In recent years, with the rapid development of the current classification system in digital content identification, automatic classification of images has become the most challenging task in the field of computer vision. As can be seen, vision is quite challenging for a system to automatically understand and analyze images, as compared to the vision of humans. Some research papers have been done to address the issue in the low-level current classification system, but the output was restricted only to basic image features. However, similarly, the approaches fail to accurately classify images. For the results expected in this field, such as computer vision, this study proposes a deep learning approach that utilizes a deep learning algorithm.

Water level and distribution is very essential in almost all life aspects. Natural and artificial lakes represent a large percentage of these water bodies in Iraq. In this research the changes in water levels are observed by calculating the areas of five different lakes in five different regions and two different marshes in two different regions of the country, in a period of 12 years (2001 - 2012), archived remotely sensed images were used to determine surface areas around lakes and marshes in Iraq for the chosen years . Level of the lakes corresponding to satellite determined surface areas were retrieved from remotely sensed data .These data were collected to give explanations on lake level and surface area fluctuations. It is imp

In this study, the optimum conditions for COD removal from petroleum refinery wastewater by using a combined electrocoagulation- electro-oxidation system were attained by Taguchi method. An orthogonal array experimental design (L18) which is of four controllable parameters including NaCl concentration, C.D. (current density), PH, and time (time of electrolysis) was employed. Chemical oxygen demand (COD) removal percentage was considered as the quality characteristics to be enhanced. Also, the value of turbidity and TDS (total dissolved solid) were estimated. The optimum levels of the studied parameters were determined precisely by implementing S/N analysis and analysis of variance (ANOVA). The optimum conditions were found to be NaCl = 2.5

The fluctuation properties of energy spectrum, electromagnetic transition intensities and electromagnetic moments in nucleus are investigated with realistic shell model calculations. We find that the spectral fluctuations of are consistent with the Gaussian orthogonal ensemble of random matrices. Besides, we observe a transition from an order to chaos when the excitation energy is increased and a clear quantum signature of the breaking of chaoticity when the single-particle energies are increased. The distributions of the transition intensities and of the electromagnetic moments are well described by a Porter-Thomas distribution. The statistics of electromagnetic transition intensities clearly deviate from a Porter-Thomas distribution (i

This paper presents a new design of a nonlinear multi-input multi-output PID neural controller of the active brake steering force and the active front steering angle for a 2-DOF vehicle model based on modified Elman recurrent neural. The goal of this work is to achieve the stability and to improve the vehicle dynamic’s performance through achieving the desired yaw rate and reducing the lateral velocity of the vehicle in a minimum time period for preventing the vehicle from slipping out the road curvature by using two active control actions: the front steering angle and the brake steering force. Bacterial forging optimization algorithm is used to adjust the parameters weights of the proposed controller. Simulation resul

Deep learning has recently received a lot of attention as a feasible solution to a variety of artificial intelligence difficulties. Convolutional neural networks (CNNs) outperform other deep learning architectures in the application of object identification and recognition when compared to other machine learning methods. Speech recognition, pattern analysis, and image identification, all benefit from deep neural networks. When performing image operations on noisy images, such as fog removal or low light enhancement, image processing methods such as filtering or image enhancement are required. The study shows the effect of using Multi-scale deep learning Context Aggregation Network CAN on Bilateral Filtering Approximation (BFA) for d

In the geotechnical and terramechanical engineering applications, precise understandings are yet to be established on the off-road structures interacting with complex soil profiles. Several theoretical and experimental approaches have been used to measure the ultimate bearing capacity of the layered soil, but with a significant level of differences depending on the failure mechanisms assumed. Furthermore, local displacement fields in layered soils are not yet studied well. Here, the bearing capacity of a dense sand layer overlying loose sand beneath a rigid beam is studied under the plain-strain condition. The study employs using digital particle image velocimetry (DPIV) and finite element method (FEM) simulations. In the FEM, an experiment

Thermomechanical analysis (TMA) and differential scanning calorimetry (DSC) are used to investigate the effect of molding and annealing of polyester on the behavior of thermal expansion and crystallization since these factors play role in the reprocessing or recycling of the polymer. The dynamic mode of the TMA provides enhanced characterization information about the polyester since it separates the transitions into reversible and irreversible signals, and also reveals the progress of the amorphous regions as the polyester loses strength with the increasing temperature approaching melting. Slow cooling after annealing brings crystallization that may be attributed to molecular chain straightening due to orientation.