×
The submission system is temporarily under maintenance. Please send your manuscripts to
Go to Editorial ManagerThis study has been performed to compare the compartmental modeling of two types of extravascular routes, sustained-release (SR) oral dosage forms and intramuscular (IM) injection. Twenty healthy volunteers received a single dose of 100 mg Diclofenac Sodium (DS) sustained-release tablet, then 75 mg DS Intramuscular injection after two weeks washout period. The concentrations of DS in plasma were measured using reverse-phase high-performance liquid chromatography (HPLC). The data analyzed using compartmental modeling, with single time-variant input and output. Primary kinetic parameters for both formulations, ( , , ) and other kinetic parameters were evaluated. The result shows that the IM injection needs a shorter time to reach the maximum concentration with convergent bioavailability to SR oral dosage forms, in another hand the data of IM injection fitted to single-compartment model with a correlation coefficient of 0.93 and the data of SR tablet fitted to two-compartment models with a correlation coefficient of 0.97.
Dynamic modeling of a robot manipulator is a central problem in an accurate robot control. In this paper; the dynamic equations of motion were derived by using Eular-Lagrange method for a six degree of freedom articulated robot manipulator based on the geometrical jacobian construction for each link and actuator. In addition, friction effects beside the end effector forces that act the environment are considered. A Matlab Simulink plant is developed to embrace the theoretical work and simulate the dynamic response for a designed nonlinear controller Proportional Derivative plus Gravity (PD+G), also a modified controller is applied to reject the disturbances and the internal friction effect where the settling errors were 3.57E-6, 2.09E-7, -3.63E-6, 8.84E-6, -5.39E-8 and -4.39E-5 (deg) for joints one to six respectively. The presented approach can be applicable to solve the dynamic problem of other n-link robot manipulators and achieve a suitable solution for tracking trajectories.
Specimens with the structure of a face-centered cubic were produced using several sets of printing conditions. An experimental testing is conducted to carefully evaluate the microstructural analysis and compressive strength of this structure. The results include the measurement of mechanical properties, such as the peak stress. Fused deposition modeling is employed for the additive manufacturing of experimental specimens made from shape memory polymer thermoplastic polyurethane (MM-3520). We take into account the impact of printing factors on lattice structures, such as layer thickness, printing temperature, and printing speed. Analyzing the microstructure of the printed specimens exhibits that the specimens with highest printing temperature, lowest printing speed and thinner printing layer have better layers adhesion and lower porosities. All the mechanical tests are performed on specimens with the same structure and at a relatively constant density. Among the tested printing parameters, using a layer height of 0.1 mm, a printing temperature of 230 °C, and a printing speed of 20 mm/s yields the highest strength in the specimens. However, specimens printed with a layer height of 0.2 mm, a printing temperature of 220 °C, and a printing speed of 30 mm/s also exhibit good strength, albeit slightly lower than the maximum values. Additionally, when using these specific settings (0.3 mm – 210 °C – 40 mm/s), the mechanical qualities are minimized, yet the stress-strain curves exhibit characteristics similar to elastomers.
This paper presents a numerical investigation to study the effect of variations in displacement history sequence and magnitude on cyclic response of RC tapered (haunched) beams (RCHBs).Five simply supported RCHBs (four haunched and one prismatic) were selected from experimental work carried out by Aranda et al. The selected variables included were five loading history types. The first part of this study focused to verify the finite element analysis with selected experimental work and the second part of this study focused too studying the effect of varying in loading history to the response of RCHBs. The finite element code Abaqus was used in the modeling. The adopted cyclic simulation performance of the selected beams using the plastic- damage model for concrete developed by Lubliner and Lee & Fenves. The constitutive model of plain concrete describing the uniaxial compression response under cyclic loading proposed by Thorenfeldt, and the uniaxial tension response follows the softening law proposed by Hordijk was used in the modeling. Menegotto-Pinto model was used to simulate the steel response. Model verification has shown A good agreement to the selected experimental work. The variations in loading history will decrease the ultimate load and corresponding deflection with increase in the number of cycles at ultimate load.
