alexandria engineering journal最新文献

{"title":"DATDM: Dynamic attention transformer diffusion model for underwater image enhancement","authors":"Wang Hu ,&nbsp;Shitu Chen ,&nbsp;Tuyan Luo ,&nbsp;Lijun Zhang ,&nbsp;Hongjin Zhang ,&nbsp;Zhixiang Liu ,&nbsp;Shiwen Zhang ,&nbsp;Jingxiang Xu","doi":"10.1016/j.aej.2025.04.078","DOIUrl":"10.1016/j.aej.2025.04.078","url":null,"abstract":"<div><div>Underwater image degradation presents complex challenges, significantly impairing the efficiency of underwater tasks. The mainstream underwater image enhancement (UIE) methods are roughly divided into traditional physics-based and data-driven deep-learning methods. However, physical model-based methods have poor generalization capabilities. Data-driven methods require high-quality training data and suffer from limited model stability. We propose a novel UIE framework, DATDM, to address the above limitations and improve degraded underwater images. We first introduce a color correction module (CCM) to strengthen the model’s image restoration capabilities. On the other hand, we propose a novel dynamic attention transformer (DAT) denoising network with excellent performance. The proposed DAT denoising network utilizes a dynamic attention transformer mechanism that adaptively extracts feature information based on the complexity of the feature map, effectively capturing rich features while optimizing computational efficiency. The proposed DATDM method significantly outperforms the existing state-of-the-art methods, with peak signal-to-noise ratios of 24.05 and 27.39 and structural similarity index measures of 0.9233 and 0.9504 on the UIEB and LSUI datasets, respectively. The final experiments demonstrate that our DATDM achieves better performance and visual effects on UIE tasks.</div></div>","PeriodicalId":7484,"journal":{"name":"alexandria engineering journal","volume":"126 ","pages":"Pages 591-604"},"PeriodicalIF":6.2,"publicationDate":"2025-05-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143913027","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":"Impact of side-by-side twin tunneling with various tunnel-pile clearances on pile group responses under a fluid-solid coupling effect","authors":"Tianhua Wu ,&nbsp;Yongtao Gao ,&nbsp;Changfu Huang ,&nbsp;Yu Zhou ,&nbsp;Jianwang Li ,&nbsp;Wenrui Qi","doi":"10.1016/j.aej.2025.05.012","DOIUrl":"10.1016/j.aej.2025.05.012","url":null,"abstract":"<div><div>In urban subway construction, shield tunneling near pile groups is common, where additional loads may threaten existing structures. This study establishes multiple 3D nonlinear FDM models with fluid-solid coupling to investigate how tunnel–pile clearances (<em>H</em>_<em>c</em>) affect the mechanical response of low-cap pile groups (2 ×2) during side-by-side twin tunneling in composite strata. The advanced CYSoil model, incorporating nonlinearity, strain path dependency, and small strain behavior, is employed to simulate soil response. Results show that tunneling induces up to a ∼66.7 % reduction in pore water pressure, forming a funnel-shaped seepage pattern. As <em>H</em>_<em>c</em> increases from 0.8<em>D</em> to 2.6<em>D</em>, the low-pressure zone shifts from sidewalls to vault and invert, while maximum displacements reduce by up to 14.04 mm (lateral), 5.28 mm (transverse), and 19.68 mm (vertical). Axial force evolution in piles follows a three-stage decline, i.e., rapid, slow, and moderate, with peak shaft resistance concentrated near the tunnel axis. These findings aid in optimizing tunnel-pile configurations and mitigating geotechnical risks.</div></div>","PeriodicalId":7484,"journal":{"name":"alexandria engineering journal","volume":"127 ","pages":"Pages 1-17"},"PeriodicalIF":6.2,"publicationDate":"2025-05-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143918557","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":"Cross-modal enhanced sparse CT imaging via null-space denoising diffusion with random medical measurement embedding","authors":"Xiaoyue Li ,&nbsp;Kai Shang ,&nbsp;Mark D. Butala ,&nbsp;Gaoang Wang","doi":"10.1016/j.aej.2025.04.021","DOIUrl":"10.1016/j.aej.2025.04.021","url":null,"abstract":"<div><div>Recent advancements in diffusion models for sparse-view medical computed tomography (CT) have mitigated common issues in supervised deep learning, such as over-smoothing and limited generalization. However, these models often rely on lengthy sampling chains, leading to impractical computation times and error accumulation, especially under significant data distribution shifts. Moreover, they typically overlook clinical noise, which is prevalent in real-world scenarios. To address these challenges, we introduce the Denoising Diffusion model with cross-Modal prior and physical Measurement embedding (DDMM-CT) for reconstructing sparse-view CT images. DDMM-CT refines the null space of intermediate results during inference by leveraging cross-modal geometric information, narrowing the target region in