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
Pilot-scale dead end microfiltration membranes were carried out to determine the feasibility of the process for treating the oily wastewater which discharge from some Iraqi factories such as power station of south of Baghdad and the general company of petrochemical industries. Polypropylene membranes (cylindrical shape) with different pore diameters (1 and 5 micron) were used to conduct the study on micromembrane process. The variables studied are oil concentration (100 – 1000 ppm), feed flow rate (20 – 40 l/h), operating temperature (31 – 50°C) and time (0 – 3 h). It was found that the flux increases with increasing feed flow rate, temperature and pore size of membrane, and decreases with increasing oil concentration and operating
... Show MoreThe expressive discourse, in the form of the rural singing, is considered one of the interactive framework and the metaphorical dialogues in creating the aesthetic climate that connects the circles of its basic elements, singing, playing music, expression, costumes, sham movements and so forth.
The rhetorical language in this field includes all those parts and turns them into an integrated idea within the culture of the musical science, specifically the heart of the rural singing. This research dealt with a number of topics of relevance in the expressive discourse for the form of the rural singing. The first chapter consists of the methodological framework of the research, represented by the r
... Show MoreAbstract The purpose of this study, teach the art of performing Olympic lifts (snatch and, clean and jerk) using the two methods are instructional (self-learning associated with the model) and (reverse style of partial way). Identify the effectiveness of these methods in learning the art of performance and style of the best Olympic lifting in the learning and retention of novice for Olympic lifts. The research sample consisted of 16 lifters were selected purposively representing specialist center for the care of athletic talent to weightlifting for ages 14 years. The sample was divided into two experimental, Each group (8) eight weightlifters. The experimental group used the style of the first self-learning associated with the m
... Show MoreThe aim of this study was to identify the effectiveness of using generative learning model in learning kinetic series on rings and horizontal bar in artistic gymnastics for men ,Also, the two groups were better in learning the two series of movements on the rings and horizontal bar . The experimental method was used to design two parallel groups with pretested and posttest .The sample included third graders at the College of Physical Education and Sports Sciences - University of Baghdad ,The third class (d) was chosen to represent the control group that applied the curriculum in the college, with (12) students per group. After conducting the tribal tests, the main experiment was carried out for (8) weeks at the rate of two units per week di
... Show More— To identify the effect of deep learning strategy on mathematics achievement and practical intelligence among secondary school students during the 2022/2023 academic year. In the research, the experimental research method with two groups (experimental and control) with a post-test were adopted. The research community is represented by the female students of the fifth scientific grade from the first Karkh Education Directorate. (61) female students were intentionally chosen, and they were divided into two groups: an experimental group (30) students who were taught according to the proposed strategy, and a control group (31) students who were taught according to the usual method. For the purpose of collecting data for the experimen
... Show MoreIn this study, we fabricated nanofiltration membranes using the electrospinning technique, employing pure PAN and a mixed matrix of PAN/HPMC. The PAN nanofibrous membranes with a concentration of 13wt% were prepared and blended with different concentrations of HPMC in the solvent N, N-Dimethylformamide (DMF). We conducted a comprehensive analysis of these membranes' surface morphology, chemical composition, wettability, and porosity and compared the results. The findings indicated that the inclusion of HPMC in the PAN membranes led to a reduction in surface porosity and fiber size. The contact angle decreased, indicating increased surface hydrophilicity, which can enhance flux and reduce fouling tendencies. Subsequently, we evaluated the e
... Show MoreIn this study, a traumatic spinal cord injury (TSCI) classification system is proposed using a convolutional neural network (CNN) technique with automatically learned features from electromyography (EMG) signals for a non-human primate (NHP) model. A comparison between the proposed classification system and a classical classification method (k-nearest neighbors, kNN) is also presented. Developing such an NHP model with a suitable assessment tool (i.e., classifier) is a crucial step in detecting the effect of TSCI using EMG, which is expected to be essential in the evaluation of the efficacy of new TSCI treatments. Intramuscular EMG data were collected from an agonist/antagonist tail muscle pair for the pre- and post-spinal cord lesi
... Show MoreThe speaker identification is one of the fundamental problems in speech processing and voice modeling. The speaker identification applications include authentication in critical security systems and the accuracy of the selection. Large-scale voice recognition applications are a major challenge. Quick search in the speaker database requires fast, modern techniques and relies on artificial intelligence to achieve the desired results from the system. Many efforts are made to achieve this through the establishment of variable-based systems and the development of new methodologies for speaker identification. Speaker identification is the process of recognizing who is speaking using the characteristics extracted from the speech's waves like pi
... Show More