In this study, the analytic model (Azmi Model) had been considered for computation the load capacities of the composite open web steel joists and compared them with those obtained from experimental tests. The capacities of seven joists had been studied, each including one of the following variables (distribution of headed studs, connection degree of the connectors, inclination of the web, shape of the web, density of slab concrete, length of connectors).Theoretically, according to the Analytic model, the referenced joist of (45° web inclination , uniformly distributed ,over connected ,short headed studs) exhibited maximum load capacity of (18.45) ton, while the joist of (45° web inclination, uniformly distributed, under connected, short headed studs) exhibited minimum load capacity of (16.23) ton at yield point of bottom chord. Experimentally, the referenced joist exhibited maximum load capacity of (15.51) ton, while the joist of (34° web inclination, uniformly distributed, over connected, short headed studs) exhibited (12.49) ton load capacity. The load capacities values of the tested joists ranged between (67%-85%) of the predicted values according to the analytic model.
The improvement in solar chimneys' thermal performance and thermal behavior that can be achieved by adding metal foam has been tested in computational work. The flow and heat transfer governing equations for solar chimney models were solved using computational fluid dynamics (CFD). It was solved using the control volume numerical method in ANSYS FLUENT 14.5. It is used to construct a finite volume modeling technique for solving the governing equations and the radiation heat transfer equations. With standard flat absorber plates, the results showed that heat transmission was increased by the inclusion of metal foam (10 PPI), leading to an increase in air velocity at the solar chimney of around 13.3%. The highest average air velocity with 10 PPI drops by 54.4% as the height of the absorber plate changes from 5 cm to 25 cm respectively.
This study implements the soft computing techniques such as Artificial Neural Network (ANN) and an adaptive Neuro-Fuzzy (ANFIS) approach. Thus to model the rutting prediction with the aid of experimental uniaxial creep test results for asphalt mixtures. Marshall samples, having Maximum Nominal Size of 12.5 mm, have been selected from previous studies. These samples have been prepared and tested under different conditions. They were also subjected to different loading stress (0.034, 0.069, 0.103) MPa, and tested at various temperature (10, 20, 40, and 55) °C. The modeling analysis revealed that both approaches are powerful tools for modeling creep behavior of pavement mixture in terms of Root Mean Square Error and Correlation Coefficient. The best results are obtained with the ANFIS model.
The oil industry has a direct impact on the economic feasibility of other sectors and is considered to be the most important energy source used to turn the wheels of other industries. Therefore, it was necessary to pay attention and continuously develop this industry, to find the best modern techniques for designing, pre-commissioning and controlling process, to improve efficiency, preserve energy and achieve the highest production of costly components with the highest purity of the product. This study aims to provide a literary analysis of the stages of development and progress of the dynamics and control of the petroleum industry, in particular the distillation column, because it is multivariable with high interaction between control cycles, nonlinear behaviour and large gains. Control processes have undergone many developments and modernizations to achieve the best results. Various control methods have been used, ranging from simple proportional-integral-derivative controller (PID) to advanced control strategies such as model predictive control (MPC), multivariate model predictive control (MMPC), fuzzy logic control (FLC), quadratic dynamic matrix control (QDMC), artificial neural network control (ANN) and other advanced control techniques. The authors concluded from the review that the advanced control strategies superior than the conventional methods.
Distillation columns are among the most critical units in chemical processes, especially in oil refineries. This research aims to develop a mathematical model for a nonlinear multicomponent naphtha distillation column using real experimental data. The naphtha distillation column used in this research consists of a column with a diameter of 2.2 m and a height of 16.6 m, containing 20 trays of type (valve tray). The process currently operates in Al-Dora Refinery as part of the Midland Refinery Company in eastern Baghdad, Iraq. Four manipulated variables (reflux flow rate, reboiler heat duty, light compound fraction in the feed, and feed flow rate) were tested for their impact on four control variables (light compound fraction in the top product, light compound fraction in the bottom product, amount of top product, and amount of bottom product). A 4x4 transfer function is produced by representing the obtained dynamic models for the variables under study using various second-order models (having different damping factors) with dead time.
