alexandria engineering journal最新文献_第8页

SLM-DFS: A systematic literature map of deepfake spread on social media SLM-DFS：社交媒体上深度伪造传播的系统文献图谱

IF 6.2 2区工程技术 Q1 ENGINEERING, MULTIDISCIPLINARY

alexandria engineering journal

Pub Date : 2024-10-29 DOI: 10.1016/j.aej.2024.10.076

El-Sayed Atlam , Malik Almaliki , Ghada Elmarhomy , Abdulqader M. Almars , Awatif M.A. Elsiddieg , Rasha ElAgamy

In recent years, deepfakes (DFs)-realistically manipulated media created using artificial intelligence—have raised significant concerns. As this technology evolves, the urgency for effective detection methods to counter misuse intensifies. Computer science researchers are increasingly focused on stopping the spread of deepfakes (DFs) on social media. However, there has been no comprehensive overview of research in this area. This paper presents a systematic literature map that analyzes research on DF spread on social media from 286 primary studies published between 2018 and June 2024. The studies are categorized by their research type, contribution and focus, revealing a predominant emphasis on detection solutions. Notably, there are significant gaps in evaluating these solutions, using digital interventions to curb dissemination, and managing DF propagation. This literature map will aid researchers, practitioners, and policymakers navigate the rapidly evolving field of DF detection by presenting a structured overview of the available knowledge. The findings of this literature map suggest that DF detection is a multidisciplinary field that requires collaboration between experts in computer vision, machine learning, cybersecurity, and media forensics to address its current and future challenges

近年来，深度伪造（DFs）--利用人工智能制作的真实操控媒体--引起了人们的极大关注。随着这项技术的发展，迫切需要有效的检测方法来打击滥用行为。计算机科学研究人员越来越重视阻止深度伪造（DFs）在社交媒体上的传播。然而，该领域的研究还没有一个全面的概述。本文提出了一个系统的文献地图，分析了 2018 年至 2024 年 6 月间发表的 286 项主要研究中有关社交媒体上 DF 传播的研究。这些研究按照研究类型、贡献和重点进行了分类，显示出研究重点主要集中在检测解决方案上。值得注意的是，在评估这些解决方案、使用数字干预措施遏制传播以及管理 DF 传播方面存在巨大差距。本文献地图将通过对现有知识的结构化概述，帮助研究人员、从业人员和政策制定者了解快速发展的 DF 检测领域。本文献地图的研究结果表明，DF 检测是一个多学科领域，需要计算机视觉、机器学习、网络安全和媒体取证等领域的专家通力合作，共同应对当前和未来的挑战。

{"title":"SLM-DFS: A systematic literature map of deepfake spread on social media","authors":"El-Sayed Atlam , Malik Almaliki , Ghada Elmarhomy , Abdulqader M. Almars , Awatif M.A. Elsiddieg , Rasha ElAgamy","doi":"10.1016/j.aej.2024.10.076","DOIUrl":"10.1016/j.aej.2024.10.076","url":null,"abstract":"<div><div>In recent years, deepfakes (DFs)-realistically manipulated media created using artificial intelligence—have raised significant concerns. As this technology evolves, the urgency for effective detection methods to counter misuse intensifies. Computer science researchers are increasingly focused on stopping the spread of deepfakes (DFs) on social media. However, there has been no comprehensive overview of research in this area. This paper presents a systematic literature map that analyzes research on DF spread on social media from 286 primary studies published between 2018 and June 2024. The studies are categorized by their research type, contribution and focus, revealing a predominant emphasis on detection solutions. Notably, there are significant gaps in evaluating these solutions, using digital interventions to curb dissemination, and managing DF propagation. This literature map will aid researchers, practitioners, and policymakers navigate the rapidly evolving field of DF detection by presenting a structured overview of the available knowledge. The findings of this literature map suggest that DF detection is a multidisciplinary field that requires collaboration between experts in computer vision, machine learning, cybersecurity, and media forensics to address its current and future challenges</div></div>","PeriodicalId":7484,"journal":{"name":"alexandria engineering journal","volume":"111 ","pages":"Pages 446-455"},"PeriodicalIF":6.2,"publicationDate":"2024-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142537774","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

