alexandria engineering journal最新文献

{"title":"LAF: Enhancing person re-identification via Latent-Assisted Feature Fusion","authors":"Minglang Li ,&nbsp;Zhiyong Tao ,&nbsp;Sen Lin ,&nbsp;Kaihao Feng","doi":"10.1016/j.aej.2025.04.075","DOIUrl":"10.1016/j.aej.2025.04.075","url":null,"abstract":"<div><div>Person re-identification (Re-ID) in real-world scenarios is challenged by occlusions, viewpoint variations, and individuals with similar attributes. Existing methods predominantly rely on salient regions, yet such regions often become unreliable under occlusion or in crowded environments, leading to ambiguous feature representations. To address this limitation, we propose a novel Latent-Assisted Fusion (LAF) framework that systematically mines discriminative cues from non-salient areas, which are critical for distinguishing challenging samples. Our approach introduces three key innovations: Lock-Drop, Outlook-Attention, and ML-Fusion. Lock-Drop selectively erases prominent regions based on primary features, encouraging the model to learn from less obvious areas. Outlook-Attention refines the latent information, while ML-Fusion integrates these enriched features with the primary ones, significantly boosting the robustness and diversity of the learned features. Extensive experiments on five large-scale person re-identification benchmarks demonstrate that LAF consistently improves the performance of existing algorithms. Compared to state-of-the-art methods, LAF achieves superior results, including an mAP of 89.6% and Rank-1 accuracy of 95.9% on the Market1501 dataset, and an mAP of 63.3% with Rank-1 accuracy of 84.1% on the MSMT17 dataset. These results highlight the effectiveness of our proposed module in leveraging latent information from non-salient regions, leading to substantial performance improvements, particularly in challenging scenarios involving occlusions and complex backgrounds. Code is available at <span><span>https://github.com/meanlang/LAF</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":7484,"journal":{"name":"alexandria engineering journal","volume":"127 ","pages":"Pages 116-128"},"PeriodicalIF":6.2,"publicationDate":"2025-05-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143928221","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":"Comparative analysis of data-driven models on detection and classification of electrical faults in transmission systems: Explainability, applicability and industrial implications","authors":"Chibueze D. Ukwuoma ,&nbsp;Dongsheng Cai ,&nbsp;Chiagoziem C. Ukwuoma ,&nbsp;Chinedu I. Otuka ,&nbsp;Qi Huang","doi":"10.1016/j.aej.2025.04.097","DOIUrl":"10.1016/j.aej.2025.04.097","url":null,"abstract":"<div><div>Most data-driven fault detection methods often face challenges in accuracy, adaptability, and real-time implementation, particularly in complex transmission networks. To address these issues, this study presents an in-depth comparative analysis of data-driven models, including machine learning, neural networks, and deep learning techniques, for detecting and classifying electrical faults in transmission lines. A few key gaps were identified to persist particularly in terms of the accuracy, computational complexity, explainability, applicability, and industrial implications of these models. Hence, a Quadratic Discriminant Analysis by Projection (QDA-P) model which effectively captures non-linear relationships between electrical fault features is proposed, enhancing classification accuracy, less computationally complex and explainable for both binary and multi-class scenarios. Using a publicly available simulated dataset generated through MATLAB Simulink to represent various fault types, the QDA-P model achieved binary classification scores of 0.988, 0.980, 0.982, 0.995, and 0.987 while recording a multi-class classification score of 0.982, 0.979, 0.982, 0.982, and 0.980 for accuracy, precision, specificity, recall, and F1-score, respectively. Feature importance analysis showed that voltage at the sending or receiving end of the transmission line for phase A was the most influential while the length of the transmission line in phase A had the lowest importance. In contrast, techniques such as SHAP, LIME, and PDP reveal that the length of the transmission line in Phases A &amp; C significantly influenced Class 1 and Class 5 predictions, with the length of the transmission line in Phase C contributing positively and the length of the transmission line in phase A showing varied effects. An industrial applicability analysis using the Mahalanobis distance plot confirmed that the QDA-P model effectively captured underlying data patterns without significant outliers. These findings highlight the model's potential to improve fault detection accuracy and reliability, contributing to more efficient and secure energy transmission infrastructures.