small sample size of the data arises. In order to reduce the number of variables and increase the examples of the training sample, preprocessing of the data with the help of the methods Interpolation and Principal Component Analysis (PCA) is performed. A method for optimizing the structure of the neural network is applied over linear and nonlinear neural network architectures. The highest accuracy of prognosis is obtained applying the method of Optimal Brain Damage (OBD) over the nonlinear neural network. The efficiency and applicability of the method suggested is proved by numerical experiments on the basis of real data.