ArtDiff: Integrating IoT and AI to enhance precision in ancient mural restoration ArtDiff：整合物联网和人工智能，提高古代壁画修复的精度

IF 6.2 2区工程技术 Q1 ENGINEERING, MULTIDISCIPLINARY

alexandria engineering journal

Pub Date : 2024-10-29 DOI: 10.1016/j.aej.2024.09.120

Yuhan Yan , Bowen Chai , Jiapeng Li

Ancient murals, as invaluable cultural artifacts, have profound historical and cultural significance. However, these murals often face degradation phenomena such as peeling, fading, and cracking, which compromises their preservation. Conventional methodologies for protection and restoration exhibit limitations and do not adequately address multifaceted damage conditions, thus necessitating the integration of advanced technological interventions to enhance restoration effectiveness.This paper delineates a framework for the preservation and restoration of cultural heritage buildings that uses Internet of Things (IoT) technology and Artificial Intelligence (AI). Using real-time environmental and structural health surveillance, in conjunction with security mechanisms, this framework markedly improves precision and efficiency in forecasting and identifying potential risks.Furthermore, in the context of mural restoration, this paper introduces the ArtDiff model. This model amalgamates a modified U-Net for initial crack detection with an edge-guided restoration technique, employing a diffusion model for meticulous restoration. Empirical results substantiate the superiority of the ArtDiff model in crack detection and mural restoration, delivering a greater precision and efficacy relative to existing approaches. Through the implementation of multilevel supervision strategies and an avant-garde model architecture, this study offers a sophisticated mural restoration solution, furnishing novel technological support for the preservation of cultural heritage.

古代壁画作为宝贵的文物，具有深远的历史和文化意义。然而，这些壁画经常面临剥落、褪色和开裂等退化现象，影响了壁画的保存。传统的保护和修复方法存在局限性，不能充分解决多方面的损坏情况，因此需要整合先进的技术干预措施来提高修复效果。此外，在壁画修复方面，本文介绍了 ArtDiff 模型。此外，在壁画修复方面，本文介绍了 ArtDiff 模型。该模型将用于初始裂缝检测的改进型 U-Net 与边缘引导修复技术相结合，并采用扩散模型进行细致修复。实证结果证明了 ArtDiff 模型在裂缝检测和壁画修复方面的优越性，与现有方法相比，它具有更高的精度和功效。通过实施多层次监督策略和前卫的模型架构，本研究提供了一种复杂的壁画修复解决方案，为文化遗产保护提供了新颖的技术支持。

{"title":"ArtDiff: Integrating IoT and AI to enhance precision in ancient mural restoration","authors":"Yuhan Yan , Bowen Chai , Jiapeng Li","doi":"10.1016/j.aej.2024.09.120","DOIUrl":"10.1016/j.aej.2024.09.120","url":null,"abstract":"<div><div>Ancient murals, as invaluable cultural artifacts, have profound historical and cultural significance. However, these murals often face degradation phenomena such as peeling, fading, and cracking, which compromises their preservation. Conventional methodologies for protection and restoration exhibit limitations and do not adequately address multifaceted damage conditions, thus necessitating the integration of advanced technological interventions to enhance restoration effectiveness.This paper delineates a framework for the preservation and restoration of cultural heritage buildings that uses Internet of Things (IoT) technology and Artificial Intelligence (AI). Using real-time environmental and structural health surveillance, in conjunction with security mechanisms, this framework markedly improves precision and efficiency in forecasting and identifying potential risks.Furthermore, in the context of mural restoration, this paper introduces the ArtDiff model. This model amalgamates a modified U-Net for initial crack detection with an edge-guided restoration technique, employing a diffusion model for meticulous restoration. Empirical results substantiate the superiority of the ArtDiff model in crack detection and mural restoration, delivering a greater precision and efficacy relative to existing approaches. Through the implementation of multilevel supervision strategies and an avant-garde model architecture, this study offers a sophisticated mural restoration solution, furnishing novel technological support for the preservation of cultural heritage.</div></div>","PeriodicalId":7484,"journal":{"name":"alexandria engineering journal","volume":"111 ","pages":"Pages 511-520"},"PeriodicalIF":6.2,"publicationDate":"2024-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142537770","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