</div></div>","PeriodicalId":7484,"journal":{"name":"alexandria engineering journal","volume":"127 ","pages":"Pages 75-91"},"PeriodicalIF":6.2,"publicationDate":"2025-05-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143928219","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":"MATSFT: User query-based multilingual abstractive text summarization for low resource Indian languages by fine-tuning mT5","authors":"Siginamsetty Phani ,&nbsp;Ashu Abdul ,&nbsp;M. Krishna Siva Prasad ,&nbsp;V. Dinesh Reddy","doi":"10.1016/j.aej.2025.04.031","DOIUrl":"10.1016/j.aej.2025.04.031","url":null,"abstract":"<div><div>User query-based summarization is a challenging research area of natural language processing. However, the existing approaches struggle to effectively manage the intricate long-distance semantic relationships between user queries and input documents. This paper introduces a user query-based multilingual abstractive text summarization approach for the Indian low-resource languages by fine-tuning the multilingual pre-trained text-to-text (mT5) transformer model (MATSFT). The MATSFT employs a co-attention mechanism within a shared encoder–decoder architecture alongside the mT5 model to transfer knowledge across multiple low-resource languages. The Co-attention captures cross-lingual dependencies, which allows the model to understand the relationships and nuances between the different languages. Most multilingual summarization datasets focus on major global languages like English, French, and Spanish. To address the challenges in the LRLs, we created an Indian language dataset, comprising seven LRLs and the English language, by extracting data from the BBC news website. We evaluate the performance of the MATSFT using the ROUGE metric and a language-agnostic target summary evaluation metric. Experimental results show that MATSFT outperforms the monolingual transformer model, pre-trained MTM, mT5 model, NLI model, IndicBART, mBART25, and mBART50 on the IL dataset. The statistical paired t-test indicates that the MATSFT achieves a significant improvement with a <span><math><mi>p</mi></math></span>-value of <span><math><mo>≤</mo></math></span> 0.05 compared to other models.</div></div>","PeriodicalId":7484,"journal":{"name":"alexandria engineering journal","volume":"127 ","pages":"Pages 129-142"},"PeriodicalIF":6.2,"publicationDate":"2025-05-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143931562","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":"Dual-band dual-linearly polarized multibeam transmit-reflect-array antenna with independent beams control","authors":"Wei Luo,&nbsp;Liu Luo,&nbsp;Xiaoxue Wang,&nbsp;Min Wang,&nbsp;Hongsheng Zhang","doi":"10.1016/j.aej.2025.05.020","DOIUrl":"10.1016/j.aej.2025.05.020","url":null,"abstract":"<div><div>In this paper, a dual-band, dual-linearly polarized multibeam transmit-reflect-array (TRA) antenna is proposed. The dual-beams with different polarizations can be transmitted in the lower frequency band and reflected in the higher frequency band. The element comprises three metallic layers separated by substrate, enabling independent control of vertically and horizontally polarized waves in both the reflective and transmissive bands. Due to the frequency and polarization independence of the element, phase compensations are designed for vertically and horizontally polarized waves in each band, respectively. The circular aperture TRA is illuminated with a rotated linearly polarized horn, thereby generating dual-beams with different directions and polarizations in both the transmissive and reflective modes. The measurement results show that the peak aperture efficiency is 43.6 % and 36.0 % for the reflection band and transmission band. For the transmission band, the 3 dB gain bandwidths are 11.2 % (21–23.5 GHz) for horizontal polarization and 16.1 % (20–23.5 GHz) for vertical polarization. The 3 dB gain bandwidths for the reflection band are 12.1 % (27–30.5 GHz) for both the horizontal and vertical polarizations. The TRA antenna emerges as a promising contender for the implementation of bidirectional wireless communication.</div></div>","PeriodicalId":7484,"journal":{"name":"alexandria engineering journal","volume":"127 ","pages":"Pages 34-42"},"PeriodicalIF":6.2,"publicationDate":"2025-05-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143923434","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":"Global context-aware attention model for weakly-supervised temporal action localization","authors":"Weina Fu ,&nbsp;Wenxiang Zhang ,&nbsp;Jing Long ,&nbsp;Gautam Srivastava ,&nbsp;Shuai Liu","doi":"10.1016/j.aej.2025.05.006","DOIUrl":"10.1016/j.aej.2025.05.006","url":null,"abstract":"<div><div>Temporal action localization (TAL) is a significant and challenging task in the field of video understanding. It aims to locate the start and end timestamps of the actions in a video and recognize their categories. However, efficient action localization often requires extensive precise annotations. Therefore, the researchers propose weakly-supervised temporal action localization (WTAL), which aims to locate action instances in a video using only video level annotations. The existing WTAL methods lack the ability to distinguish the action context information effectively, including the pre-action and post-action scenes, which blur the action boundary and lead to the inaccurate action location. To solve the above problems, this paper proposes a global context-aware attention model (GCAM). Firstly, GCAM designs the mask attention module (MAM) to restrict the model's receptive field and make the model focus on localized features related to the action context. It enhances the ability to distinguish the action context information and clearly locate the start and end timestamps of the actions. Secondly, GCAM introduces the context broadcasting module (CBM), which supplements the global context information to keep the features intact in temporal dimension. This module solves the issue that the model overemphasizes the localized features due to the addition of the MAM. Extensive experiments on the THUMOS14 and ActivityNet1.2 datasets demonstrate the effectiveness of GCAM. On the THUMOS14 dataset, GCAM achieves an average mean average precision (mAP) of 49.5 %, representing a 2.2 % improvement over existing WTAL methods. On the ActivityNet1.2 dataset, GCAM achieves an average mAP of 27.2 %, representing a 0.3 % improvement over existing WTAL methods. These results highlight the superior performance of GCAM in accurately localizing actions in videos.