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

The Mauddud reservoir, Khabaz oil field which is considered one of the main carbonate reservoirs in the north of Iraq. Recognizing carbonate reservoirs represents challenges to engineers because reservoirs almost tend to be tight and overall heterogeneous. The current study concerns with geological modeling of the reservoir is an oil-bearing with the original gas cap. The geological model is establishing for the reservoir by identifying the facies and evaluating the petrophysical properties of this complex reservoir, and calculate the amount of hydrocarbon. When completed the processing of data by IP interactive petrophysics software, and the permeability of a reservoir was calculated using the concept of hydraulic units then, there

Machine learning models have recently provided great promise in diagnosis of several ophthalmic disorders, including keratoconus (KCN). Keratoconus, a noninflammatory ectatic corneal disorder characterized by progressive cornea thinning, is challenging to detect as signs may be subtle. Several machine learning models have been proposed to detect KCN, however most of the models are supervised and thus require large well-annotated data. This paper proposes a new unsupervised model to detect KCN, based on adapted flower pollination algorithm (FPA) and the k-means algorithm. We will evaluate the proposed models using corneal data collected from 5430 eyes at different stages of KCN severity (1520 healthy, 331 KCN1, 1319 KCN2, 1699 KCN3 a

In present work the effort has been put in finding the most suitable color model for the application of information hiding in color images. We test the most commonly used color models; RGB, YIQ, YUV, YCbCr1 and YCbCr2. The same procedures of embedding, detection and evaluation were applied to find which color model is most appropriate for information hiding. The new in this work, we take into consideration the value of errors that generated during transformations among color models. The results show YUV and YIQ color models are the best for information hiding in color images.

These days, the world is facing a global environmental and sustainability problem due to the increasing generation of large amounts of waste through construction and demolition work, which causes a serious problem for the environment. Therefore, this research was conducted to get rid of the waste disposal problems, including old glass and concrete, which were used as recycled fine aggregates. Seven different mixtures were prepared. The first mixture was with the used sand, which is glass sand, and it was adopted as a reference mixture (ORPC), and three mixtures were prepared for each of the recycled materials (waste concrete and glass) and partially replaced by glass sand in different proportions (25, 50, and 75) %. Some

A new methodology was applied to the synthesis of new imidazolones and oxyazepine derivatives containing imidazo thiazole fused rings. Starting with 5-(4-bromo phenyl) imidazo (2, 1-b) thiazole, which was synthesized using the standard procedure, the Carbaldehyed group was introduced at position 6 of 5-(4-bromo phenyl) imidazo (2, 1-b) thiazole. Then, this 6-carbaldehyed derivative was condensed with different substituted aromatic amines to afford new Schiff bases. The latter were cyclized into new oxazepine and imidazolone derivatives by using phthalic anhydride and glycine, respectively. These new derivatives were characterized by using FT-IR, 1HHNMR, and 13CNMR spectra, as well as examined (evaluated) for anti-bacterial and anti-fungal a