The axial capacity and pile transference of loads under static loading have both been well reported, but further research is needed to understand the dynamic lateral responses. The pile load imposed during an earthquake may increase, but the soil’s ability to support it may fall as a side effect of the vibration leading to more settlement. The key objective of this work is to identify what led to the substantial lateral destruction of the piles during the seismic event due to the kinematic effects. These failures were related to discontinuities in the subsoil as a result of sudden changes in soil strength due to shaking. The kinematic stresses exerted in a single pipe pile constructed in two sand layers under two different situations (dry and saturated states) are investigated in this study using numerical modeling. The bending moments were higher in the saturated sand soil than in the dry one which may be attributed to liquefaction. Generally, the acceleration increased through the loose layer (from bottom to top), and then significantly settled within the dense layer. It could be shown that using this modeling, one can estimate how a pile foundation will behave under "kinematic" loading driven by earthquakes. Therefore, the design and installation of drilled aluminum or steel piles in sand soil could make use of these present observations.
The removal of Congo red dye from industrial wastewater before its discharge to the environment is a critical problem, as it is non-biodegradable, toxic, and carcinogenic. Activated carbon was synthesized from a suggested sustainable source (sugarcane waste) and used as an adsorbent for the dye. Isotherm adsorption models and adsorption kinetics were investigated, and a simulated adsorption column model was proposed and developed based on the modified general rate model. The batch results showed that the highest removal rate achieved was 87.1% of the initial dye concentration (30 mg/L). The Freundlich isotherm model best described the equilibrium data, as evidenced by the high correlation coefficient (0.9535). Meanwhile, the maximum adsorption capacity was found to be 149.25 mg/g using the Langmuir isotherm. Furthermore, the kinetic results indicate that the pseudo-second-order model accurately describes the concentration-time relationship. A simulated maximum dynamic adsorption capacity of 0.096 mg/g was achieved at an optimal volumetric flow rate of 0.1 mL/min, with a dye concentration of 30 mg/L and a bed length of 39.69 cm. The continuous column efficiency increased with column length, reaching a maximum of 75% at 66.15 cm. Also, as the dye concentration increased, the column efficiency and dynamic adsorption capacity decreased. The study demonstrated an innovative approach to removing Congo red dye from its aqueous solution in a neutral medium using sustainably produced activated carbon derived from a sustainable source. A continuous removal process was simulated by developing a mathematical model based on adsorption curves and adsorption kinetics, which successfully described the adsorption process. This type of modeling, rather than relying on pre-existing equations, enables more efficient, scalable design.
This work investigated the removal of the reactive green (R.G) dye from wastewater using the photo-Fenton process. Batch experiments were carried out to research the role of the Impacts of operating parameters. The dosage of H2O2; dosage Fe+2; pH; temperature, and irradiation time were examined. Maximum decolorization efficiencies green dye were achieved at the [H2O2]=100 ppm; [Fe2+]=20 ppm; pH 3; temperature=56 °C and irradiation time=90 min. This research focuses on modeling, kinetics and thermodynamics of the removal of pollutant (reactive green dye) of water. The results showed that the decolorization kinetic of R.G followed pseudo-first-order reaction kinetic. Also the thermodynamic parameters ?G?, ?H? and ?S? were determined using the Van't Hoff equation for the oxidation processes. The changes in Gibbs free energy showed the oxidation process under normal conditions is non-spontaneous.
