alexandria engineering journal最新文献

{"title":"A hybrid YOLOv10—Faster R-CNN framework for mobility-aid detection and traffic optimization in disability-inclusive smart cities","authors":"Mostafa A. Elhosseini ,&nbsp;Hanaa A. Sayed ,&nbsp;Rasha F. El-Agamy ,&nbsp;Amna Bamaqa ,&nbsp;Malik Almaliki ,&nbsp;Tamer Ahmed Farrag ,&nbsp;Hanaa ZainEldin ,&nbsp;Mahmoud Badawy","doi":"10.1016/j.aej.2025.08.044","DOIUrl":"10.1016/j.aej.2025.08.044","url":null,"abstract":"<div><div>Efficient transportation for individuals with mobility disabilities in smart cities remains a critical challenge: high-speed detectors such as YOLO sacrifice precision under occlusion or poor lighting. Accurate models like Faster R-CNN incur latencies exceeding 100 ms per frame and lack integrated routing for disabled users. To address these shortcomings, this study proposes a hybrid YOLOv10–Faster R-CNN framework that sequentially applies You Only Look Once (YOLOv10) (operating at 45 fps) for initial mobility-aid localization and Faster R-CNN for bounding-box refinement, with a confidence-weighted fusion module to suppress false positives without compromising recall. By augmenting this dual-stage detection pipeline with an ensemble voting classifier that predicts traffic severity from refined detections and live intelligent transportation systems (ITSs) density metrics, the proposed system delivers the first end-to-end solution for real-time, accessibility-aware route planning tailored to wheelchair and crutch users—a capability previously unaddressed by standalone object-detection or traffic-management methods. We validate our approach on three complementary datasets – real-time urban traffic feeds, a diverse mobility-aid image corpus (wheelchairs, crutches), and a wheelchair-specific subdataset – and evaluate performance through mean average precision (mAP), recall, inference latency, traffic-prediction accuracy, and disabled-user travel-time reduction. The hybrid model achieves 99.4% mAP for general mobility aids and 98.9% mAP for wheelchairs, attains 100% recall (a 23.46% increase in true-positive detections over standalone baselines), and maintains an end-to-end latency of 22 ms per frame (<span><math><mrow><mo>≈</mo><mn>45</mn><mi>f</mi><mi>p</mi><mi>s</mi></mrow></math></span>). Traffic severity is predicted with 98.2% accuracy, and the optimized routing engine reduces disabled-user travel time by 17.3% under peak congestion compared to standard shortest-path methods. In comparative experiments, our framework outperforms YOLOv10 (mAP improvement of 2.1%) and Faster R-CNN (latency reduction of 78 ms per frame), establishing a new benchmark for inclusive, real-time traffic management in disability-inclusive smart cities.</div></div>","PeriodicalId":7484,"journal":{"name":"alexandria engineering journal","volume":"129 ","pages":"Pages 1279-1298"},"PeriodicalIF":6.8,"publicationDate":"2025-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144931895","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"An advanced performance preservation method for surface acoustic wave hydrogen sensors based on graphene sensitive layers","authors":"Xuan Zhao,&nbsp;Shu Zhu,&nbsp;Xiaoqi Wu","doi":"10.1016/j.aej.2025.08.050","DOIUrl":"10.1016/j.aej.2025.08.050","url":null,"abstract":"<div><div>High-performance hydrogen sensors are essential for efficiently utilizing hydrogen energy. We developed a high-performance surface acoustic wave sensor hydrogen sensor by integrating the advantages of surface acoustic wave technology (high sensitivity, compact structure, easy integration) with the properties of graphene-based materials. The sensor uses reduced graphene oxide, synthesized by a chemical redox method, as the sensitive film on a lithium niobate piezoelectric substrate, with platinum acting as the catalyst. Graphene provides the sensing layer with its large specific surface area and excellent optical, mechanical, and electrical properties. The fabrication process of the sensitive layer was optimized to improve sensor performance. Results show the sensor responds excellently to hydrogen, achieving a high sensitivity of 0.276 kHz/ppm and a low detection limit of 2 ppm at room temperature. This performance surpasses that of conventional metal oxide sensors. However, a significant limitation is the rapid degradation of sensor performance over time, limiting its practical application. To address this limitation, we investigated the effect of environmental humidity on sensor stability. The results show the sensor retains its capability to detect low-concentration hydrogen even after six months of storage under high-humidity conditions.