Deep learning convolution neural network has been widely used to recognize or classify voice. Various techniques have been used together with convolution neural network to prepare voice data before the training process in developing the classification model. However, not all model can produce good classification accuracy as there are many types of voice or speech. Classification of Arabic alphabet pronunciation is a one of the types of voice and accurate pronunciation is required in the learning of the Qur’an reading. Thus, the technique to process the pronunciation and training of the processed data requires specific approach. To overcome this issue, a method based on padding and deep learning convolution neural network is proposed to

A nonlinear filter for smoothing color and gray images
corrupted by Gaussian noise is presented in this paper. The proposed
filter designed to reduce the noise in the R,G, and B bands of the
color images and preserving the edges. This filter applied in order to
prepare images for further processing such as edge detection and
image segmentation.
The results of computer simulations show that the proposed
filter gave satisfactory results when compared with the results of
conventional filters such as Gaussian low pass filter and median filter
by using Cross Correlation Coefficient (ccc) criteria.

A variety of single-engine driven files and inematics have been introduced to improve the clinical performance of NiTi rotary files. The purpose of this in vitro study was to measure and compare the incidence of dentinal defects after root canal preparation with different single file systems.

It is important that real time stability in smart grids is ensured as the integration of renewables and the complexity of the systems grows. In this paper, we provide a solid architecture, which combines a Residual CNNLSTM deep neural network predictor, FPGA-accelerated Model Predictive Control (MPC), and SHAP-based explainability. The proposed method predicted with 99.8% accuracy using the Electrical grid Stability Simulated Dataset (UCI) and minimized the instability rates surpassing 85 percent in all operating conditions. Meeting real-time operating needs, FPGA deployment on a Xilinx Zynq UltraScale+ provided 3.1 ms latency and 5 times reduced energy consumption against CPU processing. By emphasizing bus voltage and frequency as major in

Abstract The wavelet shrink estimator is an attractive technique when estimating the nonparametric regression functions, but it is very sensitive in the case of a correlation in errors. In this research, a polynomial model of low degree was used for the purpose of addressing the boundary problem in the wavelet reduction in addition to using flexible threshold values in the case of Correlation in errors as it deals with those transactions at each level separately, unlike the comprehensive threshold values that deal with all levels simultaneously, as (Visushrink) methods, (False Discovery Rate) method, (Improvement Thresholding) and (Sureshrink method), as the study was conducted on real monthly data represented in the rates of theft crimes f

In this work, a local sunflower husk (SFH) was used as a natural surface for removing Basic Green-4 (BG4) dye, as a watersoluble pollutant. The effect of initial concentration, contact time, the mass of surface of the dye with the SFH as well as the medium temperature was studied. The application of Langmuir, Freundlich isotherms on the collected data of the adsorption process found to harmonize to Freundlich equation more than that of Langmuir. However, the adsorbed mass of BG4 dye showed a direct increase with the increase of SFH mass and equilibrium was achieved within a 60min window. The interaction of BG4 with SFH surface was spontaneous and exothermic. The empirical kinetic outcomes at ambient temperatures were applied to pseudo 1st a

In this study used three methods such as Williamson-hall, size-strain Plot, and Halder-Wagner to analysis x-ray diffraction lines to determine the crystallite size and the lattice strain of the nickel oxide nanoparticles and then compare the results of these methods with two other methods. The results were calculated for each of these methods to the crystallite size are (0.42554) nm, (1.04462) nm, and (3.60880) nm, and lattice strain are (0.56603), (1.11978), and (0.64606) respectively were compared with the result of Scherrer method (0.29598) nm,(0.34245),and the Modified Scherrer (0.97497). The difference in calculated results Observed for each of these methods in this study.

Healthcare professionals routinely use audio signals, generated by the human body, to help diagnose disease or assess its progression. With new technologies, it is now possible to collect human-generated sounds, such as coughing. Audio-based machine learning technologies can be adopted for automatic analysis of collected data. Valuable and rich information can be obtained from the cough signal and extracting effective characteristics from a finite duration time interval that changes as a function of time. This article presents a proposed approach to the detection and diagnosis of COVID-19 through the processing of cough collected from patients suffering from the most common symptoms of this pandemic. The proposed method is based on adopt