History shows that the infectious disease (COVID-19) can stun the world quickly, causing massive losses to health, resulting in a profound impact on the lives of billions of people, from both a safety and an economic perspective, for controlling the COVID-19 pandemic. The best strategy is to provide early intervention to stop the spread of the disease. In general, Computer Tomography (CT) is used to detect tumors in pneumonia, lungs, tuberculosis, emphysema, or other pleura (the membrane covering the lungs) diseases. Disadvantages of CT imaging system are: inferior soft tissue contrast compared to MRI as it is X-ray-based Radiation exposure. Lung CT image segmentation is a necessary initial step for lung image analysis. The main challenges of segmentation algorithms exaggerated due to intensity in-homogeneity, presence of artifacts, and closeness in the gray level of different soft tissue. The goal of this paper is to design and evaluate an automatic tool for automatic COVID-19 Lung Infection segmentation and measurement using chest CT images. The extensive computer simulations show better efficiency and flexibility of this end-to-end learning approach on CT image segmentation with image enhancement comparing to the state of the art segmentation approaches, namely GraphCut, Medical Image Segmentation (MIS), and Watershed. Experiments performed on COVID-CT-Dataset containing (275) CT scans that are positive for COVID-19 and new data acquired from the EL-BAYANE center for Radiology and Medical Imaging. The means of statistical measures obtained using the accuracy, sensitivity, F-measure, precision, MCC, Dice, Jacquard, and specificity are 0.98, 0.73, 0.71, 0.73, 0.71, 0.71, 0.57, 0.99 respectively; which is better than methods mentioned above. The achieved results prove that the proposed approach is more robust, accurate, and straightforward.
Nowadays, machine learning has emerged as a promising alternative for condition monitoring of industrial processes, making it indispensable for maintenance planning. Such a learning model is able to assess health states in real time provided that both training and testing samples are complete and have the same probability distribution. However, it is rare and difficult in practical applications to meet these requirements due to the continuous change in working conditions. Besides, conventional hyperparameters tuning via grid search or manual tuning requires a lot of human intervention and becomes inflexible for users. Two objectives are targeted in this work. In an attempt to remedy the data distribution mismatch issue, we firstly introduce a feature extraction and selection approach built upon correlation analysis and dimensionality reduction. Secondly, to diminish human intervention burdens, we propose an Automatic artificial Neural network with an Augmented Hidden Layer (Auto-NAHL) for the classification of health states. Within the designed network, it is worthy to mention that the novelty of the implemented neural architecture is attributed to the new multiple feature mappings of the inputs, where such configuration allows the hidden layer to learn multiple representations from several random linear mappings and produce a single final efficient representation. Hyperparameters tuning including the network architecture, is fully automated by incorporating Particle Swarm Optimization (PSO) technique. The designed learning process is evaluated on a complex industrial plant as well as various classification problems. Based on the obtained results, it can be claimed that our proposal yields better response to new hidden representations by obtaining a higher approximation compared to some previous works.
This work deals with the study and performance improvement of the direct power control of DFIG based on backstepping Controller. Direct power control using hysteresis regulator has certain disadvantages such as significant powers ripples, variable switching frequency and sensitivity to parametric variations. To surmount these disadvantages, we present a robust controller such as the backstepping-based direct power control using SVM. A comparison study was made between the classic direct power control and the backstepping controller. The simulation results show that the backstepping controller provides good results reduces powers ripples.
Antibiotic resistance is one of the greatest public-health challenges worldwide, especially with regard to Gram-negative bacteria (GNB). Carbapenems are the β-lactam antibiotics of choice with the broadest spectrum of activity and, in many cases, are the last-resort treatment for several bacterial infections. Carbapenemase-encoding genes, mainly carried by mobile genetic elements, are the main mechanism of resistance against carbapenems in GNB. These enzymes exhibit a versatile hydrolytic capacity and confer resistance to most β-lactam antibiotics. After being considered a clinical issue, increasing attention is being giving to the dissemination of such resistance mechanisms in the environment and especially through water. Aquatic environments are among the most significant microbial habitats on our planet, known as a favourable medium for antibiotic gene transfer, and they play a crucial role in the huge spread of drug resistance in the environment and the community. In this review, we present current knowledge regarding the spread of carbapenemase-producing isolates in different aquatic environments, which may help the implementation of control and prevention strategies against the spread of such dangerous resistant agents in the environment.
The Reynolds–averaged Navier–Stokes (RANS) equations were solved along with Reynolds stress model (RSM), to study the fully-developed unsteady and anisotropic single-phase turbulent flow in 90° bend pipe with circular cross-section. Two flow configurations are considered the first is without ribs and the second is with ribs attached to solid walls. The number of ribs is 14 ribs regularly placed along the straight pipe. The pitch ratios is 40 and the rib height e (mm) is 10% of the pipe diameter. Both bends have a curvature radius ratio, of 2.0. The solutions of these flows were obtained using the commercial CFD software Fluent at a Dean number range from 5000 to 40000. In order to validate the turbulence model, numerical simulations were compared with the existing experimental data. The results are found in good agreement with the literature data. After validation of the numerical strategy, the axial velocity distribution and the anisotropy of the Reynolds stresses at several downstream longitudinal locations were obtained in order to investigate the hydrodynamic developments of the analyzed flow. The results show that in the ribbed bend pipe, the maximum velocity value is approximately 47% higher than the corresponding upstream value but it is 9% higher in the case of the bend pipe without ribs. It was also found for both cases that the distribution of the mean axial velocity depends faintly on the Dean number. Finally, it can be seen that the analyzed flow in the bend pipe without ribs appears more anisotropic than in bend pipe with ribs.