</div></div>","PeriodicalId":7484,"journal":{"name":"alexandria engineering journal","volume":"129 ","pages":"Pages 1223-1237"},"PeriodicalIF":6.8,"publicationDate":"2025-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144931893","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Mask-RCNN-CHFNet: An improved deep learning for 3D reverse modeling of iron tailings (SiO2) real-time melting process","authors":"Yuefang Sun ,&nbsp;Xinghui Hao ,&nbsp;Yi Shi ,&nbsp;Zhaozhuang Guo ,&nbsp;Aimin Yang","doi":"10.1016/j.aej.2025.08.038","DOIUrl":"10.1016/j.aej.2025.08.038","url":null,"abstract":"<div><div>The melting process of iron tailings is influenced by thermodynamic and kinetic factors, with particle size directly affecting the melting rate. As iron tailings absorb heat, the slag system's temperature drops and viscosity increases, making particle size and melting rate critical for temperature regulation and heat compensation. In this study, a CCD camera was used to track SiO₂, the main component of iron tailings in a high-temperature molten pool, to monitor its melting behavior. The Mask-RCNN-CHFNet model is used to perform semantic segmentation on images, and an end-to-end convex hull filtering (CHF) framework is constructed to achieve quantitative analysis of the volume change and morphological evolution of high-temperature melts. During neural network training, the loss value is 0.098. On the test set, the model achieves AP50–95 of 45.4, AP50 of 82.0, and AP75 of 40.8. 3D reverse modeling is then performed on the segmented SiO₂ regions. By combining experimental data with intelligent algorithms, the complex high-temperature melting process is translated into a computable mathematical relationship. Compared with the existing water quenching technology, continuous monitoring, tracking and tempering are carried out. This approach establishes a reliable time-sequence law, providing real-time data for iron tailings melting and improving slag cotton quality.</div></div>","PeriodicalId":7484,"journal":{"name":"alexandria engineering journal","volume":"129 ","pages":"Pages 1238-1257"},"PeriodicalIF":6.8,"publicationDate":"2025-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144931894","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Developing a new modified two–parameter Liu estimator for the gamma regression model: Method, simulation and application to health data","authors":"Muqrin A. Almuqrin ,&nbsp;Mohammed AbaOud","doi":"10.1016/j.aej.2025.08.033","DOIUrl":"10.1016/j.aej.2025.08.033","url":null,"abstract":"<div><div>The gamma regression model is one of the types of generalized linear models intended to work at the observation level and be able to handle the dependent variable, which is continuous, positive, and can often be skewed. This model is particularly beneficial in situations where the data distribution does not conform to the standard linear regression model's required normality. However, this model can suffer from multicollinearity. This paper develops a new two-parameter Liu (MTP-Liu) estimator for the gamma regression model. Further, we examine the mean squared errors of the proposed MTP-Liu estimator. In addition, we offer a few theorems to establish the relationship between the new estimators and the existing ones. To study the performance of the estimators under various forms of collinearity in the sense of the above definition, we undertake a Monte Carlo simulation exercise. In order to illustrate the practical applicability of the new estimator, we include two numerical examples using real data. The simulations and results of the real data show that the proposed MTP-Liu estimator performs better than its competitors.</div></div>","PeriodicalId":7484,"journal":{"name":"alexandria engineering journal","volume":"129 ","pages":"Pages 1212-1222"},"PeriodicalIF":6.8,"publicationDate":"2025-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144925647","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Experimental study on the structural behavior of double z-shaped steel–encased concrete composite beams","authors":"M.S. Shoukry,&nbsp;A.S. Fahmy,&nbsp;S.M. Swelem,&nbsp;A.S. Elgamasy","doi":"10.1016/j.aej.2025.08.034","DOIUrl":"10.1016/j.aej.2025.08.034","url":null,"abstract":"<div><div>This paper presents an experimental investigation into the structural behavior of a novel deck configuration utilizing double Z-shaped