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

One of the most important and common problems in petroleum engineering; reservoir, and production engineering is coning; either water or gas coning. Almost 75% of the drilled wells worldwide contains this problem, and in Iraq water coning problem is much wider than the gas coning problem thus in this paper we try to clarify most of the reasons causing water coning and some of applicable solutions to avoid it using the simulation program (CMG Builder) to build a single well model considering an Iraqi well in north of Iraq black oil field with a bottom water drive, Coning was decreased by 57% by dividing into sub-layers (8) layers rather than (4) layers, also it was decreased (Coning) by 45% when perforation numbers and positions was chang

Drilling well design optimization reduces total Authorization for Expenditures (AFE) by decreasing well constructing time and expense. Well design is not a constant pattern during the life cycle of the field. It should be optimized by continuous improvements for all aspects of redesigning the well depending on the actual field conditions and problems. The core objective of this study is to deliver a general review of the well design optimization processes and the available studies and applications to employ the well design optimization to solve problems encountered with well design so that cost effectiveness and perfect drilling well performance are achievable. Well design optimization processes include unconventional design(slimhole) co

Survival analysis is widely applied in data describing for the life time of item until the occurrence of an event of interest such as death or another event of understudy . The purpose of this paper is to use the dynamic approach in the deep learning neural network method, where in this method a dynamic neural network that suits the nature of discrete survival data and time varying effect. This neural network is based on the Levenberg-Marquardt (L-M) algorithm in training, and the method is called Proposed Dynamic Artificial Neural Network (PDANN). Then a comparison was made with another method that depends entirely on the Bayes methodology is called Maximum A Posterior (MAP) method. This method was carried out using numerical algorithms re

In present work an investigation for precise hole drilling via continuous wave (CW) CO2 laser at 150 W maximum output power and wavelength 10.6 μm was achieved with the assistance of computerized numerical controlled (CNC) machine and assist gases. The drilling process was done for thin sheets (0.1 – 0.3 mm) of two types of metals; stainless steel (sst) 321H, steel 33 (st). Changing light and process parameters such as laser power, exposure time and gas pressure was important for getting the optimum results. The obtained results were supported with computational results using the COMSOL 3.5a software code.

Changing oil-wet surfaces toward higher water wettability is of key importance in subsurface engineering applications. This includes petroleum recovery from fractured limestone reservoirs, which are typically mixed or oil-wet, resulting in poor productivity as conventional waterflooding techniques are inefficient. A wettability change toward more water-wet would significantly improve oil displacement efficiency, and thus productivity. Another area where such a wettability shift would be highly beneficial is carbon geo-sequestration, where compressed CO2 is pumped underground for storage. It has recently been identified that more water-wet formations can store more CO2. We thus examined how silica based nanofluids can induce such a wettabil

Steganography is a technique of concealing secret data within other quotidian files of the same or different types. Hiding data has been essential to digital information security. This work aims to design a stego method that can effectively hide a message inside the images of the video file.  In this work, a video steganography model has been proposed through training a model to hiding video (or images) within another video using convolutional neural networks (CNN). By using a CNN in this approach, two main goals can be achieved for any steganographic methods which are, increasing security (hardness to observed and broken by used steganalysis program), this was achieved in this work as the weights and architecture are randomized. Thus,

Cloud storage provides scalable and low cost resources featuring economies of scale based on cross-user architecture. As the amount of data outsourced grows explosively, data deduplication, a technique that eliminates data redundancy, becomes essential. The most important cloud service is data storage. In order to protect the privacy of data owner, data are stored in cloud in an encrypted form. However, encrypted data introduce new challenges for cloud data deduplication, which becomes crucial for data storage. Traditional deduplication schemes cannot work on encrypted data. Existing solutions of encrypted data deduplication suffer from security weakness. This paper proposes a combined compressive sensing and video deduplication to maximize