Arabian Journal for Science and Engineering最新文献

Acute lymphoblastic leukemia (ALL) is a critical hematological malignancy where prompt and accurate diagnosis is essential for effective treatment. This study proposes a novel methodology combining efficient image segmentation with a stacked ensemble of pre-trained convolutional neural networks (CNNs) and XGBoost (FXGBoost) for accurately classifying peripheral blood smear (PBS) images. The used dataset includes 3,256 annotated PBS images from 89 patients covering benign and malignant cases. The proposed model achieves outstanding diagnostic performance, with an accuracy of 99.39% and an F1-score of 0.9963, outperforming several existing deep learning and ensemble methods. Statistical validation using confidence intervals and Tukey honestly significant difference (HSD) testing confirms the results’ significance. Comparative evaluations also include transformer-based models, and inference time per image (ITP) analysis, which is provided to assess computational feasibility. To ensure clinical applicability, we incorporate model interpretability using Gradient-weighted Class Activation Map (Grad-CAM) and address challenges such as class imbalance and overfitting. We acknowledge limitations related to dataset scope and generalizability, and future directions include domain adaptation, explainability enhancement, and real-time deployment. This work contributes a robust and clinically relevant framework for ALL diagnoses, demonstrating how AI-based tools can augment medical decision-making in real-world settings.

The increasing prevalence of social media addiction among adolescents has become a significant concern, often exceeding other harmful behaviors. Evaluating the addictive potential of various platforms is challenging due to the diversity of applications and the subjectivity inherent in expert judgments. To address these complexities, this study proposes a novel distance measure within the Pythagorean fuzzy set framework, designed to overcome the limitations of existing measures, which often yield inaccurate or inconsistent results in specific contexts. To support the mathematical validity of the proposed measure, its geometric behavior is analyzed, and a comparative study with existing distance functions is conducted using numerical examples. A comprehensive multi-criteria decision-making framework is then developed, incorporating the method based on the removal effects of criteria (MEREC) for objective weighting and stepwise weight assessment ratio analysis (SWARA) for subjective weighting. These weights are integrated using the technique for order of preference by similarity to the ideal solution (TOPSIS) to rank social media platforms based on their addiction potential. Sensitivity and comparative analyses confirm the robustness, reliability, and consistency of the proposed approach. The study concludes by demonstrating the advantages of the framework and identifying potential directions for future research.

Unmanned aerial systems equipped with thermal imaging cameras are vital for effective emergency response, especially in firefighting scenarios. These drones require high stability, rapid responsiveness, and precise positioning, all of which depend on advanced control systems. This study introduces an innovative approach using an Interval Genetic Algorithm to optimize Proportional–Integral–Derivative (PID) and H₂ controllers, enhancing the performance of thermal imaging drones for emergency response and surveillance applications. A comprehensive mathematical model was developed to simulate quadcopter dynamics in both “ + ” and “X” configurations. The challenges of PID tuning and the limitations of H₂ controllers in real-world environments were addressed, resulting in improved drone stability and control under demanding conditions. The results demonstrate a significant enhancement in altitude control and motor speed stabilization, with an average increase of 20% in control precision and a 15% reduction in system response time compared to traditional control methods. These findings advance drone technology by providing more reliable and efficient tools for emergency responders.

The increasing need for efficient CO₂ capture methods has led to the exploration of NaOH-modified nanoclay montmorillonite as an adsorbent. This study utilizes response surface methodology (RSM) and artificial neural networks (ANN) for modelling and optimizing CO₂ adsorption. Data from previous experiments were used to develop the models. RSM employed a central composite design (CCD) and was evaluated using analysis of variance (ANOVA), while ANN models were created with various training methods (Levenberg–Marquardt, Bayesian regularization, and scaled conjugate gradient). The ANN model using Bayesian regularization (R² = 0.98719; MSE = 0.00049) demonstrated the best predictive accuracy. ANOVA revealed that NaOH concentration, pressure, and temperature significantly affected CO₂ adsorption capacity. Sensitivity analysis confirmed NaOH concentration as the most influential variable. Optimization results indicated that maximum CO₂ adsorption (72.873 mg/g) occurs at 35 °C, 9 bar pressure, 5 mol/L acid concentration, and 30% w/w NaOH. This study effectively applies RSM-CCD and ANN models for optimizing CO₂ adsorption with NNM adsorbent.