</div></div>","PeriodicalId":7484,"journal":{"name":"alexandria engineering journal","volume":"127 ","pages":"Pages 43-55"},"PeriodicalIF":6.2,"publicationDate":"2025-05-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143923888","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":"Traffic load prediction for bridge construction based on Internet of Things and BIM","authors":"Ouyang Lou ,&nbsp;Miao Wang ,&nbsp;Shirong Zheng","doi":"10.1016/j.aej.2025.04.077","DOIUrl":"10.1016/j.aej.2025.04.077","url":null,"abstract":"<div><div>With the development of urban transportation infrastructure, bridge construction often leads to traffic congestion and safety hazards. The traditional traffic load prediction fails to solve the dynamic change of traffic during construction. For this reason, this paper proposes a traffic load prediction and dynamic optimization method based on the integration of Building Information Modeling (BIM) and Internet of Things (IoT). Real-time traffic, bridge status and construction information are collected through IoT devices, and two-way data fusion is carried out by combining BIM model and real-time data. The real-time feedback provided by IoT optimizes the traffic flow prediction and adjusts the construction plan. Combining LSTM and NSGA-II optimization methods, a dynamic prediction and adjustment framework is constructed to significantly improve the accuracy of traffic prediction and management efficiency during construction.</div></div>","PeriodicalId":7484,"journal":{"name":"alexandria engineering journal","volume":"127 ","pages":"Pages 56-65"},"PeriodicalIF":6.2,"publicationDate":"2025-05-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143928337","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":"The research on recognition of passenger abnormal behavior in urban rail transit stations based on conditional generative adversarial networks","authors":"Jing Zuo,&nbsp;Zexin Li,&nbsp;Ming He,&nbsp;Qiaoli Yang","doi":"10.1016/j.aej.2025.04.096","DOIUrl":"10.1016/j.aej.2025.04.096","url":null,"abstract":"<div><div>With the exponential growth of urban rail transit passenger flow, manual monitoring for passenger abnormal behavior recognition is prone to missed detections and misjudgments due to visual fatigue. Developing rapid and accurate intelligent recognition method for passenger abnormal behavior has therefore become crucial for enhancing operational management and ensuring passenger safety. To address these challenges. First, a U-shaped generator network based on Swin Transformer architecture was constructed to overcome the spatial limitations of conventional convolutional kernels, thereby substantially enhancing the model's capability to extract global information from station surveillance video sequences. Second, the framework incorporates a Patch GAN local discriminator network combined with Lite FlowNet to rectify local and motion distortions in generated frame, thereby enhancing passenger behavioral modeling accuracy. Finally, passenger abnormal behaviors are recognized by computing the Peak Signal-to-Noise Ratio (PSNR) between original surveillance and generated frame. To validate the proposed method's performance, comparative experiments were conducted on both public datasets (UCSD Ped2, CUHK Avenue, Subway Exit) and our self-built PAB dataset. The proposed method achieved AUC values of 96.2 %, 86.6 %, 99.4 %, and 84.3 % respectively, demonstrating superior abnormal behavior recognition performance compared to baseline methods. Experimental results demonstrate that the proposed method achieves superior recognition accuracy and robust applicability for passenger abnormal behaviors in complex urban rail transit environments with long-narrow platform configurations and high passenger density conditions.</div></div>","PeriodicalId":7484,"journal":{"name":"alexandria engineering journal","volume":"126 ","pages":"Pages 640-650"},"PeriodicalIF":6.2,"publicationDate":"2025-05-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143922635","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 analysis of model testing and finite element approach for distribution of earth pressures","authors":"Jungang Liu ,&nbsp;Feng Liang ,&nbsp;Geng Chen","doi":"10.1016/j.aej.2025.04.083","DOIUrl":"10.1016/j.aej.2025.04.083","url":null,"abstract":"<div><div>This study presents a comprehensive comparison of laboratory experiments and numerical simulations using finite element analysis (FEA) to investigate the effects of various geotextile spacing on the distribution of earth pressure. The experiments were conducted in the \"Tiger Cage (TC)\" testing facility at the University of Colorado Denver's (UCD) Geotechnical Engineering Science Center. A total of four large-scale tests were performed on Leyden Clay (LC) and Colorado Department of Transportation Class 1 Structure Backfill