steel–concrete composite beams (2ZSCCBs). It is proposed as an alternative to conventional U-shaped steel–concrete composite beams (USCCBs). The 2ZSCCB consists of a plain concrete beam partially encased by double cold-formed Z-shaped steel sections, connected using threaded bolts without welding—addressing the challenges of welding thin-walled sections. The experimental program involved five full-scale beam specimens tested under a four-point bending setup. One specimen was a conventional reinforced concrete beam (BRC), used as the reference, whereas the other four were 2ZSCCBs without traditional shear or flexural reinforcement. Four key parameters were investigated: (i) diameter of bottom flange bolts, (ii) length of bottom flange bolts, (iii) presence of side bolts in the web, and (iv) use of angle connectors. Results showed significant improvements in load-carrying capacity and stiffness for the 2ZSCCB specimens compared to the reference beam. Bolt connectors in the tension zone were especially effective. The ultimate load capacity of the 2ZSCCBs was approximately three times higher than that of the BRC beam with the same cross-section. The use of 12 mm diameter, 80 mm long bolts (B2) at the bottom flange notably enhanced ultimate strength, increased strain energy absorption, developed a tiny relative slip between the bottom flange of 2Z-shaped steel and encased concrete, and changed the failure mode from flexural to shear-compression failure. Additionally, the inclusion of side bolts (B3) further enhanced performance by preventing bolt shear failure and improving energy absorption.</div></div>","PeriodicalId":7484,"journal":{"name":"alexandria engineering journal","volume":"128 ","pages":"Pages 1231-1244"},"PeriodicalIF":6.8,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144925482","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Fabrication of graphene/MoS2 composite material for enhanced electrochemical sensing of carcinoembryonic antigen in lung cancer detection","authors":"Ke Zhang ,&nbsp;ZhiQian Zhao ,&nbsp;Jing Huang ,&nbsp;Hui Fu ,&nbsp;Sicong Jiang ,&nbsp;Min Shi","doi":"10.1016/j.aej.2025.08.041","DOIUrl":"10.1016/j.aej.2025.08.041","url":null,"abstract":"<div><div>Carcinoembryonic antigen (CEA) is a widely recognized tumor biomarker that plays a critical role in the early detection and prognosis of several cancers, particularly lung, colorectal, and breast cancer. Accurate and sensitive quantification of CEA levels in biological samples is vital for timely diagnosis and effective treatment monitoring. In this study, we present the development and characterization of a novel electrochemical immunosensor utilizing a three-dimensional graphene/MoS₂ composite for detecting CEA. The composite material was synthesized via a one-step hydrothermal process at 200°C and comprehensively characterized using scanning electron microscopy (SEM), X-ray diffraction (XRD), Raman spectroscopy, and X-ray photoelectron spectroscopy (XPS) analysis. The hierarchical structure combined a highly porous graphene network with flower-like MoS₂ nanoflowers, demonstrating a 2.8-fold increase in effective electrochemical surface area compared to bare electrodes. Under optimized conditions, the immunosensor achieved sensitive CEA detection with a linear response range of 0.001–150 ng/mL and a detection limit of 0.0006 ng/mL. The sensor showed outstanding selectivity in distinguishing CEA from common interfering substances, with signal fluctuations of less than 5 %. Clinical validation using human serum samples showed strong correlation with standard ELISA methods (r = 0.992) and exceptional recovery rates between 94.2 % and 107.0 %. The developed immunosensor exhibited remarkable stability, maintaining 96 % of its initial response after 1 month of storage, while requiring minimal sample volumes (10 μL) and significantly reduced analysis time (40 min).