In this study, the effects of intercritical annealing (ICA) temperature, martensite volume fraction (MVF), and martensite grain size (MGS) on the microstructure and mechanical properties of pre-alloyed powder metallurgy (PM) steel parts subjected to dual-phase (DP) treatment were investigated. Sintering (S), normalization (N), quenching (Q), and DP heat treatments were applied to the parts manufactured by warm pressing method. Afterward, mechanical testing and microstructure characterizations were carried out. A dual-phase microstructure with a homogeneous distribution in pre-alloyed PM steel parts was successfully produced with DP heat treatment. MVF and MGS increased as the ICA temperature increased. At the same ICA temperature, small MGS caused low MVF. DP heat treatment increased the strength and hardness of sintered pre-alloyed PM steel parts but decreased their ductility. As MVF increased at different ICA temperatures, strength and hardness increased but ductility decreased. In these samples, the highest strength of 241 MPa and the highest hardness of 174 HBW were obtained in SNDP-750 sample containing 48.87% MVF. This sample exhibited a low uniform elongation (0.68%). At the same ICA temperatures, as MGS of the samples got smaller, their strength and hardness increased but they exhibited a similar ductility. The highest strength of 242 MPa and the highest hardness of 169 HBW were observed in the SQDP-740 sample containing 2.91 μm MGS. This sample exhibited a uniform elongation of 2.15%. The results showed that DP heat treatment improved the mechanical properties of sintered pre-alloyed PM steels.

Pharmaceutical contaminants in wastewater represent a growing environmental concern due to their persistence and potential ecological impacts. This study proposes a sustainable approach by developing copper-doped titanium dioxide (Cu–TiO₂) nanoparticles for the effective removal of cetirizine hydrochloride (CTZ-H), a widely used antihistamine frequently detected in effluents. Cu–TiO₂ photocatalysts were synthesized via the impregnation method with varying copper loadings (0.5–3 wt%) and thoroughly characterized. Their photocatalytic performances were evaluated under natural sunlight, considering the effects of dopant concentration, solution pH, catalyst dosage, and pollutant concentration. Optimal degradation efficiency of 93% was achieved using 0.5 wt% Cu–TiO₂ at pH 4.9, a catalyst dose of 100 mg/L, and an initial CTZ-H concentration of 10 mg/L. Kinetic modeling indicated a pseudo-first-order reaction with a rate constant (k_CTZ-H) of 0.025 min⁻¹. Phytotoxicity assays using lentil seeds demonstrated significantly reduced toxicity of the treated water, supporting its potential for safe environmental discharge or reuse. Additionally, the Support Vector Machine (SVM) model coupled with the Improved Grey Wolf Optimizer (IGWO) accurately predicted photocatalytic degradation outcomes, with a correlation coefficient (R) of 0.9999. These results underscore the promise of Cu-doped TiO₂ as an efficient and eco-friendly photocatalyst for mitigating pharmaceutical pollution in aquatic environments.

The fata morgana algorithm (FATA) is a novel swarm intelligence optimization algorithm, and its design inspiration stems from the unique natural phenomenon of mirages. To overcome the premature convergence of the FATA, which leads to its entrapment in local optimal solutions, an improved FATA (IMFATA) is proposed in this paper based on a circle chaotic map and adaptivee t-Distribution perturbation mutation. The IMFATA is validated against the FATA on 23 benchmark functions and CEC2021 test functions and compared with the honey badger algorithm (HBA), beluga whale optimization (BWO), the whale optimization algorithm (WOA),the goose algorithm(GOOSE), the dung beetle optimizer (DBO), and the aquila optimizer (AO). The experimental results show that the IMFATA can effectively improve its computational accuracy and convergence speed, and its global optimization ability is superior to that of the other algorithms. Finally, the IMFATA is applied to optimize the parameters of a support vector machine (SVM) for Dendrobium grade classification. The experimental results show that the classification accuracy (F1 value) achieved for the Dendrobium grades optimized by the IMFATA is relatively high, fully demonstrating the superiority of the IMFATA in practical engineering applications.