3D-AOCL: Analytic online continual learning for imbalanced 3D point cloud classification 3D-AOCL：不平衡三维点云分类的分析在线持续学习

IF 6.2 2区工程技术 Q1 ENGINEERING, MULTIDISCIPLINARY

alexandria engineering journal

Pub Date : 2024-10-29 DOI: 10.1016/j.aej.2024.10.037

Ziqian Zeng , Jianwei Wang , Lin Wu , Weikai Lu , Huiping Zhuang

Recent autonomous driving systems heavily rely on 3D point cloud data collected from multiple sensors for environmental awareness and decision-making. However, it is unrealistic to expect the autonomous driving system to recognize all road environments and handle every traffic situation. Models for autonomous driving need to be updated in real time in order for the system to adapt to more situations. This is where online continual learning becomes crucial. Online continual learning is an important method in the field of autonomous driving, as it enables models to update their parameters with streaming input data for adapting to new environments and conditions. Online continual learning in the field of autonomous driving faces several challenges: inefficient data fusion, catastrophic forgetting, insufficient computational resources, violation of road privacy and categories imbalance. To tackle these challenges, we propose an Analytic Online Continual Learning method for 3D Point Cloud Classification (3D-AOCL). This approach utilizes Analytic Learning to update parameters and integrates a feature fusion module along with a category balancer to address the above issues. It is capable of fusing data in feature level, balancing samples across various categories and updating parameters by calculating the analytical solution. We have validated our method on the vehicle side, the infrastructure side, and vehicle-infrastructure cooperative data on the V2X-Seq dataset. The experimental results demonstrate that our model effectively addresses key issues in online continual learning for autonomous driving systems, outperforming other models by approximately 4.00% to 6.00% in AMCA scores while only keeping 0.75% trainable parameters.

最近的自动驾驶系统在很大程度上依赖于从多个传感器收集的三维点云数据来进行环境感知和决策。然而，期望自动驾驶系统识别所有道路环境并处理所有交通状况是不现实的。自动驾驶模型需要实时更新，以便系统适应更多情况。这就是在线持续学习的关键所在。在线持续学习是自动驾驶领域的一种重要方法，因为它能使模型根据流输入数据更新参数，以适应新的环境和条件。自动驾驶领域的在线持续学习面临着几个挑战：数据融合效率低下、灾难性遗忘、计算资源不足、侵犯道路隐私和类别不平衡。为了应对这些挑战，我们提出了一种用于三维点云分类的分析在线持续学习方法（3D-AOCL）。该方法利用分析学习更新参数，并集成了一个特征融合模块和一个类别平衡器，以解决上述问题。它能够在特征级融合数据，平衡不同类别的样本，并通过计算分析解决方案更新参数。我们在 V2X-Seq 数据集上对车辆端、基础设施端以及车辆-基础设施合作数据验证了我们的方法。实验结果表明，我们的模型有效地解决了自动驾驶系统在线持续学习的关键问题，在 AMCA 分数上比其他模型高出约 4.00% 至 6.00%，同时只保留了 0.75% 的可训练参数。