This paper presents an experimental study to evaluate the effect of local mineral additions (pozzolan, slag and limestone) on the rheological behaviour of based cement binder’s pastes. The binary, ternary and quaternary binder pastes were prepared with the partial clinker cement replacement limited up to 20%, according with type CEM II specifications. The cements were characterized by their geometric shapes, the reactivity and the chemical composition. An experimental design plan was used to modelling the rheological behaviour of pastes. The relatives yield stress and plastic viscosity of binder’s pastes, with normal consistency, were determined. The results showed that all the tested compositions with additions follow the same rheological behaviour law according to the Bingham model. The binder pastes rheological parameters (yield stress and viscosity) are affected by mineral additions. The highest values of the rheological parameters were measured in binary and ternary cements with limestone and pozzolan. On the other hand, the lower viscosity among the tested pastes was obtained with slag addition. The statistical approach allowed us to obtain a satisfactory modelling of viscosity and yield stress with a coefficient of determination R2 = 0.91 and 0.92, respectively and a satisfactory correlation between the viscosity and the water/binder ratio (W/B) for a normal consistency with a coefficient of determination R2 = 0.91.
The current study focuses on the chemical composition, and evaluation of antioxidant and antibacterial activity of the aerial parts of Centaurea resupinata subsp. dufourii. Using different chromatographic methods nine compounds 1–9 were isolated. The structural identification of isolated compounds was achieved using several spectroscopic methods NMR techniques (1H NMR, 13C NMR, COSY, HSQC, HMBC) and mass spectroscopy (ESI-MS) and by comparison with literature data. The structures of these compounds were identified as nicotiflorin (1), apigetrin (2), chrysoeriol (3), apigenin (4), chrysin (5), daucosterol (6), β-sitosterol (7), taraxastrerol (8) and lupeol (9). The antibacterial and antioxidant activities of ethyl acetate and n-butanol extracts have been evaluated. The antioxidant activity was assessed in vitro using DPPH radical scavenging method, which showed that ethyl acetate extract possessed an interesting antioxidant potential (IC50 = 36.263 ± 0.005 μg/mL).
A recent study from GLOBOCAN disclosed that during 2018 two million women worldwide had been diagnosed with breast cancer. Currently, mammography, magnetic resonance imaging, ultrasound, and biopsies are the main screening techniques, which require either, expensive devices or personal qualified; but some countries still lack access due to economic, social, or cultural issues. As an alternative diagnosis methodology for breast cancer, this study presents a computer-aided diagnosis system based on convolutional neural networks (CNN) using thermal images. We demonstrate that CNNs are faster, reliable and robust when compared with different techniques. We study the influence of data pre-processing, data augmentation and database size on several CAD models. Among the 57 patients database, our CNN models obtained a higher accuracy (92%) and F1-score (92%) that outperforms several state-of-the-art architectures such as ResNet50, SeResNet50, and Inception. This study exhibits that a CAD system that implements data-augmentation techniques reach identical performance metrics in comparison with a system that uses a bigger database (up to 33%) but without data-augmentation. Finally, this study proposes a computer-aided system for breast cancer diagnosis but also, it stands as baseline research on the influence of data-augmentation and database size for breast cancer diagnosis from thermal images with CNNs
: In this paper, we have studied a different fault tolerant control (FTC) strategies for a three-phase induction motor (3p-IM). Further we introduce Backstepping controller (BC) and Input-output linearization controller (IOLC). To provide a direct comparison between these FTCs approaches, the performances are evaluated using the control of 3p-IM under failures, variable speed, and variable parameters. A comparison between the two control strategies is proposed to prove the most robust one. The simulation results show the robustness and good performance of the fault tolerant control with Input-output linearization controller compared to one with Backstepping controller. The FTC with IOLC is more stable and robust against failures, load torque perturbation and speed reversion
In the industry, automated inspection is important for ensuring the high quality and allows acceleration of procedures for quality control of parts or mechanical assemblies. Although significant progress has been made in precision machining of complex surfaces, precision inspection of such surfaces remains a difficult problem. Thus the problem of the conformity of the parts of complex geometry is felt more and more. Motivated by the need to increase quality and reduce costs, and supported by the progress made in the field of it as well as the automation of production which in recent years has seen a considerable evolution in all these stages: from design to control through manufacturing. Due to, we used a 3D computer aided inspection technique on a physical gear using a coordinate measuring machine equipped with a “PC-DMIS” measurement and inspection software. Our work consists in developing a procedure for inspection for reproduction of gear profile by reconstruction of a circle involute gear from a cloud point’s measurement. In order to obtain a reliable result. In this works, we design the CAD-model of the part as accurately as possible (using a mathematical model) and matched with the 3D points cloud that represents the measurement that obtained from scanner. we compare the measurement cloud points from coordinate measurement machine with the mathematical model of construction by ICP (Iterative Closest Point) methods in order to obtain a conformed result and to show the impact of the dimensional inspection and geometric.