</div></div>","PeriodicalId":7484,"journal":{"name":"alexandria engineering journal","volume":"128 ","pages":"Pages 1219-1230"},"PeriodicalIF":6.8,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144922607","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Maximum power tracking of grid integrated PV system with power electronic converters: A hybrid COA-QNN approach","authors":"R. Aandal,&nbsp;A. Ravi","doi":"10.1016/j.aej.2024.03.055","DOIUrl":"10.1016/j.aej.2024.03.055","url":null,"abstract":"<div><div>To optimize solar PV power connected to the grid, a new power electronic setup with maximum power point tracking is necessary. This technology minimizes losses and maximizes solar output by employing direct energy transfer to the grid for rated power, while surplus power is directed to a converter for DC loads. So this manuscript proposes a hybrid approach for extracting the maximum power of Photovoltaic with high gain converter. The proposed topology is quantum neural network (QNN) and the combination of Cheetah Optimization Algorithm (COA), known as COA-QNN. This main goal of COA-QNN method is to regulate the active-power needs of loads using solar power generated, and after satisfying the load-demand, surplus power is supplied to the grid. COA is used to optimize the MPPT and QNN is used to forecast the optimal control signal of the converter. After that, the COA-QNN methodology is completed in the MATLAB platform and contrasted with other current approaches. The COA-QNN technique offers superior performance in terms of power-quality (PQ), stability, and settling time compared to other controllers. Simulation analysis shows low total harmonic distortion (THD) at 1.7%, high efficiency at 99.52%, and minimal error at 0.01%, demonstrating its effectiveness over existing methods.</div></div>","PeriodicalId":7484,"journal":{"name":"alexandria engineering journal","volume":"128 ","pages":"Pages 1203-1218"},"PeriodicalIF":6.8,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144920352","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Voting-based ensemble classifiers model on ransomware detection for cybersecurity driven iiot in cloud computing infrastructure","authors":"Fatimah Alhayan ,&nbsp;Monir Abdullah ,&nbsp;Asma Alshuhail ,&nbsp;Munya A. Arasi ,&nbsp;Othman Alrusaini ,&nbsp;Sultan Alahmari ,&nbsp;Abdulsamad Ebrahim Yahya ,&nbsp;Samah Al Zanin","doi":"10.1016/j.aej.2025.08.028","DOIUrl":"10.1016/j.aej.2025.08.028","url":null,"abstract":"<div><div>The smart factory environment was converted into an Industrial Internet of Things (IIoT) environment because it is an open approach and interconnected. This has made smart manufacturing plants susceptible to cyberattacks and has openly led to real damage. Many cyberattacks targeting smart factories were controlled using malware. So, a solution that effectively identifies malware by analyzing and monitoring network traffic for malware threats in a smart factory IIoT environment is vital. However, attaining precise real malware recognition in such environments was challenging. Ransomware is a kind of malware that encodes the victim's data and demands payment to restore access. The effective recognition of ransomware attacks is highly based on how its features are learned and how accurately its activities are recognized. This article proposes a Voting-Based Ensemble Classifiers Model on Ransomware Detection for Cybersecurity (VBECM-RDCS) technique for IIoT in cloud computing infrastructure. The VBECM-RDCS technique utilizes the squirrel search algorithm (SSA) model for feature subset selection. Furthermore, a voting ensemble classifier for ransomware detection employs the convolutional autoencoder (CAE) integrated with bidirectional gated recurrent unit (Bi-GRU). Finally, the walrus optimization algorithm (WAOA) model is implemented for optimum hyperparameter tuning to improve the recognition performance of ensemble methods. The simulation study of the VBECM-RDCS technique is examined under the ransomware detection dataset. The VBECM-RDCS technique attained a superior accuracy value of 99.76 % under 2000 training epochs, outperforming existing models in the experimental evaluation.</div></div>","PeriodicalId":7484,"journal":{"name":"alexandria engineering journal","volume":"129 ","pages":"Pages 1198-1211"},"PeriodicalIF":6.8,"publicationDate":"2025-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144920240","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"SKIN-ORBIT: A bio-mimetic oscillatory resonance-based inference topology for universal skin lesion segmentation","authors":"Anjali Thachankattil ,&nbsp;Abhishek Sujith","doi":"10.1016/j.aej.2025.08.012","DOIUrl":"10.1016/j.aej.2025.08.012","url":null,"abstract":"<div><div>Accurate segmentation of skin lesions is a foundational task in dermatology, essential for early diagnosis, treatment planning, and long-term monitoring of skin conditions. However, current state-of-the-art models—primarily based on convolutional neural networks and transformers—depend on rigid feature hierarchies and large-scale annotated datasets. These architectures struggle to generalize across