The main reason for the emergence of a deepfake (deep learning and fake) term is the evolution in artificial intelligence techniques, especially deep learning. Deep learning algorithms, which auto-solve problems when giving large sets of data, are used to swap faces in digital media to create fake media with a realistic appearance. To increase the accuracy of distinguishing a real video from fake one, a new model has been developed based on deep learning and noise residuals. By using Steganalysis Rich Model (SRM) filters, we can gather a low-level noise map that is used as input to a light Convolution neural network (CNN) to classify a real face from fake one. The results of our work show that the training accuracy of the CNN model

Image pattern classification is considered a significant step for image and video processing. Although various image pattern algorithms have been proposed so far that achieved adequate classification, achieving higher accuracy while reducing the computation time remains challenging to date. A robust image pattern classification method is essential to obtain the desired accuracy. This method can be accurately classify image blocks into plain, edge, and texture (PET) using an efficient feature extraction mechanism. Moreover, to date, most of the existing studies are focused on evaluating their methods based on specific orthogonal moments, which limits the understanding of their potential application to various Discrete Orthogonal Moments (DOM

The need for participants’ performance assessments in academia and industry has been a growing concern. It has attendance, among other metrics, is a key factor in engendering a holistic approach to decision-making. For institutions or organizations where managing people is an important yet challenging task, attendance tracking and management could be employed to improve this seemingly time-consuming process while keeping an accurate attendance record. The manual/quasi-analog approach of taking attendance in some institutions could be unreliable and inefficient, leading to inaccurate computation of attendance rates and data loss. This work, therefore, proposes a system that employs embedded technology and a biometric/ w

Abstract 

Locally natural occurring Iraqi rocks of Bauxite and Porcelanite (after pre calcinations at 1000^oC for 1hr) were used, with the addition of different proportions of MgO and Al₂O₃, to prepare refractory materials. The effects of these additives on the physical and thermal properties of the prepared refractories were investigated.

Many batches of Bauxite/MgO, Bauxite/Al₂O₃, Bauxite/MgO/Al₂O₃, and   Porcelanite/ MgO/Al₂O₃ were prepared. The mixture is milled and classified into different size fractions; fine (less than 45μm) 40%, middle (45-75μm) 40%, and coarse (75-106μm) 20% .

BP algorithm is the most widely used supervised training algorithms for multi-layered feedforward neural net works. However, BP takes long time to converge and quite sensitive to the initial weights of a network. In this paper, a modified cuckoo search algorithm is used to get the optimal set of initial weights that will be used by BP algorithm. And changing the value of BP learning rate to improve the error convergence. The performance of the proposed hybrid algorithm is compared with the stan dard BP using simple data sets. The simulation result show that the proposed algorithm has improved the BP training in terms of quick convergence of the solution depending on the slope of the error graph.

In this paper, a compact genetic algorithm (CGA) is enhanced by integrating its selection strategy with a steepest descent algorithm (SDA) as a local search method to give I-CGA-SDA. This system is an attempt to avoid the large CPU time and computational complexity of the standard genetic algorithm. Here, CGA dramatically reduces the number of bits required to store the population and has a faster convergence. Consequently, this integrated system is used to optimize the maximum likelihood function lnL(φ1, θ1) of the mixed model. Simulation results based on MSE were compared with those obtained from the SDA and showed that the hybrid genetic algorithm (HGA) and I-CGA-SDA can give a good estimator of (φ1, θ1) for the ARMA(1,1) model. Anot

This study uses an environmentally friendly and low-cost synthesis method to manufacture zinc oxide nanoparticles (ZnO NPs) by using zinc sulfate. Eucalyptus leaf extract is an effective chelating and capping agent for synthesizing ZnO NPs. The structure, morphology, thermal behavior, chemical composition, and optical properties of ZnO nanoparticles were studied utilizing FT-IR, FE-SEM, EDAX, AFM, and Zeta potential analysis. The FE-SEM pictures confirmed that the ZnO NPs with a size range of (22-37) nm were crystalline and spherical. Two methods were used to prepare ZnO NPs. The first method involved calcining the resulting ZnO NPs, while the second method did not. The prepared ZnO NPs were used as adsorbents for removing acid black 210

Multiple eliminations (de-multiple) are one of seismic processing steps to remove their effects and delineate the correct primary refractors. Using normal move out to flatten primaries is the way to eliminate multiples through transforming these data to frequency-wavenumber domain. The flatten primaries are aligned with zero axis of the frequency-wavenumber domain and any other reflection types (multiples and random noise) are distributed elsewhere. Dip-filter is applied to pass the aligned data and reject others will separate primaries from multiple after transforming the data back from frequency-wavenumber domain to time-distance domain. For that, a suggested name for this technique as normal move out- frequency-wavenumber domain