Material (CDOT Class 1 SBM) to validate the finite element model. The research focuses on the distribution of earth pressure on Leyden Clay and CDOT Class 1 SBM, validated through large-scale physical tests and 3D FEA simulations performed using the LS-DYNA and ABAQUS software. The results demonstrate the accuracy of numerical models in predicting earth pressure distributions, with strong correlations observed between experimental data and simulation results. The study reveals that the current method provision is inaccurate in predicting earth pressure distribution at the bottom of the wall, as the predicted data from numerical models show the highest earth pressures of 485Kpa around two-thirds of the wall height (150 cm). This research provides valuable insights into soil-structure interaction, contributing to the design and analysis of retaining walls and foundations in geotechnical engineering.</div></div>","PeriodicalId":7484,"journal":{"name":"alexandria engineering journal","volume":"127 ","pages":"Pages 18-33"},"PeriodicalIF":6.2,"publicationDate":"2025-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143918558","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 dust storms on plant biomass: Model structure and dynamic study","authors":"Mustafa Ahmed ,&nbsp;Shireen Jawad ,&nbsp;Dipam Das ,&nbsp;Salah Boulaaras ,&nbsp;M.S. Osman","doi":"10.1016/j.aej.2025.04.058","DOIUrl":"10.1016/j.aej.2025.04.058","url":null,"abstract":"<div><div>Dust storms endanger humans and the ecosystem. One efficient way to reduce dust storms is using plant biomass in a greenbelt. Reforestation is required to enhance plant biomass. Reforestation efforts can be assessed by their financial cost. This study provides a mathematical model for how dust storms affect plant biomass dynamics. The planned model is accurately described. The model's analysis is centered on identifying prospective equilibrium positions. The study indicates that it is feasible to establish four steady states. The stability analysis illustrates that all steady states are consistently stable under the specified conditions. The local bifurcations at each steady state are derived; specifically, transcritical bifurcation and Hopf bifurcation. The theoretical study is validated through numerical simulations. The analysis shows that desertification may arise if the coefficients related to the depletion of reforestation initiatives, the implementation rate of these initiatives, the depletion of plant biomass due to dust pollutants, and the plant biomass-induced dust pollutants depletion coefficient cannot be controlled.</div></div>","PeriodicalId":7484,"journal":{"name":"alexandria engineering journal","volume":"126 ","pages":"Pages 605-622"},"PeriodicalIF":6.2,"publicationDate":"2025-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143918369","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":"Assessing the ultimate strength of damaged tankers: Collision impacts and design improvements","authors":"Mahmoud Darwish,&nbsp;Yehia Abdel-Nasser,&nbsp;Yasser M. Ahmed","doi":"10.1016/j.aej.2025.04.009","DOIUrl":"10.1016/j.aej.2025.04.009","url":null,"abstract":"<div><div>Tankers transport substantial volumes of oil and other liquid cargoes across extensive distances. Collisions and groundings can inflict significant damage on their hulls, compromise their structural integrity, and raise concerns about environmental catastrophes. When a tanker sustains damage from collision or grounding, its capacity to withstand stress is diminished. Ultimate strength analysis is a critical methodology for assessing the residual strength of a vessel's hull after damage especially those above 150 m in length. This study investigates the influence of key design parameters, namely plate thickness, stiffener type, and material strain rate, on the ultimate bending moment capacity of damaged tanker hull structures. The research employs finite element analysis using LS-Dyna to simulate a perpendicular collision scenario, incorporating detailed representations of the hull structure and material properties. The analysis focuses on assessing the residual strength of the hull after damage by comparing the ultimate bending moment capacity before and after the collision. The research aims to identify effective strategies for mitigating the reduction in ultimate bending moment capacity, such as plate thickness, selecting appropriate stiffener profiles, and leveraging the enhanced properties of high-strain-rate materials. The study explores the potential benefits of utilizing high-strain-rate materials like A572 or 4140 steel to enhance the structural resilience of tankers. The findings of this research have significant implications for improving the safety and operational efficiency of tanker vessels by enhancing their structural robustness and potentially reducing repair costs and downtime. Future research should further investigate the impact of these parameters on other critical failure modes, such as buckling and shear, and explore the feasibility and cost-effectiveness of implementing high-strain-rate materials in large-scale tanker construction.</div></div>","PeriodicalId":7484,"journal":{"name":"alexandria engineering journal","volume":"126 ","pages":"Pages 623-639"},"PeriodicalIF":6.2,"publicationDate":"2025-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143918370","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}