The effect of fines content (material finer than 0.075 mm) on the mechanical properties of subbase course aggregate is studied in this paper. a laboratory tests were carried out using percentage of fines material 5%, 10% and 15% by weight adding to the original subbase aggregate class B according to Iraqi specification (SCRB) which the specification limit the range of fines between 5-15%. The repeated load CBR test was done to study the mechanical properties; accumulative permanent, elastic deformation and equivalent elastic modulus.The RL CBR test was useful technique to assess the influence of fines material and stress level on the equivalent elastic modulus, and on the evolution of deformation. The equivalent modulus increase when adding 5% of fines material in case of plastic fines, but in case of non-plastic the increase continues until adding 10% fines material. Adding fines material also led to change in accumulative permanent deformation, where adding 5% fines material increase the permanent deformation by 36%, 5% for material with plastic fines and 20% for material with non-plastic fines for unsoaked samples. In case of soaked samples permanent deformation increase by 28% and 25% at adding fines material for material with plastic fines where decrease by 1% at adding 5% fines to original granular material with non-plastic fines. The theoretical modeling show that the deformation increase by increasing number of loads repetitions.
Recently microwave photonic filter (MPF) have a great interest due to their advantages which include low loss, wide bandwidth tunability, reconfigurability, and no electromagnetic interference. This paper presented a comprehensive optical transmission analysis of a reflective-type microring resonator (R-MRR) using coupled mode theory, and design guidelines for MPF through two cascaded R-MRR using COMSOL software simulation results. The design was implemented on silicon-on-insulator (SOI) platform-based MPF which exhibits wide bandwidth tunability and reconfigurability by adjusting the coupling coefficient in the two coupling regions. In this structure, a grating coupler (GC) reflector is introduced to the drop port of MRR. The analysis and simulation results were confirmed by utilizing a GC reflector and Mach-Zehender Interferometer (MZI). The results of the proposed MPF at laser light input of (1.55*10^6- m) wavelength showed the bandwidth and center frequency are adjusted from 0.3 to 6 GHz and 13 to 54.8 GHz, respectively, with a high rejection ratio reaching 70 dB. Overall, the structure represents a significant step towards designing the MPFs, which show perfect flexibility and have numerous applications in such fields as radar, sensor, and wireless communications.
The heavy metals are considered dangerous pollutants which harm health and environment. The adsorption process is the cost effective process to get-rid of heavy metal efficiently. In this study, the adsorption bed of Nickel is simulated by using COMSOL Multiphysics to find the effect of different operating parameters namely; flow rate, temperature and pollutant concentration on adsorption bed efficiency. The modeling of non-isothermal adsorption bed based on experimental isotherms kinetic of previous work is developed too. The results showed that the optimal conditions to generate maximum removal efficiency of heavy metal were at 50?C inlet temperature, 0.1 M inlet concentration, and 80 ml/min flow rate to achieve removal values higher than 50 % of long operation period time.
In this work a general dynamic response of two-story building due to earthquake is investigated .A spatial case of two degree mass-spring–damper random vibration model is employed .The base excitation acceleration is represented according to the well- known_x000D_ regression model by Kanai –Tajimi in term of the power specturm density (PSD). The transfer function between the ground an the roofs are evaluated assuming transverse modes of vibration._x000D_ A case study of typical two symitrical story building manufactored from reinforced concret and steel is investigated.The vibration parameters such as effective mass and stiffiness and damping are calculated according to the ACI 318-11 code.The natural frequncies , mode shape and transfer functions are calculated and plotted.The PSD acceleration at the roofs are evaluated from which the mean and standared diviation of the random accelration are found .The drift at the walls is calculated and compared with the allowable limits recommended by IBC 2015 .It is found that the probability of the bulding to be safe is between (13.74 -7.35)% for the first story and (8.7 - 1.67) % for the second.
