Engineering reports : open access最新文献

{"title":"Neural Topic Generation Utilizing Attention Mechanisms With Transformer-Based Embeddings for Root-Cause Analysis of Manufacturing Defects in Electronic Products","authors":"Vutivi Mabasa,&nbsp;Uche A. K. Chude-Okonkwo,&nbsp;Babu S. Paul","doi":"10.1002/eng2.70191","DOIUrl":"https://doi.org/10.1002/eng2.70191","url":null,"abstract":"<p>Root-cause analysis (RCA) is a critical process for identifying and mitigating manufacturing defects, particularly in the electronics industry, where minor issues can lead to significant operational and financial consequences. Traditional approaches to RCA, relying heavily on manual inspections or rule-based systems, often fail to scale with the growing complexity and volume of defect-related data. This study introduces a neural topic generation model that leverages transformer-based embeddings from BART and T5 to automatically identify latent topics representing defect patterns, providing actionable insights into their root causes. By integrating these models with attention mechanisms and a VAE, the model effectively handles unstructured textual data, generating interpretable and coherent topics. The performance of the proposed models is compared with traditional NTM models, such as NTM with Word2Vec and VAE-based NTM. Experimental results show that NTM-BART achieved the highest coherence score (0.468) and a low perplexity score (124), while NTM-T5 achieved the lowest perplexity score (119) and a coherence score of 0.434. In contrast, traditional NTM models exhibited significantly lower coherence scores (0.296 for NTM with Word2Vec) and higher perplexity (207 for VAE-based NTM), underscoring their limitations. These findings highlight the ability of BART and T5 to generate coherent and interpretable topics, making them highly effective tools for RCA in complex manufacturing environments. The study emphasizes the transformative potential of advanced NLP techniques in industrial applications, paving the way for smarter, more efficient manufacturing systems.</p>","PeriodicalId":72922,"journal":{"name":"Engineering reports : open access","volume":"7 5","pages":""},"PeriodicalIF":1.8,"publicationDate":"2025-05-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/eng2.70191","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144085384","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Two-Dimensional Free Surface Flow Through Solid Walls With Surface Tension Effects","authors":"Zineb Guellati,&nbsp;Abdelkader Gasmi","doi":"10.1002/eng2.70166","DOIUrl":"https://doi.org/10.1002/eng2.70166","url":null,"abstract":"<p>We examine the two-dimensional, steady, and irrotational flow of an inviscid and incompressible fluid emerging from certain cases of flow through solid walls. Surface tension (T) is considered, while gravitational effects are neglected. This problem is complicated by the nonlinear boundary condition imposed by the Bernoulli equation on the free surface, which presents challenges when adapting numerical methods used by many researchers. We employ a series truncation method for numerical solution. We computed solutions for various values of the angle (<i>β</i>) between the walls AB and the horizontal, the length of the vertical wall BC, and different Weber numbers. For determining the shape of the free surface, most of the calculations were performed for <i>N</i> = 50. We were able to find approximate solutions for <span></span><math>\u0000 <semantics>\u0000 <mrow>\u0000 <mi>α</mi>\u0000 <mo>≥</mo>\u0000 <mn>1</mn>\u0000 </mrow>\u0000 <annotation>$$ alpha ge 1 $$</annotation>\u0000 </semantics></math> To validate our results, they were compared with studies using other numerical methods and in special cases of the angle β, compared with the exact solution in the limit of <span></span><math>\u0000 <semantics>\u0000 <mrow>\u0000 <mi>α</mi>\u0000 <mo>→</mo>\u0000 <mi>∞</mi>\u0000 </mrow>\u0000 <annotation>$$ alpha to infty $$</annotation>\u0000 </semantics></math>.