{"title":"3D-AOCL: Analytic online continual learning for imbalanced 3D point cloud classification","authors":"Ziqian Zeng , Jianwei Wang , Lin Wu , Weikai Lu , Huiping Zhuang","doi":"10.1016/j.aej.2024.10.037","DOIUrl":"10.1016/j.aej.2024.10.037","url":null,"abstract":"<div><div>Recent autonomous driving systems heavily rely on 3D point cloud data collected from multiple sensors for environmental awareness and decision-making. However, it is unrealistic to expect the autonomous driving system to recognize all road environments and handle every traffic situation. Models for autonomous driving need to be updated in real time in order for the system to adapt to more situations. This is where online continual learning becomes crucial. Online continual learning is an important method in the field of autonomous driving, as it enables models to update their parameters with streaming input data for adapting to new environments and conditions. Online continual learning in the field of autonomous driving faces several challenges: inefficient data fusion, catastrophic forgetting, insufficient computational resources, violation of road privacy and categories imbalance. To tackle these challenges, we propose an Analytic Online Continual Learning method for 3D Point Cloud Classification (3D-AOCL). This approach utilizes Analytic Learning to update parameters and integrates a feature fusion module along with a category balancer to address the above issues. It is capable of fusing data in feature level, balancing samples across various categories and updating parameters by calculating the analytical solution. We have validated our method on the vehicle side, the infrastructure side, and vehicle-infrastructure cooperative data on the V2X-Seq dataset. The experimental results demonstrate that our model effectively addresses key issues in online continual learning for autonomous driving systems, outperforming other models by approximately 4.00% to 6.00% in AMCA scores while only keeping 0.75% trainable parameters.</div></div>","PeriodicalId":7484,"journal":{"name":"alexandria engineering journal","volume":"111 ","pages":"Pages 530-539"},"PeriodicalIF":6.2,"publicationDate":"2024-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142537763","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Topic-aware neural attention network for malicious social media spam detection 用于恶意社交媒体垃圾邮件检测的主题感知神经注意网络

IF 6.2 2区工程技术 Q1 ENGINEERING, MULTIDISCIPLINARY

alexandria engineering journal

Pub Date : 2024-10-29 DOI: 10.1016/j.aej.2024.10.073

Maged Nasser , Faisal Saeed , Aminu Da’u , Abdulaziz Alblwi , Mohammed Al-Sarem

Social media platforms, such as Facebook and X (formally known as Twitter), have become indispensable tools in today's society because they facilitate social discussion and information sharing. This feature makes social networks more attractive for spammers who intentionally spread fake messages, post malicious links and spread rumours. Recently, several machine learning methods have been introduced for social network malicious spam classification. However, most existing methods generally rely on handcrafted features and traditional embedding models, which are relatively less effective. Therefore, inspired by the success of the neural attention network, we propose an interactive neural attention-based method for malicious spam detection by integrating long short-term memory (LSTM), topic modelling, and the BERT technique. In the proposed approach, first, we employed the LSTM encoder, which was integrated with the Twitter latent Dirichlet allocation (LDA) model via an interactive attention mechanism to jointly learn local content and global topic representations. Second, to further learn the contextualized features of texts, the model was further integrated with the BERT technique. Last, the Softmax function was then applied at the output layer for the final spam classification. A series of experiments were conducted utilizing two real-world datasets to evaluate the model. Using dataset 1, the proposed model outperformed the baseline techniques, with average improvements in recall, precision, and F1 and accuracies of 17.54 %, 6.19 %, 11.91 %, and 12.27 %, respectively. In addition, the proposed model performed well for the second dataset and obtained average gains of 11.81 %, 4.38 %, 8.12, and 7.42 in terms of recall, precision, F1, and accuracy, respectively.

Facebook 和 X（正式名称为 Twitter）等社交媒体平台已成为当今社会不可或缺的工具，因为它们促进了社会讨论和信息共享。这一特点使得社交网络对故意传播虚假信息、发布恶意链接和散布谣言的垃圾邮件发送者更具吸引力。最近，有几种机器学习方法被引入到社交网络恶意垃圾邮件分类中。然而，现有的大多数方法一般都依赖于手工制作的特征和传统的嵌入模型，效果相对较差。因此，受神经注意网络成功经验的启发，我们提出了一种基于交互式神经注意的恶意垃圾邮件检测方法，该方法综合了长短期记忆（LSTM）、主题建模和 BERT 技术。在所提出的方法中，首先，我们采用了 LSTM 编码器，并通过交互式注意力机制将其与 Twitter 潜在 Dirichlet 分配（LDA）模型相结合，以共同学习局部内容和全局话题表征。其次，为了进一步学习文本的上下文特征，该模型进一步与 BERT 技术相结合。最后，在输出层应用 Softmax 函数进行最终的垃圾邮件分类。我们利用两个真实世界的数据集进行了一系列实验，以评估该模型。利用数据集 1，所提出的模型在召回率、精确度、F1 和准确度方面的平均改进分别为 17.54 %、6.19 %、11.91 % 和 12.27 %，优于基线技术。此外，所提出的模型在第二个数据集上也表现出色，在召回率、精确度、F1 和准确度方面的平均收益分别为 11.81 %、4.38 %、8.12 和 7.42 %。