The composite opened web steel joist supported floor systems have been common for many years. It is economic and has light weight and can embed the electrical conduit, ductwork and piping, eliminating the need for these to pass under the member, consequently eliminate the height between floors. In order to study the joist strength capacity under the various conditions, it had been fabricated seven joists composed of the steel and concrete slab connected to the top chord by shear connectors (headed studs). These joist have 2820 mm length c/c of the supports and 235 mm overall depth. In the present study, six variable parameters are adopted (Studs distribution, Degree of shear connection, Degree of the web inclination, Shape of the web, Density of concrete for slab and length of the shear connector). The test results exhibited that minimum strength capacity was 160kN for light weight joist and maximum capacity was 225kN for joist of long shear connectors at failure. The results were compared by ultimate flexural model by Azmi.
The transportation cost problem of solid waste presents the biggest part of the budget allocated by municipalities for SWM. So, there is no comprehensive plan to address transport routes optimization problems in SWM that including the transfer of solid waste from transfer stations to final landfill sites. Therefore, the aim of the study finding a scientific method to solve the transportation problem of solid waste transport suitable Baghdad city that tries to find feasible solutions that ensure reducing total transport costs and leads to an effective solid waste management system. In this research, a new methodology has been developed to select the optimal transport routs of SWM in Baghdad city which involves determining the best-supposed scenario. the proposed methodology includes integration of Global Positioning System (GPS) technologies with Network Analysis model (NA). Therefore, this work provides an advanced framework of decision-makers for analysis and simulation of the optimal transport routs problem related to SWM. Applying these modeling tools to select the scenario that can provide economic benefits by minimizing travel time, travel distance and reduction of total transportation costs. The Results of work implementation show that all solutions that include current state S1 and suggested scenarios have been evaluated. The scenarios generated include (S2, S3) by applying the proposed technique for analyzed and identified the optimal routes. The solutions of scenario S2, specified with two landfill sites while scenarios S3 specified with four landfill sites. Finally, this work shows the Scenario S3 is the best scenario of the solution, that include applied GPS and Network Analysis for four landfill sites.
Fused deposition modeling (FDM) is a commonly used 3D printing technique that involves heating, extruding, and depositing thermoplastic polymer filaments. The quality of FDM components is greatly influenced by the chosen processing settings. In this study, the Taguchi technique and artificial neural network were employed to predict the ultimate tensile strength of FDM components and establish a mathematical model. The mechanical properties of ABS were analyzed by varying parameters such as layer thickness, printing speed, direction angle, number of parameters, and nozzle temperature at five different levels. FDM 3D printers were used to fabricate samples for testing, following the ASTM-D638 standards, using the Taguchi orthogonal array experimental design method to set the process parameters. The results indicated that the printing process factors had a significant impact on tensile strength, with test values ranging from 31 to 38 MPa. The neural network achieved a maximum error of 5.518% when predicting tensile strength values, while the analytical model exhibited an error of 19.376%.
CFDSST Concrete Filled Double-skinned steel tubular columns are composite columns consisting of two concentric circular steel tubes with concrete filler in between. Finite elements method is considered through the use of the computer program ABAQUS to model CFDSST columns numerically under cyclic axial compression. Damage plasticity model was considered to model the concrete while elastic-plastic model used to model the steel tubes. six CFDSST specimens and three ordinary Concrete Filled Steel Tubular (CFST) specimens were analyzed under static axial compression, while three CFDSST specimens were considered for analysis under cyclic axial compression. The numerical results were presented in terms of axial load axial strain displacement curves. It was found that the ultimate axial load carrying capacity calculated numerically in good agreement with that of the experimentally tested specimens. Also it was concluded that Damage plasticity model used for simulating the behavior of concrete and metal plasticity model used for simulating the behavior of steel produced accurate results as compared to the experimental results.
