Arabian Journal for Science and Engineering最新文献

Machine learning-based IDSs have demonstrated promising outcomes in identifying and mitigating security threats within IoT networks. However, the efficacy of such systems is contingent on various hyperparameters, necessitating optimization to elevate their performance. This paper introduces a comprehensive empirical and quantitative exploration aimed at enhancing intrusion detection systems (IDSs). The study capitalizes on a genetic algorithm-based hyperparameter tuning mechanism and a pioneering hybrid feature selection approach to systematically investigate incremental performance improvements in IDS. Specifically, our work proposes a machine learning-based IDS approach tailored for detecting attacks in IoT environments. To achieve this, we introduce a hybrid feature selection method designed to identify the most salient features for the task. Additionally, we employed the genetic algorithm (GA) to fine-tune hyperparameters of multiple machine learning models, ensuring their accuracy in detecting attacks. We commence by evaluating the default hyperparameters of these models on the CICIDS2017 dataset, followed by rigorous testing of the same algorithms post-optimization through GA. Through a series of experiments, we scrutinize the impact of combining feature selection methods with hyperparameter tuning approaches. The outcomes unequivocally demonstrate the potential of hyperparameter optimization in enhancing the accuracy and efficiency of machine learning-based IDS systems for IoT networks. The empirical nature of our research method provides a meticulous analysis of the efficacy of the proposed techniques through systematic experimentation and quantitative evaluation. Consolidated in a unified manner, the results underscore the step-by-step enhancement of IDS performance, especially in terms of detection time, substantiating the efficacy of our approach in real-world scenarios.

Hybrid nanofluids are a type of nanofluid that is created by combining two different types of nanoparticles with a traditional fluid. These nanofluids have unique physicochemical properties that make them more effective at transferring heat than traditional nanofluids. This research paper focuses on predicting thermal and energy transport in non-Newtonian biomagnetic hybrid nanofluids that contain gold and silver nanoparticles, using Gaussian process regression (GPR). The study uses blood as the traditional fluid and incorporates the effects of thermal radiation, thermophoresis, Brownian motion and activation energy into the model equation. The governing nonlinear partial differential equations are simplified to a set of ordinary differential equations using similarity replacements. The shooting method, along with the Runge–Kutta-Fehlberg fourth–fifth-order scheme, is used to solve the transformed equations using MATLAB. The results of the study are presented through figures and tables, which include the coefficient of skin friction, Nusselt number, Sherwood number and motile microbe’s flux, illustrated with surface plots. The GPR model is developed using four basic function kernels (squared exponential, exponential, rational quadratic and matern32 functions) and evaluated using statistical indicators such as RMSE, MSE, MAE and R. The predicted results and simulated numerical values are in good agreement with the coefficient of determination (R²) of 0.999999 for all parameters. The study also finds that GPR models with exponential kernel functions outperform other kernel functions in both the Oldroyd-B and Casson hybrid nanofluid data sets. However, the findings indicate that nanofluids and hybrid nanofluids have superior thermal qualities and stability, making them promising candidates for various thermal applications including solar thermal systems, automotive cooling systems, heat sinks, engineering, medical areas and thermal energy storage.

Local morphometric variables (LMVs) are frequently found as weaker predictors than other environmental covariates in digital soil mapping. This study tested and evaluated the performance of a hybrid approach combining gradient boosted regression trees (GBRT) and regularized regression (RR) algorithms in predicting soil textural fractions using a set of LMVs in Khuzestan province, Iran. Here five LMVs (slope gradient, slope aspect, horizontal curvature, vertical curvature, and contour geodesic torsion) were derived from a spheroidal equal-angular DEM as original predictors. The results demonstrated that the hybrid approach improved prediction accuracy for sand, clay, and silt contents by an average of 56% compared to the GBRT models. The importance analysis revealed the significant contribution of tree-based variables obtained from decomposing GBRT models in predicting soil textural fractions. This approach could be recommended for digital soil mapping, particularly in situations of limited environmental covariates or geomorphometric techniques that cannot be easily applied.