{"title":"Topic-aware neural attention network for malicious social media spam detection","authors":"Maged Nasser , Faisal Saeed , Aminu Da’u , Abdulaziz Alblwi , Mohammed Al-Sarem","doi":"10.1016/j.aej.2024.10.073","DOIUrl":"10.1016/j.aej.2024.10.073","url":null,"abstract":"<div><div>Social media platforms, such as Facebook and X (formally known as Twitter), have become indispensable tools in today's society because they facilitate social discussion and information sharing. This feature makes social networks more attractive for spammers who intentionally spread fake messages, post malicious links and spread rumours. Recently, several machine learning methods have been introduced for social network malicious spam classification. However, most existing methods generally rely on handcrafted features and traditional embedding models, which are relatively less effective. Therefore, inspired by the success of the neural attention network, we propose an interactive neural attention-based method for malicious spam detection by integrating long short-term memory (LSTM), topic modelling, and the BERT technique. In the proposed approach, first, we employed the LSTM encoder, which was integrated with the Twitter latent Dirichlet allocation (LDA) model via an interactive attention mechanism to jointly learn local content and global topic representations. Second, to further learn the contextualized features of texts, the model was further integrated with the BERT technique. Last, the Softmax function was then applied at the output layer for the final spam classification. A series of experiments were conducted utilizing two real-world datasets to evaluate the model. Using dataset 1, the proposed model outperformed the baseline techniques, with average improvements in recall, precision, and F1 and accuracies of 17.54 %, 6.19 %, 11.91 %, and 12.27 %, respectively. In addition, the proposed model performed well for the second dataset and obtained average gains of 11.81 %, 4.38 %, 8.12, and 7.42 in terms of recall, precision, F1, and accuracy, respectively.</div></div>","PeriodicalId":7484,"journal":{"name":"alexandria engineering journal","volume":"111 ","pages":"Pages 540-554"},"PeriodicalIF":6.2,"publicationDate":"2024-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142537764","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Tropical cyclone track prediction model for multidimensional features and time differences series observation 多维特征和时差序列观测的热带气旋路径预测模型

IF 6.2 2区工程技术 Q1 ENGINEERING, MULTIDISCIPLINARY

alexandria engineering journal

Pub Date : 2024-10-29 DOI: 10.1016/j.aej.2024.10.090

Peihao Yang , Guodong Ye

Tropical Cyclones (TCs) are highly destructive weather phenomena that can cause significant social and economic damage. With the development of meteorological monitoring technology and the updating of database, accurately forecasting the track of TC movement is one of the effective ways to minimize losses. However, traditional movement track forecasting methods suffer the disadvantages of low efficiency and low accuracy. To address the these problems, a novel Convolutional Neural Network-Temporal Convolutional Network (CNN-TCN) model based on Multidimensional Features and Time Difference Series (MT-CNN-TCN) is presented in this paper. First, different types of meteorological data are processed and then the feature differences between adjoining moments are extracted. Second, a two-branch structure based on Two Dimensional Convolutional Neural Network (2DCNN), 3DCNN and TCN is taken to effectively integrate different types of meteorological features to strengthen its forecasting effect. Finally, experiments are conducted using Northwest Pacific TC data from years 2000–2019. Test results show that the proposed model MT-CNN-TCN can perform well at all three forecast periods (12 h, 24 h, and 48 h), with a significant improvement in accuracy by 7 %, 13 %, and 16 % respectively, compared with current forecasting methods such as Long Short Term Memory (LSTM).