Traditional deep learning (DL) models face key limitations in bearing fault detection within wireless sensor networks (WSNs). They require high computational power and large labeled datasets–resources often unavailable in WSNs due to energy, memory, and processing constraints. The scarcity of some bearing fault classes limits the availability of labeled data, complicating effective model training. Additionally, DL models struggle to generalize across varying operating conditions and sensor types, limiting their robustness. Such constraints highlight the inadequacy of conventional DL in WSN-based fault diagnosis and support the use of advanced DL technique compatible with the resource limitations of WSN platforms. This work presents bearing network BearNet, a novel technique designed to enhance bearing fault diagnosis, that strengthens the functionalities of WSN technology in detecting bearing fault by using the concept of transfer learning (TL) with the pre-trained Yet another audio mobilenet network (YAMNet) neural network. Our method converts sensor data into Mel spectrograms, which serve as critical features for training our neural network model. The application of pre-trained YAMNet, along with our tailored target DL model, allows for efficient and accurate classification of different classes of bearing faults. The proposed architecture addresses the constraints of WSNs, such as limited processing capabilities, by utilizing only the unfrozen and additional layers during validation and testing, rather than the entire YAMNet model, thereby optimizing resource usage. Empirical results conducted on the CWRU and MFPT datasets demonstrate that our BearNet technique achieves high diagnostic accuracy, showing significant improvements of 3.1% and between 0.02–5.26% compared to pure YAMNet and state-of-the-art models, respectively. This validates its effectiveness for practical condition monitoring applications across various industrial settings.

Activation of peroxymonosulfate (PMS) by Co and Cu doped zeolitic imidazolate framework, ZIF-8 s for degradation of sulfamethazine (SMZ) was investigated. It was observed that combination of the two metals increased the PMS activation efficiency by using the activity of both metal redox pairs to increase the production of sulfate and hydroxyl radicals. Different characterization techniques, including nitrogen (N₂) adsorption, Fourier-transform infrared (FTIR), scanning electron microscopy energy-dispersive spectroscopy (SEM–EDS mapping), X-ray photoelectron spectroscopy (XPS), and thermogravimetric analysis (TGA), were used to characterize the synthesized catalysts, ZIF-8, Cu/ZIF-8, and Co/ZIF-8. No structural differences were observed in catalysts obtained after bimetallic synthesis. The BET surface area was calculated as 1145, 742, 945 m²/g for ZIF-8, Cu/ZIF-8, and Co/ZIF-8, respectively. Under reaction conditions of 0.1 g/L PMS dosage, 0.5 g/L catalyst dosage, and original pH, sulfamethazine degradation after 30 min was 10.5% with PMS alone (no catalyst), 28.0% with ZIF-8, 33.9% with Cu/ZIF-8, and 58.4% with Co/ZIF-8, clearly demonstrating the superior catalytic performance of Co/ZIF-8. Using Box–Behnken design and response surface methodology, reaction parameters were optimized in the presence of the most efficient catalyst, Co/ZIF-8. The sulfamethazine removal was optimized at 0.55 g/L catalyst dosage, pH 5.2 and 0.15 g/L PMS dosage. Under the optimal reaction conditions 67.3% sulfamethazine removal was achieved within 30 min in the presence of Co/ZIF-8 as catalyst. Scavenging experiments showed that the dominant reactive oxygen species was hydroxyl radicals. According to the phytotoxicity test performed by using L. sativum, 35.9% growth inhibition was evaluated.

Breast cancer remains a leading cause of cancer-related mortality globally, driving the need for novel effective and less toxic therapeutic agents. This study explores the synthesis and characterization of bioactive compounds: 1-(4-methoxyphenyl)-N-(p-tolyl)methanimine (MPTI), N-(4-methylphenyl)benzamide (MPB), and 4-methyl-N-(p-tolyl)benzenesulfonamide (MTS), and their incorporation into a PMMA/PVP polymer matrix for potential anticancer applications. Morphological analysis of the PMMA/PVP-loaded agents via SEM depicts structural modifications in the PMMA/PVP nanofibrous matrix upon incorporation of the bioactive agents. The FTIR analysis of the synthesized compounds before and after loading into the 7PMMA:3PVP nanofibers reveals successful incorporation of MPTI, MPB, and MTS, with characteristic absorption bands confirming their molecular structures and interactions within the polymeric blend. Moreover, XRD diffractograms showed a transition to an amorphous state upon incorporation of the synthesized compounds into the polymer blend confirming full encapsulation. In vitro release studies showed a sustained release profile of the bioactive agents, with initial burst releases observed over a period of 3 days. Cytotoxicity assays against the MCF-7 breast cancer cell line revealed significant concentration-dependent effects, with MTS exhibiting the highest efficacy. Notably, the PMMA/PVP matrix reduced the cytotoxicity of the formulations, suggesting a protective effect that enhances safety. The findings indicate that the PMMA/PVP system may serve as an effective platform for delivering these bioactive agents for anticancer applications.