Polymer nanocomposites have been employed for various applications, including biocompatible biomedical devices, electronic devices, UV shielding, and thermal management. There is a pressing need to develop comprehensive characterization approaches that can assess the overall performance of these materials under irradiation conditions, encompassing a broader range of mechanical properties beyond those traditionally studied. In this context a hybrid polymer nanocomposite was developed using Polyvinyl Alcohol, glutaraldehyde, Silver, and Graphene Oxide nanoparticles through a straightforward in situ chemical reduction process. These prepared samples were subjected to varying doses of gamma radiation, ranging from 0 to 10 kGy, to investigate alterations in their structural and mechanical properties. To validate the elemental composition and functional groups present in both unirradiated and irradiated nanocomposites, EDX and FTIR spectra were employed. The investigation to the mechanical characteristics of these samples. In unirradiated samples, elongation at break (ϵ_f) was determined to be 134.67 ± 1.45%, while radiation exposure resulted in an increase in the ϵ_f to 175.33 ± 8.01%. Tensile strength (σ_ult) initially declined for the 2 kGy exposure but increased at 5 kGy, only to decrease again with further dose increments. Remarkably, the material exhibited increased toughness as the dose reached 5 kGy, with a measured value of modulus of toughness (MT) at 55.30 ± 6.09 J/m³. These findings shed light on the impact of gamma radiation on the structural and mechanical properties of the polymer nanocomposite material.

Abstract

This study has been done to investigate the behavior of water-based hybrid nanofluid impinges on a stretching sheet at arbitrary inclination angles. The velocity slip and convective heat transfer are considered at the sheet’s surface. This problem formulation consists of Al (_2) O (_3) and Cu as nanoparticles with water as a base fluid. Some scaling variables are used for constructing ordinary differential equations from partial differential equations. The resulting equations are solved using bvp4c fourth-order boundary value solver in MATLAB. Graphical representations of the fluctuations in velocity, temperature, Nusselt number, and shear stress components are shown with important physical parameters. The variation in Nusselt number and shear stress components are displayed for different impinging angles of the fluid. When inclined angles are increased from (15^circ ) to (60^circ ) along with a change in the Biot number from 1 to 4, the rate of heat transmission grows from 6.15% to near 10%. Additionally, under the same angle elevation, the Nusselt number increases from 5.8% to 12.56% when the slip parameter’s value is increased from 1 to 4.

This article describes a research study on an electromechanical system with saturation, where a fuzzy hybrid controller with integral action and anti-windup is applied. The study focuses on implementing this Integral Fuzzy Logic Controller (IFLC) on a Field-Programmable Gate Array (FPGA) board. The fuzzy controllers, known for their effectiveness in handling disturbances and saturations, are used in a parallel structure. To optimize the performance of the controller, the Particle Swarm Optimization (PSO) technique is employed to tune the membership functions and feedback loop gains. The complex algebraic concepts and Type 1 fuzzy logic algorithms are transformed into mathematical equations suitable for VHSIC Hardware Description Language (VHDL). The proposed controller is co-simulated using Vivado and Xilinx® System Generator (XSG) tools on both software and hardware platforms. The utilization of fixed-point data propagation in the controller's structure ensures optimized implementation methods. The performance index of our controller surpasses that of a conventional Proportional-Integral-Derivative (PID) controller, demonstrating superior efficacy in regulating the system dynamics. To verify the efficacy of the proposed control strategy, a thorough comparison is done using control simulations between it and previous PID systems. The results show a 31% decrease in speed overshoot.

High development cost of shale fields produced with multi-fractured well systems prompts for improved and faster production forecasting tools. This study advances the use of a Gaussian pressure transient-based reservoir model (GRM). In this new simulator, the migration of reservoir fluids is fully controlled by the hydraulic diffusivity; the value of which can be initially estimated for any particular reservoir by history-matching a Gaussian decline curve to early production data. In a next step, the reservoir model based on the Gaussian pressure transient will compute—from the bottomhole pressures in the well system (imposed by the engineering intervention on the initial reservoir pressure)—the spatial and temporal advance of the pressure depletion and fluid flow near the multistage fractured wells. Real-world data from the Hydraulic Fracture Test Site-1, Midland Basin (West Texas), is utilized to validate the Gaussian solutions in comparison with a commercial simulator through history-matching and a comprehensive sensitivity analysis. The validated GPT method allows for fast iteration of well productivity sensitivity to the placement and orientation of the hydraulic fractures, allowing for proper planning to optimize field development plans.