热带气旋（TC）是一种破坏性极强的天气现象，可造成重大的社会和经济损失。随着气象监测技术的发展和数据库的更新，准确预报热带气旋的移动路径是将损失降到最低的有效方法之一。然而，传统的移动轨迹预报方法存在效率低、精度低的缺点。针对这些问题，本文提出了一种基于多维特征和时差序列的新型卷积神经网络-时差卷积网络（CNN-TCN）模型（MT-CNN-TCN）。首先，对不同类型的气象数据进行处理，然后提取相邻时刻之间的特征差异。其次，采用基于二维卷积神经网络（2DCNN）、3DCNN 和 TCN 的双分支结构，有效整合不同类型的气象特征，以加强其预报效果。最后，利用西北太平洋 2000-2019 年的 TC 数据进行了试验。测试结果表明，所提出的 MT-CNN-TCN 模型在三个预报时段（12 h、24 h 和 48 h）均表现良好，与当前的预报方法（如长短期记忆（LSTM））相比，准确率分别显著提高了 7%、13% 和 16%。

{"title":"Tropical cyclone track prediction model for multidimensional features and time differences series observation","authors":"Peihao Yang , Guodong Ye","doi":"10.1016/j.aej.2024.10.090","DOIUrl":"10.1016/j.aej.2024.10.090","url":null,"abstract":"<div><div>Tropical Cyclones (TCs) are highly destructive weather phenomena that can cause significant social and economic damage. With the development of meteorological monitoring technology and the updating of database, accurately forecasting the track of TC movement is one of the effective ways to minimize losses. However, traditional movement track forecasting methods suffer the disadvantages of low efficiency and low accuracy. To address the these problems, a novel Convolutional Neural Network-Temporal Convolutional Network (CNN-TCN) model based on Multidimensional Features and Time Difference Series (MT-CNN-TCN) is presented in this paper. First, different types of meteorological data are processed and then the feature differences between adjoining moments are extracted. Second, a two-branch structure based on Two Dimensional Convolutional Neural Network (2DCNN), 3DCNN and TCN is taken to effectively integrate different types of meteorological features to strengthen its forecasting effect. Finally, experiments are conducted using Northwest Pacific TC data from years 2000–2019. Test results show that the proposed model MT-CNN-TCN can perform well at all three forecast periods (12 h, 24 h, and 48 h), with a significant improvement in accuracy by 7 %, 13 %, and 16 % respectively, compared with current forecasting methods such as Long Short Term Memory (LSTM).</div></div>","PeriodicalId":7484,"journal":{"name":"alexandria engineering journal","volume":"111 ","pages":"Pages 432-445"},"PeriodicalIF":6.2,"publicationDate":"2024-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142537773","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Optimizing data retrieval latency in IoT through information centric in-network caching 通过以信息为中心的网内缓存优化物联网中的数据检索延迟

IF 6.2 2区工程技术 Q1 ENGINEERING, MULTIDISCIPLINARY

alexandria engineering journal

Pub Date : 2024-10-29 DOI: 10.1016/j.aej.2024.10.067

Muhammad Ali Naeem , Meng Yahui , Ahmad Abrar

The integration of Information Centric Networking (ICN) with the Internet of Things (IoT) will meet the expectations of end users by providing an admirable network system. ICN enhances the IoT by utilizing in-network caching regarding data dissemination with the help of various paths labeled by the name of the path by which the data is returned. Caching is a significant technique for improving content accessibility, reducing hops while transferring data, and finally shortening data access time, which in turn improves IoT networks. This study develops a novel caching strategy that caches content in suitable locations at highly requested nodes, thereby improving the information caching efficiency of ICN-based IoT systems. When comparing the proposed caching scheme with other caching methods, it pay attention to the data retrieval latency, cache hit ratio, and the average number of hops. These results consistently show that the proposed strategy enhances cache performance by a high margin. The future context of the utilization of the specified caching strategy will lie in the advancements of fog, edge, and ad hoc networks concerning the concept of IoT and new trends like 5 G and 6 G.