</p>","PeriodicalId":72922,"journal":{"name":"Engineering reports : open access","volume":"7 5","pages":""},"PeriodicalIF":1.8,"publicationDate":"2025-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/eng2.70166","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144074338","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Enhancing Surveillance Video Abnormal Behavior Detection Using Deep Convolutional Generative Adversarial Network With GRU Model","authors":"Setegn Asnakew Kasegn,&nbsp;Ronald Waweru Mwangi,&nbsp;Michael Kimwele,&nbsp;Surafel Lemma Abebe","doi":"10.1002/eng2.70177","DOIUrl":"https://doi.org/10.1002/eng2.70177","url":null,"abstract":"<p>Automatic detection of unusual behavior in videos is a challenging task. This challenge comes from its complexity and the wide range of applications it covers. Several deep learning approaches have been proposed to address this challenge. This includes recent generative methods that use deep convolutional generative adversarial networks (DCGAN). The DCGAN model has gained high research attention recently due to its performs well in extracting spatial features and solve class imbalance issue to detect abnormalities. However, a DCGAN is unstable during training and has low performance owing to its inability to capture the long-term temporal dependency between sequences of video frames. In this study, we propose a novel gated recurrent unit (GRU)-based DCGAN architecture to improve the training stability and performance of a DCGAN model for abnormal video behavior detection. The proposed model was trained using UCSD Ped1, UCSD Ped2, CUHK Avenue, and ShanghaiTech benchmark anomaly dataset. Compared to the DCGAN model, the proposed GRU-based DCGAN model improved the detection accuracy and area under the curve (AUC) by an average of 19.91% and 8.57%, respectively. Compared with the 3D-DCGAN model, the GRU-based DCGAN model improved the detection accuracy and AUC by an average of 7.67% and 3.73%, respectively. Furthermore, the GRU-based DCGAN model stabilized from epoch 10 and converged at epoch 38, whereas the other models remained unstable and did not converge at epoch 50. The findings highlight that the combination of GRU to enhance temporal modeling within a DCGAN framework is a logical extension to improve training stability and performance for abnormal video behavior detection.</p>","PeriodicalId":72922,"journal":{"name":"Engineering reports : open access","volume":"7 5","pages":""},"PeriodicalIF":1.8,"publicationDate":"2025-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/eng2.70177","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144074387","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Finite Element Analysis and Machine Learning-Based Prediction of Oil Tank Behavior Under Diverse Operating Conditions","authors":"Themba Mashiyane,&nbsp;Lagouge Tartibu,&nbsp;Smith Salifu","doi":"10.1002/eng2.70173","DOIUrl":"https://doi.org/10.1002/eng2.70173","url":null,"abstract":"<p>Ensuring the structural integrity and operational reliability of oil storage tanks is critical to preventing catastrophic failures, including environmental pollution and economic losses. This study integrates Finite Element Analysis (FEA) and Machine Learning (ML) to predict the behavior (structural) and useful life of oil tanks under diverse operating conditions. The methodology involves applying FEA simulation (using Abaqus) to model the strain, stress, and buckling behavior of the oil storage tank. Thereafter, fe-safe postprocessing software was used to post-process the FEA results to estimate the useful life of the tank. These FEA and fe-safe outputs were trained using Artificial Neural Networks (ANN) and Adaptive Neuro-Fuzzy Inference Systems (ANFIS) to predict unknown tank operating scenarios. The study revealed that the filled tanks experienced higher stress (485.4 MPa) and reduced life expectancy (1429 h) compared to half-filled tanks (388.7 MPa and 3551 h). For the ML, ANFIS excelled in predicting stress and strain with <i>R</i>² values of 0.999, while ANN proved superior for useful life predictions with <i>R</i>² values of 0.998. This hybrid FEA-ML approach enables efficient and precise analysis, thereby facilitating design optimization and maintenance strategies for industrial applications.