each denoising step. The measurement-related space component is replaced with a combination of the physical operator and measurements to enforce data consistency with minimal additional computation. An error-feedback correction block is integrated to reduce errors from imperfect reconstruction steps. We also present DDMM-CT-noise, designed for clinical scenarios with complex noise mixtures. The proposed method demonstrates superior generalization and flexibility, allowing adjustments in the number of projections and measurement noise intensity without retraining. Our results show that DDMM-CT outperforms recent comparable methods in terms of inference time and image quality. The code is available at <span><span>https://github.com/Lxy98Code/DDMM-CT</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":7484,"journal":{"name":"alexandria engineering journal","volume":"126 ","pages":"Pages 565-577"},"PeriodicalIF":6.2,"publicationDate":"2025-05-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143906299","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":"Image small target detection in complex traffic scenes based on Yolov8 multiscale feature fusion","authors":"Xuguang Chai ,&nbsp;Meizhi Zhao ,&nbsp;Jing Li ,&nbsp;Junwu Li","doi":"10.1016/j.aej.2025.04.105","DOIUrl":"10.1016/j.aej.2025.04.105","url":null,"abstract":"<div><div>Addressing the challenging issues in small target detection within complex traffic scenes, such as scale variation, complex background noise, and the problems of missed and false detections, this paper introduces a Multi-Scale Feature Fusion YOLOv8 (MSFF-YOLOv8) approach. Initially, building upon the YOLOv8 detection framework, an attention mechanism module is integrated for novel adaptive feature assimilation and redistribution. This innovation facilitates the effective amalgamation of multi-scale features, thereby bolstering the model's proficiency in identifying small targets and enhancing the richness of the contextual information within the output features. Furthermore, the incorporation of deformable convolution amplifies the algorithm's capacity to maintain target consistency amidst complexity. Additionally, employing a feature distillation technique permits the student model to absorb crucial feature representations from the teacher model, circumventing the detrimental effects of semantic disparities across stages. This significantly elevates the model's generalizability and robustness. Experimental validations corroborate the efficacy and superiority of the proposed method. Enhanced detection performance is achieved, effectively mitigating the challenges of small target detection in complex scenarios, such as under poor lighting conditions in traffic environments, and elevating both the accuracy and efficiency of detection.</div></div>","PeriodicalId":7484,"journal":{"name":"alexandria engineering journal","volume":"126 ","pages":"Pages 578-590"},"PeriodicalIF":6.2,"publicationDate":"2025-05-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143906300","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":"Monotonic and oscillatory features of solutions to general functional differential equations with a neutral-delay argument","authors":"Osama Moaaz ,&nbsp;Asma Al-Jaser","doi":"10.1016/j.aej.2025.04.041","DOIUrl":"10.1016/j.aej.2025.04.041","url":null,"abstract":"<div><div>This work is concerned with establishing several criteria for investigating the oscillatory features of solutions to a class of second-order neutral differential equations. This type of equation is rich in interesting analytical points as well as its applications in physical and engineering fields. Based on some new monotonic properties, we derive sufficient conditions for oscillation using the comparison principle and Riccati substitutions. The approach used allows us to remove some restrictions that are usually imposed on the coefficients of neutral differential equations in previous works. Moreover, some of the new criteria provide a sharp result when applied to the Euler differential equation. We support the theoretical results by applying them to special cases and comparing them with relevant results in the literature.</div></div>","PeriodicalId":7484,"journal":{"name":"alexandria engineering journal","volume":"126 ","pages":"Pages 546-554"},"PeriodicalIF":6.2,"publicationDate":"2025-05-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143906203","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":"Guardian-AI: A novel deep learning based deepfake detection model in images","authors":"Hadeel Alsolai ,&nbsp;Khalid Mahmood ,&nbsp;Asma Alshuhail ,&nbsp;Achraf Ben Miled ,&nbsp;Mohammed Alqahtani ,&nbsp;Abdulrhman Alshareef ,&nbsp;Fouad Shoie Alallah ,&nbsp;Bandar M. Alghamdi","doi":"10.1016/j.aej.2025.04.095","DOIUrl":"10.1016/j.aej.2025.04.095","url":null,"abstract":"<div><div>The rapid advancement of deepfake technology has introduced significant challenges and opportunities across various