There is a growing trend toward employing sustainable materials to address the drawbacks of traditional construction materials. This experimental study explores the utilization of basalt and steel fibers, both independently and in combination, alongside fly ash and desert sand. The findings reveal that the introduction of further basalt fibers led to a reduction in concrete workability, density, and compressive strength. The optimal compressive strength for concrete made from desert sand was achieved in the mixed concrete incorporating 1% steel fibers, measuring at 50.6 MPa. Meanwhile, the highest flexural and tensile strengths were observed in a concrete mixture of 0.3% basalt fiber and 1% steel fiber, measuring 7.35 MPa and 4.6 MPa. Scanning Electron Microscopy, Energy Dispersive Spectroscopy, and X-ray Diffraction tests were conducted to examine the concrete microstructure. The results demonstrate that including a low content of hybrid steel and basalt fibers significantly improved the concrete microstructure. This study recommends conducting further studies to investigate the durability of concrete mixtures containing desert sand and basalt fibers and enhance sustainability in the construction industry.

This paper proposes a novel stabilizing control method aimed at overcoming the instability challenges posed by the negative incremental resistance characteristics of a constant power load (CPL) within an autonomous microgrid (MG). The proposed stabilization technique integrates a power derivative-integral term with conventional droop control, strategically applied to enhance the MG's dynamic stability in the presence of CPL. The considered MG model, encompassing three inverter-based distributed generations (DGs), a constant impedance load (CIL), and CPL, is meticulously developed and simulated using MATLAB environment. Phase Locked Loop (PLL) is employed to synchronize the CPL with MG. The proposed controller is a key highlight, featuring optimally designed and tuned controller parameters for all DGs, CPL, and PLL. Particle Swarm Optimization (PSO) and Genetic Algorithm (GA) are employed to address the challenges linked to the laborious tuning process of controllers. The simulation results, which include scenarios involving three-phase faults and step changes, provide compelling evidence of the proposed controller's superior performance compared to conventional droop scheme. Furthermore, a comparative analysis is conducted to affirm and quantify the enhancements achieved through the proposed modified droop PSO-based MG controller concerning transient response. The results obtained emphasize the effectiveness of the proposed approach in simultaneously minimizing both overshoot and settling time. In comparison with the conventional controller, the proposed controller demonstrates a substantial decrease in percentage overshoot for the active power of DG3 and DC voltage of the CPL, with values of 93.89 and 99.9%, respectively. The corresponding improvements in settling time are notable, showcasing reductions of 83.11% for the active power of DG3 and 66.1% for the DC voltage of the CPL. When compared to the GA-based controller, the proposed controller exhibits significant percentage overshoot reductions for and DC voltage of the CPL, achieving 79.42 and 99.8%, respectively. Additionally, the settling time records noteworthy improvements, with reductions of 76.19% for the active power of DG3 and 57.57% for the DC voltage of the CPL. To further validate the real-world applicability and effectiveness of the proposed method, a real-time digital simulator (RTDS) is employed. The RTDS experiments results confirm the proposed scheme's ability to enhance MG stability, substantiating the simulation findings. This holistic approach, encompassing theoretical modeling, simulation studies, and real-time validation, establishes the proposed stabilizing control method as a promising and effective solution for mitigating instability issues associated with CPL in autonomous MGs.

Both academics and the IT industry are now researching the Internet of Things and software-defined networks. They have received a number of criticisms in the SD-IoT due to their novelty. One of the 5 G technologies that makes it possible to construct complex, controllable, economical, and adaptive networks is software-defined networking (SDN). In contrast, edge computing (EC) uses data from sensors, network switches, or other devices to automatically do analytical computing rather than waiting for the data to be sent back to a centralised data repository. This article offers a study on feature selection using an ensemble of filter methods to create a lightweight IDS for SD-IoT edge devices that support OpenFlow in order to defend against such attacks. To create the ensemble of filter methods, three filter-based methods, namely Pearson’s correlation coefficient (PCC), mutual information (MI), and Fisher’s score, have been used. The features selected by this ensemble is sent to the ensemble of classifiers called stack of the classifiers that comprises of support vector machine (SVM) and K-nearest neighbour (KNN) at level ’0’ and logistic regression (LR) at level ’1’. To check the effectiveness of the selected features, stack of the classifiers and individual classifiers are trained and tested with ’All’ and ’Selected’ features, and then their performances are compared. Two datasets, the BoT-IoT dataset and the TON-IoT dataset, were utilised to complete this work. The performance is compared under some performance measuring metrics, namely recall, accuracy, FAR, F1, precision, CKC, and prediction time. It has been discovered that classifiers perform better when trained with selected features rather than all the features. Also, it is discovered that stack of the classifiers with chosen features outperforms all individual classifiers, hence it is chosen for deployment in OpenFlow enabled edge devices of the SD-IoT data plane where it can identify and counteract threats in real-world settings. This offers the SD-IoT distributed attack detection approach.