The 3-D numerical simulations of the thermal collectors in solar heating systems were conducted to simulate the conventional solar heating system, multipurpose solar water heater (MPSWH), and multipurpose solar air heater (MPSAH). The commercial computational fluid dynamics (CFD), AVL Fire ver. 2009.2 was used to solve and investigate the temperature distributions in the absorber plate and riser tube of both solar water and air heater during summer and winter seasons. The RNG k -turbulence model was employed for this CFD study. The present paper was to provide a good understanding of thermal performance for the solar collector at different operating conditions. The experimental setup and physical data of Venkatesh, R. and Christraj, W. [15] were employed as geometric parameters and initial boundary conditions to model and to validate the predicted numerical values. Comparing to the values of temperatures for the conventional SWH and SAH, the predicted results of the MPSWH and the MPSAH showed a good improvement on the thermal performance. These enhancements on the temperature may have been due to the new design adopted in the multipurpose solar heating systems by using riser tubes and headers to the original design of the thermal systems. Additionally, the thermal performance of solar collectors increases with increasing the mass flow rates and thermal conductivity of absorber plate. For validation aspect, the predicted results of all cases examined showed a good agreement against the measured results in terms of temperature distribution levels and thermal efficiencies.
Public school building projects in Karbala Province experiences payment problems due to improper cash-flow planning by both parties; contractors and clients. These payment problems lead to work stoppages and conflicts. This research aims at developing a suitable model to forecast the expected contractors’ cash-in-flow in public school building projects in Karbala based on historical data. Complete sets of interim payments of (33) out of (38) school building projects finished in the years (2007-2012) in Karbala were interpolated using seven different regression methods namely; Polynomial, Gompertz, Morgan-Morgan-Finney, Logistic, Exponential, Gaussian and Linear in order to identify the best-suited model. It is found that the third degree polynomial model is more suitable for cash-in-flow forecasting of the case under study with coefficient of correlation of (97.89%) and standard error of (0.0441). Data of the remaining (5) projects were used to test the validity of the best-fitted model using Mean Absolute Percentage Error, Root Mean Square Error and Average Accuracy Percentage. The model is expected to be of high advantage in predicting contractors’ cash-in-flow in public school building projects in Karbala, and consequently clients’ cash-out-flow as well._x000D_
The solar vortex engine (SVE) has been investigated to generate power using renewable energy. The SVE was constructed from a vortex generation engine (VGE) and solar air collector (SAC). The SVE system primarily utilizes vertical air movement. However, the airflow entering the VGE experiences an obstruction. The purpose of this paper is to propose a new design for the VGE that creates a swirling updraft capable of overcoming air obstruction and reducing energy losses. A 3D numerical model of VGE was developed to visualize vortex generation. The modeling of the VGE is carried using SOLIDWORKS software and ANSYS-FLUENT 18. The improved VGE has six vertical twisted convergence blades connected to six guide vanes to direct updraft air in an anticlockwise swirl. All blades and vanes are housed in a VGE cylinder with a diameter of 20cm and a height of 30cm. The simulation results were validated by comparing with the results obtained from the present experimental model. The simulation results match with a mean difference of less than 5% with the experimental measurements. The results of the current CFD investigation indicate that there is a gradient in air temperature and pressure within the VGE, ranging from the highest values of 314 K and 3.85 Pa to the lowest values of 308 K and 2.42 Pa, respectively. The CFD visualization shows a threefold increase in axial velocity and a fivefold increase in tangential velocity within an artificial vortex. Therefore, it can be concluded that the new VGE construction is highly efficient in generating a vortex.
A dam failure results in losses in terms of economy and infrastructure, in addition to the loss of many lives and assets. Inadequate seepage control procedures are typically the cause of seepage failure in earth-fill dams. For an earthen dam to be waterproof and to minimize seepage, non-homogeneous dams with a clay core are one kind of embankment dam used. As water moves through the dam's core, friction causes it to lose a lot of energy. Both vertical and inclined cores can be used in the design and construction of zoned embankment dams. As a result, choosing the proper materials and dimensions for the earth dam's core is critical. The main objective of this study is to investigate different seepage control strategies for an earth dam (HORAN DAM) using the Finite Element Method (FEM). We modeled and analyzed nine cases of various seepage control techniques that have been modeled and analyzed using SEEP/W, a FEM-based software. The modeling results show using chimney filters reduces pore water pressure more effectively than using toe rock and horizontal filters. Regarding seepage, trapezoidal cores perform better than inclined cores, and the milder slope is preferred over steeper core slopes. The results show when the core permeability decreases, the seepage quantity also decreases. Toe rock decreases seepage more than horizontal filters and chimney filters. Additionally, it has been shown that using a toe rock filter together with a trapezoidal core with a mild slope performs better than using a different filter and a different internal clay core shape.
