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 achieves (4.81) dB GNSDR gain, (7.28) dB GSIR gain, and (3.39) dB GSAR gain in comparison to current approaches
In the knowledge society, artificial intelligence (AI) forms a cornerstone of global education. This quasi-experimental study examines the impact of an Intelligent Adaptive Learning Strategy (IALS) on flexible thinking (FT) and academic achievement among 60 3rd-year undergraduate students at the College of Education/University of Baghdad (experimental n = 30; control n = 30). The IALS was implemented via an AI-supported educational platform, while the control group received conventional instruction. Post-test intervention assessments included an FT test (10 items, content validity = 0.89, Cronbach’s α = 0.87) and an achievement test (10 objective items, α = 0.85). Results revealed statistically significant superiority of the exp
... Show MoreAccurate prediction of river water quality parameters is essential for environmental protection and sustainable agricultural resource management. This study presents a novel framework for estimating potential salinity in river water in arid and semi‐arid regions by integrating a kernel extreme learning machine (KELM) with a boosted salp swarm algorithm based on differential evolution (KELM‐BSSADE). A dataset of 336 samples, including bicarbonate, calcium, pH, total dissolved solids and sodium adsorption ratio, was collected from the Idenak station in Iran and was used for the modelling. Results demonstrated that KELM‐BSSADE outperformed models such as deep random vector funct
The present work reports on the performance of three types of nanofiltration membranes in the removal of highly polluting and toxic lead (Pb2+) and cadmium (Cd2+) from single and binary salt aqueous solutions simulating real wastewaters. The effect of the operating variables (pH (5.5-6.5), types of NF membrane and initial ions concentration (10-250 ppm)) on the separation process and water flux was investigated. It was observed that the rejection efficiency increased with increasing pH of solution and decreasing the initial metal ions concentrations. While the flux decreased with increasing pH of solution and increasing initial metal ions concentrations. The maximum rejection of lead and cadmium ion
... Show MoreSix proposed simply supported high strength-steel fiber reinforced concrete (HS-SFRC) beams reinforced with FRP (fiber reinforced polymer) rebars were numerically tested by finite element method using ABAQUS software to investigate their behavior under the flexural failure. The beams were divided into two groups depending on their cross sectional shape. Group A consisted of four trapezoidal beams with dimensions of (height 200 mm, top width 250 mm, and bottom width 125 mm), while group B consisted of two rectangular beams with dimensions of (125 ×200) mm. All specimens have same total length of 1500 mm, and they were also considered to be made of same high strength concrete designed material with 1% volume fraction of steel fiber.
... Show MoreSpeech is the essential way to interact between humans or between human and machine. However, it is always contaminated with different types of environment noise. Therefore, speech enhancement algorithms (SEA) have appeared as a significant approach in speech processing filed to suppress background noise and return back the original speech signal. In this paper, a new efficient two-stage SEA with low distortion is proposed based on minimum mean square error sense. The estimation of clean signal is performed by taking the advantages of Laplacian speech and noise modeling based on orthogonal transform (Discrete Krawtchouk-Tchebichef transform) coefficients distribution. The Discrete Kra
Image retrieval is used in searching for images from images database. In this paper, content – based image retrieval (CBIR) using four feature extraction techniques has been achieved. The four techniques are colored histogram features technique, properties features technique, gray level co- occurrence matrix (GLCM) statistical features technique and hybrid technique. The features are extracted from the data base images and query (test) images in order to find the similarity measure. The similarity-based matching is very important in CBIR, so, three types of similarity measure are used, normalized Mahalanobis distance, Euclidean distance and Manhattan distance. A comparison between them has been implemented. From the results, it is conclud
... Show MoreNurse scheduling problem is one of combinatorial optimization problems and it is one of NP-Hard problems which is difficult to be solved as optimal solution. In this paper, we had created an proposed algorithm which it is hybrid simulated annealing algorithm to solve nurse scheduling problem, developed the simulated annealing algorithm and Genetic algorithm. We can note that the proposed algorithm (Hybrid simulated Annealing Algorithm(GS-h)) is the best method among other methods which it is used in this paper because it satisfied minimum average of the total cost and maximum number of Solved , Best and Optimal problems. So we can note that the ratios of the optimal solution are 77% for the proposed algorithm(GS-h), 28.75% for Si
... Show More