domains. This article proposes a robust deepfake detection pipeline utilising a combination of attention mechanisms, pre-trained Vision Transformers (ViTs), and Long Short-Term Memory (LSTM) networks. The initial phase of the pipeline involves preparing photos and videos, potentially using optional facial detection to enhance accuracy. Vision Transformers derive features by capturing the global dependencies of input data. Long short-term memory (LSTM) networks address inter-frame temporal dependencies, whereas multi-head and traditional attention processes focus on essential elements. Ultimately, fully connected layers are employed for classification within the ensemble architecture, which consolidates the outcomes of several models. To ensure generalisability, assessment and regularisation approaches are employed to train the model using labelled datasets. Given the escalating threat of deepfakes, the findings indicate that the pipeline can consistently distinguish between genuine and fabricated information.</div></div>","PeriodicalId":7484,"journal":{"name":"alexandria engineering journal","volume":"126 ","pages":"Pages 507-514"},"PeriodicalIF":6.2,"publicationDate":"2025-05-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143906304","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":"Multi-rate selection and power allocation assisted probabilistic edge caching for cooperative video transmission in dense D2D networks","authors":"Thuong C. Lam ,&nbsp;Nguyen-Son Vo ,&nbsp;Viet V. Lam ,&nbsp;Trang Hoang ,&nbsp;Minh-Phung Bui ,&nbsp;Trung Q. Duong","doi":"10.1016/j.aej.2025.04.057","DOIUrl":"10.1016/j.aej.2025.04.057","url":null,"abstract":"<div><div>In this paper, we consider a cooperative transmission model for video applications and services (VASs) in dense device-to-device (D2D) networks. The model enables the mobile users (MUs) to flexibly receive the videos from macro base station (MBS) and D2D networks with mobile edge caching. Particularly, we formulate a multi-rate selection and power allocation assisted probabilistic edge caching (MPC) optimisation problem under the resource constraints on storage, bandwidth, and power. This problem is solved for the optimal caching probabilities of requested videos corresponding to proper encoding rates selected. The optimal powers of caching MUs and MBS for transmitting the videos are also found to maximise the playback quality, while utilising the system resources. The MPC optimisation problem, which is complicated due to the presence of binary and real variables and various constraints, is feasibly solved by genetic algorithms (GA) with penalty function and truncated chromosome. Simulation results are shown to demonstrate the benefits of both GA and MPC methods compared to other benchmarks. Detailed analyses and interesting findings provide useful insights into the mobile edge caching design of dense D2D networks for VASs.</div></div>","PeriodicalId":7484,"journal":{"name":"alexandria engineering journal","volume":"126 ","pages":"Pages 555-564"},"PeriodicalIF":6.2,"publicationDate":"2025-05-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143906204","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":"Battery thermal management using heavy fuels: An approach to lightweight diesel fuelled hybrid electric vehicles","authors":"Mansour Al Qubeissi ,&nbsp;Raja Mazuir Raja Ahsan Shah ,&nbsp;Ali Almshahy","doi":"10.1016/j.aej.2025.04.064","DOIUrl":"10.1016/j.aej.2025.04.064","url":null,"abstract":"<div><div>Lithium-Ion Batteries (LIBs) experience heat generation during charge and discharge, leading to high temperatures, capacity loss, thermal runaway, and material degradation. Battery Thermal Management Systems (BTMS) are crucial for maintaining optimal LIB performance and longevity. This study explores the use of dielectric fuel components as alternative BTMS coolants in diesel/battery-powered hybrid electric vehicles (HEVs). The 1P3S LIB module and BTMS are designed using CATIA. The BTMS Computational Fluid Dynamics (CFD) modelling is conducted using ANSYS-Fluent. Two coolants, air and 3M-Novec 7200, are compared with alternative dielectric fuels based on the EU standard diesel fuel composition. The study evaluates the BTMS performance under varying inlet velocities (0.1–1 m/s) and battery discharge rates (1 C to 2 C). Results show that air is insufficient for maintaining the LIB pack operational temperature (20°C to 45°C). The alternative fuels, particularly n-decane, perform well and similarly to 3M-Novec 7200 in cooling efficiency, keeping the battery pack within optimal temperature ranges and minimizing temperature differences (≤0.5°C). Additionally, these fuels have lower densities than 3M-Novec 7200, offering potential weight reduction (up to 50 kg) while improving cooling efficiency.