<p>Analyzing X-rays and computed tomography-scan (CT scan) images using a convolutional neural network (CNN) method is a very interesting subject, especially after coronavirus disease 2019 (COVID-19) pandemic. In this paper, a study is made on 423 patients’ CT scan images from Al-Kadhimiya (Madenat Al Emammain Al Kadhmain) hospital in Baghdad, Iraq, to diagnose if they have COVID or not using CNN. The total data being tested has 15000 CT-scan images chosen in a specific way to give a correct diagnosis. The activation function used in this research is the wavelet function, which differs from CNN activation functions. The convolutional wavelet neural network (CWNN) model proposed in this paper is compared with regular convolutional neural network that uses other activation functions (exponential linear unit (ELU), rectified linear unit (ReLU), Swish, Leaky ReLU, Sigmoid), and the result is that utilizing CWNN gave better results for all performance metrics (accuracy, sensitivity, specificity, precision, and F1-score). The results obtained show that the prediction accuracies of CWNN were 99.97%, 99.9%, 99.97%, and 99.04% when using wavelet filters (rational function with quadratic poles (RASP1), (RASP2), and polynomials windowed (POLYWOG1), superposed logistic function (SLOG1)) as activation function, respectively. Using this algorithm can reduce the time required for the radiologist to detect whether a patient has COVID or not with very high accuracy.</p>
In this paper, the developed sprite allocation method is designed to be coherent with the introduced block-matching method in order to minimize the allocation process time for digital video. The accomplished allocation process of sprite region consists of three main steps. The first step is the detection of sprite area; where the sequence of frames belong to Group of Video sequence are analysed to detect the sprite regions which survive for long time, and to determine the sprite type (i.e., whether it is static or dynamic). Then as a second step, the flagged survived areas are passed through the gaps/islands removal stage to enhance the detected sprite areas using post-processing operations. The third step is partitioning the sprite area in
... Show MoreAspect-Oriented Software Development (AOSD) is a technology that helps achieving
better Separation of Concern (SOC) by providing mechanisms to identify all relevant points
in a program at which aspectual adaptations need to take place. This paper introduces a
banking application using of AOSD with security concern in information hiding.
Smart water flooding (low salinity water flooding) was mainly invested in a sandstone reservoir. The main reasons for using low salinity water flooding are; to improve oil recovery and to give a support for the reservoir pressure.
In this study, two core plugs of sandstone were used with different permeability from south of Iraq to explain the effect of water injection with different ions concentration on the oil recovery. Water types that have been used are formation water, seawater, modified low salinity water, and deionized water.
The effects of water salinity, the flow rate of water injected, and the permeability of core plugs have been studied in order to summarize the best conditions of low salinity
... Show MoreThe proliferation of cellular network enabled users through various positioning tools to track locations, location information is being continuously captured from mobile phones, created a prototype that enables detected location based on using the two invariant models for Global Systems for Mobile (GSM) and Universal Mobile Telecommunications System (UMTS). The smartphone application on an Android platform applies the location sensing run as a background process and the localization method is based on cell phones. The proposed application is associated with remote server and used to track a smartphone without permissions and internet. Mobile stored data location information in the database (SQLite), then transfer it into location AP
... Show MoreUsed automobile oils were subjected to filtration to remove solid material and dehydration to remove water, gasoline and light components by using vacuum distillation under moderate pressure, and then the dehydrated waste oil is subjected to extraction by using liquid solvents. Two solvents, namely n-butanol and n-hexane were used to extract base oil from automobile used oil, so that the expensive base oil can be reused again.
The recovered base oil by using n-butanol solvent gives (88.67%) reduction in carbon residue, (75.93%) reduction in ash content, (93.73%) oil recovery, (95%) solvent recovery and (100.62) viscosity index, at (5:1) solvent to used oil ratio and (40 oC) extraction temperature, while using n-hexane solvent gives (6
Electrospinning is a novel technique that can be used to produce highly porous fibers with highly tunable properties. In this research, this technique is adopted to prepare the electrospun nanofiber membrane for membrane distillation application. A custom-built electrospinning setup was made to prepare the nanofibers membrane. Polyvinylidene fluoride (PVDF) polymer was used in the electrospinning process due to its high hydrophobicity. Electrospun (PVDF) nanofibers were tested in direct contact membrane distillation (DCMD) process using 0.6 M sodium chloride as a feed solution. The resulting nanofiber membrane exhibited high performance in DCMD (i.e. relatively high water flux and high salt rejection). It has been found
... Show MoreFace Identification is an important research topic in the field of computer vision and pattern recognition and has become a very active research area in recent decades. Recently multiwavelet-based neural networks (multiwavenets) have been used for function approximation and recognition, but to our best knowledge it has not been used for face Identification. This paper presents a novel approach for the Identification of human faces using Back-Propagation Adaptive Multiwavenet. The proposed multiwavenet has a structure similar to a multilayer perceptron (MLP) neural network with three layers, but the activation function of hidden layer is replaced with multiscaling functions. In experiments performed on the ORL face database it achieved a
... Show MoreRecognizing speech emotions is an important subject in pattern recognition. This work is about studying the effect of extracting the minimum possible number of features on the speech emotion recognition (SER) system. In this paper, three experiments performed to reach the best way that gives good accuracy. The first one extracting only three features: zero crossing rate (ZCR), mean, and standard deviation (SD) from emotional speech samples, the second one extracting only the first 12 Mel frequency cepstral coefficient (MFCC) features, and the last experiment applying feature fusion between the mentioned features. In all experiments, the features are classified using five types of classification techniques, which are the Random Forest (RF),
... Show More