</p>","PeriodicalId":72922,"journal":{"name":"Engineering reports : open access","volume":"7 5","pages":""},"PeriodicalIF":1.8,"publicationDate":"2025-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/eng2.70173","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144074385","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Orthogonal Multi-Swarm Greedy Selection Based Sine Cosine Algorithm for Optimal FACTS Placement in Uncertain Wind Integrated Scenario Based Power Systems","authors":"Sunilkumar P. Agrawal,&nbsp;Pradeep Jangir,&nbsp; Arpita,&nbsp;Sundaram B. Pandya,&nbsp;Anil Parmar,&nbsp;Mohammad Khishe,&nbsp;Bhargavi Indrajit Trivedi","doi":"10.1002/eng2.70167","DOIUrl":"https://doi.org/10.1002/eng2.70167","url":null,"abstract":"<p>Modern power systems encounter significant challenges in optimal power flow (OPF) management due to the unpredictable nature of wind energy integration. Flexible AC Transmission System (FACTS) devices, including Static VAR Compensator (SVC), Thyristor-Controlled Series Compensator (TCSC), and Thyristor-Controlled Phase Shifter (TCPS), enhance system stability, reduce losses, and lower operational costs when optimally placed. Conventional optimization techniques like Particle Swarm Optimization (PSO), Sine Cosine Algorithm (SCA), Moth Flame Optimization (MFO), Gray Wolf Optimizer (GWO), and Whale Optimization Algorithm (WOA) struggle to balance exploration and exploitation in complex OPF problems, leading to suboptimal solutions. This study proposes a novel hybrid metaheuristic approach, the Orthogonal Multi-swarm Greedy Selection Sine Cosine Algorithm (OMGSCA), integrating orthogonal learning, multi-swarm mechanisms, and greedy selection to enhance solution quality. Orthogonal learning explores new search spaces, while the multi-swarm strategy improves exploitation. The greedy selection mechanism prevents premature convergence. OMGSCA optimizes FACTS device placement and sizing in wind-integrated power systems under fixed and uncertain loading conditions. Performance evaluation on the IEEE 30-bus test system with wind energy and FACTS devices demonstrates OMGSCA's superiority over traditional algorithms. Case studies focus on minimizing generation costs, active power losses, and gross costs. Results show OMGSCA achieves a power loss of 5.6209 MW in Case 1, comparable to WOA (5.6121 MW) and outperforming PSO, SCA, and MFO by 0.90%, 0.06%, and 0.57%, respectively. OMGSCA's gross generation cost (1369.3961 $/h) surpasses PSO, SCA, MFO, and GWO by 0.39%, 0.28%, 3.48%, and 0.20%, respectively. The algorithm proves effective in OPF problems, delivering cost-efficient operations, reduced losses, and enhanced stability across varying load conditions.</p>","PeriodicalId":72922,"journal":{"name":"Engineering reports : open access","volume":"7 5","pages":""},"PeriodicalIF":1.8,"publicationDate":"2025-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/eng2.70167","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144074386","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Enhanced Automatic Generation Control in Multiarea Power Systems: Crow Search Optimized Cascade FOPI-TIDDN Controller With Integrated Renewable Solar Thermal Models and HVDC Lines","authors":"Naladi Ram Babu,&nbsp;Pamarthi Sunitha,&nbsp;Ganesh Pardhu B. S. S.,&nbsp;Sanjeev Kumar Bhagat,&nbsp;Adireddy Ramesh,&nbsp;Arindita Saha,&nbsp;Wulfran Fendzi Mbasso,&nbsp;Pradeep Jangir,&nbsp;Ahmed Hossam-Eldin","doi":"10.1002/eng2.70185","DOIUrl":"https://doi.org/10.1002/eng2.70185","url":null,"abstract":"<p>As renewable energy sources (RES) are increasingly unified into multiarea power systems, automatic generation control (AGC) faces challenges such as frequency instability, longer settling times, and higher overshoot. While existing optimization techniques like Firefly (FF) and gray wolf (GW) suffer from slow convergence and local optima trapping, conventional controllers like FOPI, PIDN, TIDN, and TIDDN struggle to maintain stability under fluctuating load conditions. Fractional-Order Proportional-Integral with Tilt Integral Double Derivative and Filter (FOPI-TIDDN), a novel cascade controller optimized using the crow search (CS) algorithm, is proposed in this paper to overcome these issues. Furthermore, a two-area AGC framework incorporates realistic dish-Stirling solar thermal systems (RDSTS) and parabolic trough solar thermal plants (PTSTP), and the effects of these systems are examined under different patterns of solar insolation. Additionally, the study assesses how high voltage direct current (HVDC) tie-lines contribute to increased system stability. According to simulation data, the FOPI-TIDDN controller works noticeably better than others in terms of improved frequency regulation, faster settling time, and less overshoot. Compared to FF and GW approaches, the CS algorithm guarantees faster convergence. An ideal fixed-random solar insolation method and HVDC integration also improve system performance. The suggested method enhances renewable-integrated power systems' resilience, efficiency, and stability.