</div></div>","PeriodicalId":7484,"journal":{"name":"alexandria engineering journal","volume":"126 ","pages":"Pages 515-545"},"PeriodicalIF":6.2,"publicationDate":"2025-05-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143906305","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":"Applications and development trends of textile materials in sports: A review","authors":"Guomei Cui,&nbsp;Chuanjun Wang","doi":"10.1016/j.aej.2025.04.094","DOIUrl":"10.1016/j.aej.2025.04.094","url":null,"abstract":"<div><div>Sports textiles represent a rapidly evolving discipline at the intersection of material science, sports engineering, and human physiology, underpinning athlete performance, comfort, and safety. This review opens by highlighting the core physiological and ergonomic demands placed on athletes—effective thermoregulation, efficient moisture management, mechanical support and proprioceptive feedback—and then elucidates the fundamental mechanisms by which fiber architecture and fabric structure fulfill these requirements. We examine capillary-driven moisture transport through engineered micro- and nano-scale fiber networks, thermal buffering achieved via phase-change materials and inherently low-conductivity fibers, and dynamic compression effects arising from elastomeric yarns that improve circulation and stability. The manuscript then surveys cutting-edge material innovations, including smart textiles embedded with flexible sensor arrays, nanocoatings that confer water repellency, antimicrobial action and ultraviolet protection, and stimuli-responsive polymers that change shape or porosity in response to temperature and humidity. Multifunctional nanocomposites—combining carbon-based nanomaterials with polymer matrices—are reviewed for their dual capacity to reinforce mechanical properties and enable real-time physiological monitoring. An in-depth analysis of manufacturing processes follows, covering advanced fiber synthesis methods (electrospinning, wet spinning), high-precision spinning techniques for core–sheath and coaxial yarns, seamless knitting and 3D textile printing technologies, as well as strategies for integrating electronic components without compromising wearability. We critically assess standardized testing protocols for thermophysiological comfort, moisture management metrics, mechanical durability and endurance of smart functionalities under repeated laundering. A dedicated section on sustainability examines lifecycle impacts, emerging bio-based and recyclable fiber alternatives, closed-loop manufacturing, and approaches to mitigate microfiber shedding. Customization trends driven by digital manufacturing and on-demand production are discussed in terms of personalized fit, performance profiling and consumer aesthetics. Finally, we identify research gaps—such as long-term durability of smart textiles, integration of energy-harvesting systems and scalable eco-friendly process development—and propose strategic directions to accelerate the creation of next-generation, high-performance, environmentally responsible sportswear.</div></div>","PeriodicalId":7484,"journal":{"name":"alexandria engineering journal","volume":"126 ","pages":"Pages 491-506"},"PeriodicalIF":6.2,"publicationDate":"2025-05-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143906303","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":"MDP-AD: A Markov decision process-based adaptive framework for real-time detection of evolving and unknown network attacks","authors":"Fucai Luo,&nbsp;Tingfa Xu,&nbsp;Jianan Li,&nbsp;Fengxiang Xu","doi":"10.1016/j.aej.2025.04.091","DOIUrl":"10.1016/j.aej.2025.04.091","url":null,"abstract":"<div><div>With the continuous development of network technology and the increasing complexity of application scenarios, network attacks have become more diverse and covert, posing significant challenges to system security. Traditional network security measures often struggle to detect and respond to rapidly evolving attack patterns in real time. Therefore, there is an urgent need for a new detection technology that can dynamically assess risks and adapt to changing environments. The Markov Decision Process (MDP) offers an effective and interpretable approach to sequential decision-making, providing a novel method for automatic network attack detection. This study proposes an automatic detection model based on MDP, which dynamically analyzes network traffic and system behavior while continuously improving detection accuracy through adaptive learning strategies. To evaluate the model's effectiveness, multiple experiments were conducted in various scenarios, achieving a maximum detection accuracy of 94.3 %. The results demonstrate that the proposed MDP-based detection model offers significant advantages in detection accuracy, response speed, and adaptability to unknown attacks.</div></div>","PeriodicalId":7484,"journal":{"name":"alexandria engineering journal","volume":"126 ","pages":"Pages 480-490"},"PeriodicalIF":6.2,"publicationDate":"2025-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143906302","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}