This study concerns utilization of nonlinear finite element method for to evaluate the role of longitudinal soffit-bonded CFRP strips in elevating the shear behavior of RC beams without stirrups. All beams cross-sections were of 150 mm breadth and 200 mm depth, the overall length was 1500 mm with clear span 1300 mm. One beam was provided by minimum web reinforcement according to the ACI 318M-14, while the other five were without web reinforcement but externally strengthened by a variety of CFRP-strip combinations consisting of longitudinal soffit-bonded strips. The predictions of a proposed ANSYS (version 14.5) model for six of the test beams including modeling of concrete, steel rebars, CFRP strips and supports and loading steel plates, by SOLID65, LINK180, SHELL41 and SOLID185 elements, respectively, show high agreements with experimental evidence, which stands as a definite witness to the efficiency and reliability of the present numerical model.
The present work is a manual that describes the practical aspects of optimizing dental precision by virtual dentoskeletal modeling, use the precises model in virtual planning, and splint design of orthognathic surgery. A single case study is used to demonstrate the stages involved in this approach, which include acquiring CBCT scan data and digital dental models, incorporating this data into developing a virtual dentoskeletal model using superimposition process to replace the unclear teeth. Utilizes virtual assessment and three-dimensional cephalometry to diagnose the maxillofacial deformity of the patient correctly. The results of the diagnosis played a crucial role in formulating a comprehensive plan for dental alignment, which involved osteotomy and correction of bone positions. The final step is to create a personalized splint. The importance of virtual tools is highlighted in our work to optimizing dental precision, diagnose and treat maxillofacial deformities. Present a virtual planning methodology for orthognathic surgeons as well as researchers.
The current study focuses on utilizing machine learning (ML) models in optimizing and predicting laser-induced surface cold hardening in aluminum alloy 6061-O using a pulsed fiber laser. Three input features were utilized: power density (Pd), frequency (f), and pulse overlap (OV), with surface hardness as the matching aim. A set of ML models, including XGBoost and Adaptive Ensemble, was employed. The dataset was preprocessed for normalization and outlier handling, hyperparameter tuning, and assessment through the grid search and cross-validation, and model performance was evaluated using the coefficient of determination (R²) and mean square error (MSE) metrics. The Linear regression and Random Forest regression models were excluded due to their weakness in performance, exhibiting noticeable enhancement in performance of the ensemble. After excluding weak models, the results of XGBoost and Adaptive Ensemble models demonstrated great results of R2/MSE of 0.970/0.774 and 0.949/1.319, respectively. The XGBoost model occupied the first order, followed by the Adaptive Ensemble model, in improving the predictive accuracy to around 96% compared to other models.
Deep learning modeling could provide to detected Corona Virus 2019 (COVID-19) which is a critical task these days to make a treatment decision according to the diagnostic results. On the other hand, advances in the areas of artificial intelligence, machine learning, deep learning, and medical imaging techniques allow demonstrating impressive performance, especially in problems of detection, classification, and segmentation. These innovations enabled physicians to see the human body with high accuracy, which led to an increase in the accuracy of diagnosis and non-surgical examination of patients. There are many imaging models used to detect COVID-19, but we use computerized tomography (CT) because is commonly used. Moreover, we use for detection a deep learning model based on convolutional neural network (CNN) for COVID-19 detection. The dataset has been used is 544 slice of CT scan which is not sufficient for high accuracy, but we can say that it is acceptable because of the few datasets available in these days. The proposed model achieves validation and test accuracy 84.4% and 90.09%, respectively. The proposed model has been compared with other models to prove superiority of our model over the other models.