</p>","PeriodicalId":72922,"journal":{"name":"Engineering reports : open access","volume":"7 5","pages":""},"PeriodicalIF":1.8,"publicationDate":"2025-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/eng2.70185","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144074388","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Critical Factors Governing the Frictional Coefficient in Mg Alloys—Learn From Machine Learning","authors":"Negar Bagherieh,&nbsp;Moslem Noori,&nbsp;Dongyang Li,&nbsp;Meisam Nouri","doi":"10.1002/eng2.70140","DOIUrl":"https://doi.org/10.1002/eng2.70140","url":null,"abstract":"<p>Data-driven methods are emerging as a promising approach in discovering the correlation between tribological properties, composition, and mechanical properties of engineering materials. In the present study, the capability of several ML models in predicting the coefficient of friction (COF) of magnesium alloys is studied. To this end, first 1400 data points are extracted from prior studies through an extensive literature review. The collected data is then used to train models for the following two scenarios: (i) COF prediction using composition, processing parameters, and tribological variables; (ii) COF prediction using mechanical properties (hardness, yield strength, ultimate tensile strength, ductility, and elastic modulus), and tribological variables. After preprocessing, the data is partitioned into train and test datasets where the train dataset is used for model training and hyperparameter tuning, K-fold cross-validation, and the test dataset is used for evaluating the best trained models. The results indicate that light gradient boosting (LGBM) accurately predicts COF of magnesium alloys using the processing procedure, heat treatment, alloy composition, and tribology variables with an R-squared value of 0.89. Further, the gradient boosting method (GBM) achieves an R-squared score of 0.87 for predicting the COF using mechanical properties and tribological variables, showing a promising performance. In addition, a comparative analysis between alloying elements, manufacturing process, heat treatment, mechanical properties, and tribological test variables is performed using feature importance in the trained random forest (RF) models. Our findings highlight the importance of normal load, elastic modulus, and content of Zn in determining the COF in magnesium alloys, which helps improve materials and mechanical system design for effective COF control.</p>","PeriodicalId":72922,"journal":{"name":"Engineering reports : open access","volume":"7 5","pages":""},"PeriodicalIF":1.8,"publicationDate":"2025-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/eng2.70140","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144074699","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Analysis of Ti-Alloy Nanoparticles in Paraffin Oil for 3D MHD Darcy-Forchheimer Flow Over a Bi-Directional Stretching Surface","authors":"D. Thenmozhi,&nbsp;M. Eswara Rao,&nbsp;Kalyan Kumar Challa,&nbsp;Muhammad Jawad,&nbsp;Liaqat Hamdard,&nbsp;Walid Abdelfattah","doi":"10.1002/eng2.70136","DOIUrl":"https://doi.org/10.1002/eng2.70136","url":null,"abstract":"<p>The three-dimensional model of Darcy-Forchheimer flow in a convection system consisting of Ti-alloy nanoparticles (TiO₂) suspended in paraffin oil is mathematically constructed using fluid mechanics and partial differential equations (PDEs). A novel aspect of this study is the application of similarity transformation techniques to convert complex PDEs into a system of ordinary differential equations (ODEs), which are then solved using the Runge–Kutta 4th order method with the shooting technique. This unique approach provides deeper insights into the effects of magnetohydrodynamics (MHD), porosity, heat source, stretching surface, and radiation on bi-directional velocity and temperature profiles. The results demonstrate that Ti-alloy nanoparticles significantly enhance the thermal conductivity of the base fluid, leading to a 34.7% increase in temperature profiles compared to conventional fluids. The presence of a magnetic field induces a Lorentz force, reducing the bi-directional velocity by 18.5% while increasing fluid temperature by 22.9%. An increase in the porosity parameter results in a 15.3% reduction in velocity due to higher resistance, whereas the temperature profile shows a corresponding rise of 26.1%. Furthermore, an increase in the Forchheimer parameter reduces velocity by 21.6%, while the radiation parameter enhances heat transfer by 29.4%. These findings highlight the superior heat transfer efficiency of Ti-alloy-based nanofluids, making them highly suitable for applications in thermal energy storage, solar energy systems, and industrial cooling technologies.