Monaural source separation is a challenging issue due to the fact that there is only a single channel available; however, there is an unlimited range of possible solutions. In this paper, a monaural source separation model based hybrid deep learning model, which consists of convolution neural network (CNN), dense neural network (DNN) and recurrent neural network (RNN), will be presented. A trial and error method will be used to optimize the number of layers in the proposed model. Moreover, the effects of the learning rate, optimization algorithms, and the number of epochs on the separation performance will be explored. Our model was evaluated using the MIR-1K dataset for singing voice separation. Moreover, the proposed approach achi

    Feature selection represents one of the critical processes in machine learning (ML). The fundamental aim of the problem of feature selection is to maintain performance accuracy while reducing the dimension of feature selection. Different approaches were created for classifying the datasets. In a range of optimization problems, swarming techniques produced better outcomes. At the same time, hybrid algorithms have gotten a lot of attention recently when it comes to solving optimization problems. As a result, this study provides a thorough assessment of the literature on feature selection problems using hybrid swarm algorithms that have been developed over time (2018-2021). Lastly, when compared with current feature selection procedu

Abstract 

For sparse system identification,recent suggested algorithms are  -norm Least Mean Square (  -LMS), Zero-Attracting LMS (ZA-LMS), Reweighted Zero-Attracting LMS (RZA-LMS), and p-norm LMS (p-LMS) algorithms, that have modified the cost function of the conventional LMS algorithm by adding a constraint of coefficients sparsity. And so, the proposed algorithms are named  -ZA-LMS, 

In this work , a hybrid scheme tor Arabic speech for the recognition

of  the speaker  verification  is presented  . The scheme is hybrid as utilizes the traditional digi tal signal processi ng and neural network . Kohonen neural  network has been used as a recognizer  tor speaker verification after extract spectral  features from an acoustic signal  by Fast Fourier Transformation Algorithm(FFT) .

The system was im plemented using a PENTIUM  processor , I000

MHZ compatible and MS-dos 6.2 .

This paper introduces a non-conventional approach with multi-dimensional random sampling to solve a cocaine abuse model with statistical probability. The mean Latin hypercube finite difference (MLHFD) method is proposed for the first time via hybrid integration of the classical numerical finite difference (FD) formula with Latin hypercube sampling (LHS) technique to create a random distribution for the model parameters which are dependent on time [Formula: see text]. The LHS technique gives advantage to MLHFD method to produce fast variation of the parameters’ values via number of multidimensional simulations (100, 1000 and 5000). The generated Latin hypercube sample which is random or non-deterministic in nature is further integ

This paper presents a hybrid approach called Modified Full Bayesian Classifier (M-FBC) and Artificial Bee Colony (MFBC-ABC) for using it to medical diagnosis support system. The datasets are taken from Iraqi hospitals, these are for the heart diseases and the nervous system diseases. The M-FBC is depended on common structure known as naïve Bayes. The structure for network is represented by D-separated for structure's variables. Each variable has Condition Probability Tables (CPTs) and each table for disease has Probability. The ABC is easy technique for implementation, has fewer control parameters and it could be easier than other swarm optimization algorithms, so that hybrid with other algorithms to reach the optimal structure. In the

Feature selection (FS) constitutes a series of processes used to decide which relevant features/attributes to include and which irrelevant features to exclude for predictive modeling. It is a crucial task that aids machine learning classifiers in reducing error rates, computation time, overfitting, and improving classification accuracy. It has demonstrated its efficacy in myriads of domains, ranging from its use for text classification (TC), text mining, and image recognition. While there are many traditional FS methods, recent research efforts have been devoted to applying metaheuristic algorithms as FS techniques for the TC task. However, there are few literature reviews concerning TC. Therefore, a comprehensive overview was systematicall

This paper has the interest of finding the approximate solution (APPS) of a nonlinear variable coefficients hyperbolic boundary value problem (NOLVCHBVP).  The given boundary value problem is written in its discrete weak form (WEFM) and proved  have a unique solution, which is obtained via the mixed Galerkin finite element with implicit method that reduces the problem to solve the Galerkin nonlinear algebraic system  (GNAS). In this part, the predictor and the corrector techniques (PT and CT, respectively) are proved at first convergence and then are used to transform  the obtained GNAS to a linear GLAS . Then the GLAS is solved using the Cholesky method (ChMe). The stability and the convergence of the method are stud

In this work, silicon nitride (Si₃N₄) thin films were deposited on metallic substrates (aluminium and titanium sheets) by the DC reactive sputtering technique using two different silicon targets (n-type and p-type Si wafers) as well as two Ar:N₂ gas mixing ratios (50:50 and 70:30). The electrical conductivity of the metallic (aluminium and titanium) substrates was measured before and after the deposition of silicon nitride thin films on both surfaces of the substrates. The results obtained from this work showed that the deposited films, in general, reduced the electrical conductivity of the substrates, and the thin films prepared from n-type silicon targets using a 50:50 mixing ratio and deposited on both

The aim of present work is to improve mechanical and fatigue properties for Aluminum alloy7049 by using Nano composites technique. The ZrO₂ with an average grain diameter of 30-40 nm, was selected as Nano particles, to reinforce Aluminum alloy7049 with different percentage as, 2, 4, 6 and 7 %. The Stir casting method was used to fabricate the Nano composites materials due to economical route for improvement and processing of metal matrix composites. The experimental results were shown that the adding of zirconium oxide (ZrO₂) as reinforced material leads to improve mechanical properties. The best percentage of improvement of mechanical properties of 7049 AA was with 4% wt. of ZrO₂ about (7.76% ) for ultim