Deep learning (DL) plays a significant role in several tasks, especially classification and prediction. Classification tasks can be efficiently achieved via convolutional neural networks (CNN) with a huge dataset, while recurrent neural networks (RNN) can perform prediction tasks due to their ability to remember time series data. In this paper, three models have been proposed to certify the evaluation track for classification and prediction tasks associated with four datasets (two for each task). These models are CNN and RNN, which include two models (Long Short Term Memory (LSTM)) and GRU (Gated Recurrent Unit). Each model is employed to work consequently over the two mentioned tasks to draw a road map of deep learning models for a variety of tasks under the control of a unified architecture for each proposed model.
Experimental study of heat transfer coefficients in air-liquid-solid fluidized beds were carried out by measuring the heat rate and the overall temperature differences across the heater at different operating conditions. The experiments were carried out in Q.V.F. glass column of 0.22 m inside diameter and 2.25 m height with an axially mounted cylindrical heater of 0.0367 m diameter and 0.5 m height. The fluidizing media were water as a continuous phase and air as a dispersed phase. Low density (Ploymethyl-methacrylate, 3.17 mm size) and high density (Glass beads, 2.31 mm size) particles were used as solid phase. The bed temperature profiles were measured axially and radially in the bed for different positions. Thermocouples were connecte
... Show MoreThis paper presents a comprehensive numerical analysis of the improvement in bearing capacity and settlement performance of hexagonal shallow footings with inclined skirts. Various numerical analyses were conducted using PLAXIS 3D to investigate the influence of skirt length-to-footing width (L/B) ratios and skirt inclination angles (θ) on hexagonal footings in loose sand. The models showed very good agreement with experimental data reported in previous studies, with an R² value of 0.996 and a maximum error of less than 4.31%. It was concluded that the inclusion of inclined skirts has a positive effect on bearing capacity, increasing it by up to approximately 2.97 times compared to non-inclined configurations, while significantly
... Show MoreIn order to improve the students’ performance level in some of the skills that are implemented on the mat device of ground movements, including the front and rear rolling, it is necessary to study the most important indicators that have a clear impact on the performance of those rolls. Among the objectives of the research: To identify the percentage of the contribution of flexibility of the hip joint, the angle of the knees and the muscular strength of the arms in the performance of the front and rear rolling skills, an opening of the research sample. The researchers used the descriptive method in the survey method for its suitability to the nature of the work, and the research community was represented by students of the third st
... Show MoreA Laced Reinforced Concrete (LRC) structural element comprises continuously inclined shear reinforcement in the form of lacing that connects the longitudinal reinforcements on both faces of the structural element. This study conducted a theoretical investigation of LRC deep beams to predict their behavior after exposure to fire and high temperatures. Four simply supported reinforced concrete beams of 1500 mm, 200 mm, and 240 mm length, width, and depth, respectively, were considered. The specimens were identical in terms of compressive strength ( 40 MPa) and steel reinforcement details. The same laced steel reinforcement ratio of 0.0035 was used. Three specimens were burned at variable durations and steady-state temperatures (one
... Show MoreThis work presents a five-period chaotic system called the Duffing system, in which the effect of changing the initial conditions and system parameters d, g and w, on the behavior of the chaotic system, is studied. This work provides a complete analysis of system properties such as time series, attractors, and Fast Fourier Transformation Spectrum (FFT). The system shows periodic behavior when the initial conditions xi and yi equal 0.8 and 0, respectively, then the system becomes quasi-chaotic when the initial conditions xi and yi equal 0 and 0, and when the system parameters d, g and w equal 0.02, 8 and 0.09. Finally, the system exhibits hyperchaotic behavior at the first two conditions, 0 and 0, and the bandwidth of the chaotic
... Show MoreNEACADEMY's JOURNALS
Background: Orthodontic mini-implants are increasingly used in orthodontics and the bone density is a very important factor in stabilization and success of mini-implant. The aim of this study was to observe the relationship among maximum bite force (MBF); body mass index (BMI); face width, height and type; and bone density in an attempt to predict bone density from these variables to eliminate the need for CT scan which have a highly hazard on patient. Materials and Methods: Computed tomographic (CT) images were obtained for 70 patients (24 males and 46 females) with age range 18-30 years. The maxillary and mandibular buccal cortical and cancellous bone densities were measured between 2nd premolar and 1st molar at two levels from the alveol
... Show MoreThis paper numerically and theoretically investigates the optical and thermal performance of a parabolic trough collector PTC system. Many numerical simulations and theoretical analyses are conducted to demonstrate the influence of the receiver geometry and shifting from the focal position on the optical performance. The examined receiver geometries are circular, square, triangular, elliptical, and the new circular–square combined geometry is named as channel receiver. The thermal performance of PTC is examined for different volume flow rates theoretically in the range of (0.36 to 2.4 lpm). The results show that the best optical design is the channel receiver with an intercept factor of 84%, while the worst is the elliptical receiver with
... Show MoreClassifying butterfly species is crucial in biodiversity studies and environmental monitoring. However, manual classification is often a laborious process that requires specialized expertise and is prone to error, especially when species have similar visual characteristics. To address these drawbacks, this paper presents a hybrid approach that combines machine learning with deep learning for feature extraction. To enhance the visibility of important features, preprocessing techniques such as background removal and binarization are applied to butterfly images. Feature extraction was performed using the SqueezeNet convolutional neural network, pretrained on the ImageNet dataset. By discarding the final classification layer, the networ
... Show More