</p>","PeriodicalId":72922,"journal":{"name":"Engineering reports : open access","volume":"7 5","pages":""},"PeriodicalIF":1.8,"publicationDate":"2025-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/eng2.70136","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144074258","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Modeling the Impact of Double-Dose Vaccination and Saturated Transmission Dynamics on Mpox Control","authors":"Fredrick Asenso Wireko,&nbsp;Joshua Nii Martey,&nbsp;Isaac Kwasi Adu,&nbsp;Bright Emmanuel Owusu,&nbsp;Sebastian Ndogum,&nbsp;Joshua Kiddy K. Asamoah","doi":"10.1002/eng2.70144","DOIUrl":"https://doi.org/10.1002/eng2.70144","url":null,"abstract":"<p>This study constructs a compartmental model that incorporates the dynamics of implementing a double-dose vaccination for the Mpox disease. The study further explores the pattern of saturated transmission dynamics of the Mpox disease. This model was studied through the Caputo fractional derivative as the Mpox disease has been shown to have memory dynamics. We discussed the existence and uniqueness of the Mpox disease model. Again, through the Hyers-Ulam and Hyers-Ulam-Rassias stability criteria, we have shown that the model is resilient to unexpected changes in the population. A thorough sensitivity study was performed on the model. It was observed that the effective implementation of the double-dose vaccination and minimizing direct contact between the infected and the uninfected could help eradicate the Mpox disease from the population. In the numerical simulation section, the dynamics of the memory effect in the model were explicitly exhibited as the disease continuously declined whenever <span></span><math>\u0000 <semantics>\u0000 <mrow>\u0000 <mi>ω</mi>\u0000 <mo>=</mo>\u0000 <mn>0</mn>\u0000 <mo>.</mo>\u0000 <mn>80</mn>\u0000 </mrow>\u0000 <annotation>$$ omega =0.80 $$</annotation>\u0000 </semantics></math>. Finally, we have shown that an effective implementation of isolation and treatment measures contributes massively to controlling the Mpox disease in the population.</p>","PeriodicalId":72922,"journal":{"name":"Engineering reports : open access","volume":"7 5","pages":""},"PeriodicalIF":1.8,"publicationDate":"2025-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/eng2.70144","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144074255","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Consistent Differential Privacy Dynamic Trajectory Flow Prediction Method","authors":"Hongzhi Pan","doi":"10.1002/eng2.70159","DOIUrl":"https://doi.org/10.1002/eng2.70159","url":null,"abstract":"<p>Ensuring privacy while maintaining accuracy in trajectory prediction is a crucial challenge in privacy-sensitive applications such as smart transportation and mobility analytics. This paper presents CDP-DTP (Consistent Differential Privacy Dynamic Trajectory Flow Prediction), a novel approach that effectively balances privacy protection and prediction accuracy in trajectory forecasting. The proposed method constructs a trajectory flow graph and integrates Laplace noise-based differential privacy with consistency constraint adjustments to enhance privacy while maintaining data utility. A CNN-LSTM hybrid model also extracts spatial and temporal features, improving prediction performance through feature fusion. Experiments on real-world trajectory datasets demonstrate that CDP-DTP outperforms traditional differential privacy methods by achieving lower mean squared error (MSE) while ensuring stronger privacy protection across different privacy budget settings. These results validate the model's effectiveness in privacy-sensitive trajectory prediction tasks. The proposed method provides a scalable solution for privacy-preserving mobility analytics and contributes to future research in intelligent transportation and secure data sharing.</p>","PeriodicalId":72922,"journal":{"name":"Engineering reports : open access","volume":"7 5","pages":""},"PeriodicalIF":1.8,"publicationDate":"2025-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/eng2.70159","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144074256","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}