diverse lesion morphologies, rare dermatological presentations, and variations in skin tone or imaging modality. In this work, we introduce SKIN-ORBIT (Spectral-Kinetic Inference Network with Oscillatory Resonance-Based Inference Topology), a biologically inspired, signal-centric segmentation framework that redefines how spatial patterns are modeled. Rather than relying on fixed receptive fields or attention over patches, SKIN-ORBIT treats each pixel as a localized oscillatory emitter, producing dynamic waveform signals over time. These signals propagate through a deformable resonance field, where zones of persistent phase coherence emerge as lesion regions—identified via stable, constructive interference patterns. The framework is anchored by two core components: the Kinetic Deformation Unit (KDU), which modulates spatial topology through dynamic elastic distortions driven by pixel-wise kinetic energy profiles, enabling continuous and topology-aware field reshaping; and the Oscillatory Field Propagation (OFP) module, which replaces convolution and attention with harmonic signal propagation, simulating wavefront interactions across the spatial domain without predefined kernels. To facilitate unsupervised learning, we propose a novel Cross-Modal Resonance Coherence Loss (CMRCL), which enforces phase alignment across visible, ultraviolet (UV), and infrared (IR) imaging modalities. CMRCL computes spectral-phase divergence in the latent oscillatory domain and minimizes incoherence between modality-specific representations, encouraging shared structural resonance. SKIN-ORBIT was trained and validated on a dataset of 15,318 cross-spectrum dermatological images. It achieved 98.7% segmentation accuracy, a Dice coefficient of 0.92, Jaccard index of 0.86, sensitivity of 0.91, specificity of 0.97, and a Hausdorff Distance of 5.6 pixels—substantially outperforming traditional CNN and transformer-based models. These results demonstrate that SKIN-ORBIT provides a disruptive alternative to conventional architectures, introducing a physics-driven, annotation-efficient paradigm for robust and modality-agnostic skin lesion segmentation.</div></div>","PeriodicalId":7484,"journal":{"name":"alexandria engineering journal","volume":"128 ","pages":"Pages 1177-1202"},"PeriodicalIF":6.8,"publicationDate":"2025-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144917521","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Intelligent fuzzy configuration channels: A novel self-tuning framework for complex system modeling","authors":"Muhammad Shamrooz Aslam ,&nbsp;Anqi Wu ,&nbsp;Mingyuan Qian ,&nbsp;Hazrat Bilal ,&nbsp;Abid Yahya ,&nbsp;Irfan Anjum Badruddin ,&nbsp;Sarra Ayouni","doi":"10.1016/j.aej.2025.08.031","DOIUrl":"10.1016/j.aej.2025.08.031","url":null,"abstract":"<div><div>To enhance the fuzzy inference capability of Stochastic Configuration Networks (SCNs), we propose a new neuro-fuzzy model based on Fuzzy Stochastic Configuration Networks (F-SCNs). Unlike traditional SCNs, F-SCNs replace hidden layers with Takagi–Sugeno (T–S) fuzzy inference modules, enabling them to process fuzzy input data, generate meaningful fuzzy rules connected to the output layer and perform reasoning more effectively. A key challenge is establishing a framework that ensures robust modeling performance. To address this, we introduce Self-Organizing Fuzzy Stochastic Configuration Networks (SO-FSCNs) with a Hybrid Learning Algorithm (HL-SOFSCN) for nonlinear system modeling. Additionally, we propose a growing-and-pruning productive approach that refines fuzzy rules based on network knowledge and rule firing intensity. The learning performance of fuzzy rules is improved using error correction algorithms with appropriate initial parameters, while redundant rules with low firing strength are eliminated to maintain a compact structure. Furthermore, we develop a hybrid learning algorithm that integrates a least squares method for parameter tuning with an enhanced second-order optimization approach, treating linear and nonlinear parameters separately to improve learning efficiency. The model is validated using artificial datasets, demonstrating that SCNs achieve a satisfactory predictive accuracy compared to alternative models.</div></div>","PeriodicalId":7484,"journal":{"name":"alexandria engineering journal","volume":"129 ","pages":"Pages 1185-1197"},"PeriodicalIF":6.8,"publicationDate":"2025-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144917050","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}