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

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 this study, the dynamic modeling and step input tracking control of single flexible link is studied. The Lagrange-assumed modes approach is applied to get the dynamic model of a planner single link manipulator. A Step input tracking controller is suggested by utilizing the hybrid controller approach to overcome the problem of vibration of tip position through motion which is a characteristic of the flexible link system. The first controller is a modified version of the proportional-derivative (PD) rigid controller to track the hub position while sliding mode (SM) control is used for vibration damping. Also, a second controller (a fuzzy logic based proportional-integral plus derivative (PI+D) control scheme) is developed for both vibra

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, 

Thermal conductivity for epoxy composites filled with Al2O3 and Fe2O3 are
calculated, it found that increasing the weight ratio of Al2O3 and Fe2O3 lead to
increase in the values of thermal conductivity, but the epoxy composite filled with
Fe2O3, have values of thermal conductivity less than for epoxy composite filled with
Al2O3, for the same weight ratio. Also thermal conductivity calculated for epoxy
composites by contact to every two specimens (like sandwich) content same weight
ratio of alumina-oxide and ferrite-oxide, its found that the value of thermal
conductivity lays between the values of epoxy filled Al2O3 and of epoxy filled Fe2O3

This research studies the development and synthesis of blended nanocomposites filled with Titanium dioxide (TiO2). Blended nanocomposites based on unsaturated polyester resin (UPR) and epoxy resins were synthesized by reactive blending. The optimum quantity from nano partical of titanium dioxide was selected and different weight proportions 1%, 3%, 5%, and 7% ratios of new epoxy are blended with UPR resin. The dielectric breakdown strength and thermal conductivity properties of the blended nanocomposites were compared with those of the basis material (UPR and 3% TiO2).The results show good compatibility epoxy resins with the UPR resin on blending, dielectric breakdown strength values  are higher while thermal conductivity values of

High-quality academic publishing is built on rigorous peer review [...]

The optimal combination of aluminum quality, sufficient strength, high stress to weight ratio and clean finish make it a good choice in driveshafts fabrication. This study has been devoted to experimentally investigate the effect of applying laser shock peening (LSP) on the fatigue performance for 6061-T6 aluminum alloy rotary shafts. Q-switched pulsed Nd:YAG laser was used with operating parameters of 500 mJ and 600 mJ pulse energies, 12 ns pulse duration and 10 Hz pulse repetition rate. The LSP is applied at the waist of the prepared samples for the cyclic fatigue test. The results show that applying 500 mJ pulse energy yields a noticeable effect on enhancing the fatigue strength by increasing the required number of cycles to fracture the