In the current worldwide health crisis produced by coronavirus disease (COVID-19), researchers and medical specialists began looking for new ways to tackle the epidemic. According to recent studies, Machine Learning (ML) has been effectively deployed in the health sector. Medical imaging sources (radiography and computed tomography) have aided in the development of artificial intelligence(AI) strategies to tackle the coronavirus outbreak. As a result, a classical machine learning approach for coronavirus detection from Computerized Tomography (CT) images was developed. In this study, the convolutional neural network (CNN) model for feature extraction and support vector machine (SVM) for the classification of axial lung CT-scans into two groups (COVID-19 and NonCOVID-19) had been proposed. A dataset used is 960 slices of CT scan collected from Iraqi patients /Ibn Al-Nafis teaching hospital. The performance metrics are used in this study (accuracy, recall, precision, and F1 scores). The results indicate that the proposed approach generated a high-quality model for the collected dataset, with an overall accuracy of 98.95% and an overall recall of 97 %.
In this study, the feasibility of Forward–Reverse osmosis processes was investigated for treating the oily wastewater. The first stage was applied forward osmosis process to recover pure water from oily wastewater. Sodium chloride (NaCl) and magnesium chloride (MgCl2) salts were used as draw solutions and the membrane that was used in forward osmosis (FO) process was cellulose triacetate (CTA) membrane. The operating parameters studied were: draw solution concentrations (0.25 – 0.75 M), oil concentration in feed solution (FS) (100-1000 ppm), the temperature of FS and draw solution (DS) (30 - 45 °C), pH of FS (4-10) and the flow rate of both DS and FS (20 - 60 l/h). It was found that the water flux and oil concentration in FS increas
... Show MoreThe usage of remote sensing techniques in managing and monitoring the environmental areas is increasing due to the improvement of the sensors used in the observation satellites around the earth. Resolution merge process is used to combine high resolution one band image with another one that have low resolution multi bands image to produce one image that is high in both spatial and spectral resolution. In this work different merging methods were tested to evaluate their enhancement capabilities to extract different environmental areas; Principle component analysis (PCA), Brovey, modified (Intensity, Hue ,Saturation) method and High Pass Filter methods were tested and subjected to visual and statistical comparison for evaluation. Both visu
... Show MoreThis paper presents a robust control method for the trajectory control of the robotic manipulator. The standard Computed Torque Control (CTC) is an important method in the robotic control systems but its not robust to system uncertainty and external disturbance. The proposed method overcome the system uncertainty and external disturbance problems. In this paper, a robustification term has been added to the standard CTC. The stability of the proposed control method is approved by the Lyapunov stability theorem. The performance of the presented controller is tested by MATLAB-Simulink environment and is compared with different control methods to illustrate its robustness and performance.
In this research a new system identification algorithm is presented for obtaining an optimal set of mathematical models for system with perturbed coefficients, then this algorithm is applied practically by an “On Line System Identification Circuit”, based on real time speed response data of a permanent magnet DC motor. Such set of mathematical models represents the physical plant against all variation which may exist in its parameters, and forms a strong mathematical foundation for stability and performance analysis in control theory problems.
Automation is one of the key systems in modern agriculture, providing potential solutions to the challenges related to the growing world population, demographic shifts, and economic situation. The present article aims to highlight the importance of precision agriculture (PA) and smart agriculture (SA) in increasing agricultural production and the importance of environmental protection in increasing production and reducing traditional production. For this purpose, different types of automation systems in the field of agricultural operations are discussed, as well as smart agriculture technologies including the Internet of Things (IoT), artificial intelligence (AI), machine learning (ML), big data analysis, in addition to agricultural robots,
... Show MoreIt takes a lot of time to classify the banana slices by sweetness level using traditional methods. By assessing the quality of fruits more focus is placed on its sweetness as well as the color since they affect the taste. The reason for sorting banana slices by their sweetness is to estimate the ripeness of bananas using the sweetness and color values of the slices. This classifying system assists in establishing the degree of ripeness of bananas needed for processing and consumption. The purpose of this article is to compare the efficiency of the SVM-linear, SVM-polynomial, and LDA classification of the sweetness of banana slices by their LRV level. The result of the experiment showed that the highest accuracy of 96.66% was achieved by the
... Show MoreObjectives To quantify the reproducibility of the drill calibration process in dynamic navigation guided placement of dental implants and to identify the human factors that could affect the precision of this process in order to improve the overall implant placement accuracy. Methods A set of six drills and four implants were calibrated by three operators following the standard calibration process of NaviDent® (ClaroNav Inc.). The reproducibility of the position of each tip of a drill or implant was calculated in relation to the pre-planned implants’ entry and apex positions. Intra- and inter-operator reliabilities were reported. The effects of the drill length and shape on the reproducibility of the calibration process were also investig
... Show MoreLet M be a n-dimensional manifold. A C1- map f : M M is called transversal if for all m N the graph of fm intersect transversally the diagonal of MM at each point (x,x) such that x is fixed point of fm. We study the minimal set of periods of f(M per (f)), where M has the same homology of the complex projective space and the real projective space. For maps of degree one we study the more general case of (M per (f)) for the class of continuous self-maps, where M has the same homology of the n-dimensional sphere.
In this paper we describe several different training algorithms for feed forward neural networks(FFNN). In all of these algorithms we use the gradient of the performance function, energy function, to determine how to adjust the weights such that the performance function is minimized, where the back propagation algorithm has been used to increase the speed of training. The above algorithms have a variety of different computation and thus different type of form of search direction and storage requirements, however non of the above algorithms has a global properties which suited to all problems.
The problem of dark matter in galaxies is still one of the most important unsolved problems in the contemporary extragalactic astronomy and cosmology. The existence of a significant dynamic difference between the visible mass and the conventional mass of galaxies firmly establishes observational result. In this paper an unconventional explanation will be tested as an alternative to the cold dark matter hypothesis; which is called the modified Newtonian dynamics (MOND).
In this paper covers the simulation of galactic evolutions; where the two hypotheses are tested via the rotation curves. N-body simulation was carried adopting different configuration lik