An improved machine learning technique based on downsized KPCA for Alzheimer's disease classification

Alzheimer's disease (AD), a neurodegenerative disorder, is a very serious illness that cannot be cured, but the early diagnosis allows precautionary measures to be taken. The current used methods to detect Alzheimer's disease are based on tests of cognitive impairment, which does not provide an exact diagnosis before the patient passes a moderate stage of AD. In this article, a novel classifier of brain magnetic resonance images (MRI) based on the new downsized kernel principal component analysis (DKPCA) and multiclass support vector machine (SVM) is proposed. The suggested scheme classifies AD MRIs. First, a multiobjective optimization technique is used to determine the optimal parameter of the kernel function in order to ensure good classification results and to minimize the number of retained principle components simultaneously. The optimal parameter is used to build the optimized DKPCA model. Second, DKPCA is applied to normalized features. Downsized features are then fed to the classifier to output the prediction. To validate the effectiveness of the proposed method, DKPCA was tested using synthetic data to demonstrate its efficiency on dimensionality reduction, then the DKPCA based technique was tested on the OASIS MRI database and the results were satisfactory compared to conventional approaches.     

The calculation of band gap energy in zinc oxide films

We investigated the optical properties of undoped zinc oxide thin films as the n-type semiconductor; the thin films were deposited at different precursor molarities by ultrasonic spray and spray pyrolysis techniques. The thin films were deposited at different substrate temperatures ranging between 200 and 500 ℃. In this paper, we present a new approach to control the optical gap energy of ZnO thin films by concentration of the ZnO solution and substrate temperatures in a cost-effective way. The model proposed to calculate the band gap energy with the Urbach energy was investigated. The relation between the experimental data and theoretical calculation suggests that the band gap energies are predominantly estimated by the Urbach energies, film transparency, and concentration of the ZnO solution and substrate temperatures. The measurements by these proposal models are in qualitative agreements with the experimental data; the correlation coefficient values were varied in the range 0.96-0.99999, indicating high quality representation of data based on Equation (2), so that the relative errors of all calculation are smaller than 4%. Thus, one can suppose that the undoped ZnO thin films are chemically purer and have many fewer defects and less disorder owing to an almost complete chemical decomposition and contained higher optical band gap energy.     

Design and comparative study of online kernel methods identification of nonlinear system in RKHS space

This paper proposes the design and a comparative study of two proposed online kernel methods identification in the reproducing kernel Hilbert space and other two kernel method existing in the literature. The two proposed methods, titled SVD-KPCA, online RKPCA. The two other techniques named Sliding Window Kernel Recursive Least Square and the Kernel Recursive Least Square. The considered performances are the Normalized Means Square Error, the consumed time and the numerical complexity. All methods are evaluated by handling a chemical process known as the Continuous Stirred Tank Reactor and Wiener-Hammerstein benchmark.     

Study on the correlation between crystallite size–optical gap energy and precursor molarities of ZnO Thin FilmsS. Benramachea,*, O. Belahssena, A. Guettafb and A. Arif b

We investigated the structural and optical properties of ZnO thin films as an n-type semiconductor. The films were deposited at different precursor molarities using an ultrasonic spray method. In this paper we focused our attention on a new approach describing a correlation between the crystallite size and optical gap energy with the precursor molarity of ZnO thin films. The results show that the X-ray diffraction （XRD） spectra revealed a preferred orientation of the crystallites along the c-axis. The maximum value of the crystallite size of the films is 63.99 nm obtained at 0.1 M. The films deposited with 0.1 M show lower absorption within the visible wavelength region. The optical gap energy increased from 3.08 to 3.37 eV with increasing precursor molarity of 0.05 to 0.1 M. The correlation between the structural and optical properties with the precursor molarity suggests that the crystallite size of the films is predominantly influenced by the band gap energy and the precursor molarity. The measurement of the crystallite size by the model proposed is equal to the experimental data. The minimum error value was estimated by Eq. （4） in the higher crystallinity.     

Effect of heat treatments on structural,microstructural and mechanical properties of Al 2017 alloy

The effect of ageing at 300°C before and after quenched at two temperatures of 180 and 280°C on the Al 2017 alloy was studied. The structural properties were investigated using X-ray diffraction; the microstructural evolution was investigated using scanning electron microscopy and microhardness measurement for the mechanical properties. After various states of ageing, the Al–Cu–Fe alloy shows significant changes in the microstructure and mechanical behavior. After ageing, the microstructure of the matrix consisted of a three solid solution of α-Al–Cu-Fe, β-AlFe and θ-A2Cu phases precipitations. After two-step heat treatment (quenching and ageing), the alloy reveals the formation of β and θ phases precipitates. After ageing at 300°C of original sample, the alloy reveals higher β precipitates, corresponding to the minimum value of microhardness, the volume fraction of this precipitates becomes higher. On the other hand, the TTT curves for the discontinuous and continuous precipitation reaction in this alloy have been suggested.     

Online identification of nonlinear system using reduced kernel principal component analysis

The Principal Component Analysis (PCA) is a powerful technique for extracting structure from possibly high-dimensional data sets. It is readily performed by solving an eigenvalue problem, or by using iterative algorithms that estimate principal components. This paper proposes a new method for online identification of a nonlinear system modelled on Reproducing Kernel Hilbert Space (RKHS). Therefore, the PCA technique is tuned twice, first we exploit the Kernel PCA (KPCA) which is a nonlinear extension of the PCA to RKHS as it transforms the input data by a nonlinear mapping into a high-dimensional feature space to which the PCA is performed. Second, we use the Reduced Kernel Principal Component Analysis (RKPCA) to update the principal components that represent the observations selected by the KPCA method.