以信息为中心的网络（ICN）与物联网（IoT）的整合将提供一个令人钦佩的网络系统，从而满足终端用户的期望。ICN 借助以数据返回路径名称为标记的各种路径，在数据传播方面利用网内缓存来增强物联网。缓存是提高内容可访问性、减少数据传输跳数并最终缩短数据访问时间的重要技术，从而改善物联网网络。本研究开发了一种新颖的缓存策略，将内容缓存在高请求节点的合适位置，从而提高了基于 ICN 的物联网系统的信息缓存效率。在将所提出的缓存方案与其他缓存方法进行比较时，本研究关注了数据检索延迟、缓存命中率和平均跳数。这些结果一致表明，所提出的策略能大幅提高缓存性能。未来，特定缓存策略的应用范围将包括与物联网概念有关的雾网络、边缘网络和特设网络的发展，以及 5 G 和 6 G 等新趋势。

{"title":"Optimizing data retrieval latency in IoT through information centric in-network caching","authors":"Muhammad Ali Naeem , Meng Yahui , Ahmad Abrar","doi":"10.1016/j.aej.2024.10.067","DOIUrl":"10.1016/j.aej.2024.10.067","url":null,"abstract":"<div><div>The integration of Information Centric Networking (ICN) with the Internet of Things (IoT) will meet the expectations of end users by providing an admirable network system. ICN enhances the IoT by utilizing in-network caching regarding data dissemination with the help of various paths labeled by the name of the path by which the data is returned. Caching is a significant technique for improving content accessibility, reducing hops while transferring data, and finally shortening data access time, which in turn improves IoT networks. This study develops a novel caching strategy that caches content in suitable locations at highly requested nodes, thereby improving the information caching efficiency of ICN-based IoT systems. When comparing the proposed caching scheme with other caching methods, it pay attention to the data retrieval latency, cache hit ratio, and the average number of hops. These results consistently show that the proposed strategy enhances cache performance by a high margin. The future context of the utilization of the specified caching strategy will lie in the advancements of fog, edge, and ad hoc networks concerning the concept of IoT and new trends like 5 G and 6 G.</div></div>","PeriodicalId":7484,"journal":{"name":"alexandria engineering journal","volume":"111 ","pages":"Pages 468-481"},"PeriodicalIF":6.2,"publicationDate":"2024-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142537776","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Design of stepped monopole antennas with a novel decoupling structure based on characteristic mode analysis 基于特征模态分析设计具有新型去耦结构的阶跃单极子天线

IF 6.2 2区工程技术 Q1 ENGINEERING, MULTIDISCIPLINARY

alexandria engineering journal

Pub Date : 2024-10-29 DOI: 10.1016/j.aej.2024.10.060

Myeong-Jun Kang , Daesung Park , Gunyoung Kim , Sunwoo Kim , Kyung-Young Jung

This paper presents a novel approach to enhancing the isolation of adaptive array antennas. The primary focus is on overcoming the limitations of monopole antennas in adaptive array antennas, specifically addressing the challenges posed by mutual coupling between antenna elements and the constraints of decoupling structures. Based on characteristic mode analysis, we propose stepped monopole antennas with an innovation decoupling structure, which significantly reduces mutual coupling without significantly affecting the radiation patterns. The paper details the design and function of these antennas and the development of the decoupling structure and validates the approach through simulation and measurement results

本文提出了一种增强自适应阵列天线隔离度的新方法。主要重点是克服单极子天线在自适应阵列天线中的局限性，特别是解决天线元件之间的相互耦合和去耦结构的限制所带来的挑战。基于特征模态分析，我们提出了具有创新去耦结构的阶梯式单极子天线，它能显著降低相互耦合，而不会对辐射模式造成明显影响。论文详细介绍了这些天线的设计和功能以及去耦结构的开发，并通过仿真和测量结果验证了这一方法。

引用次数: 0

Two-phase Agrawal hybrid nanofluid flow for thermal and solutal transport fluxes induced by a permeable stretching/shrinking disk 可渗透拉伸/收缩盘诱导热和溶质传输通量的两相阿格拉瓦尔混合纳米流体流

IF 6.2 2区工程技术 Q1 ENGINEERING, MULTIDISCIPLINARY

alexandria engineering journal

Pub Date : 2024-10-29 DOI: 10.1016/j.aej.2024.10.075

Hatem Gasmi , Muhammad Waqas , Umair Khan , Aurang Zaib , Anuar Ishak , Imtiaz Khan , Ali Elrashidi , Mohammed Zakarya

Nanofluid is one of the modern heat transfer fluids that offer the potential to substantially enhance the heat transfer efficiency of conventional fluids. Extensive research has been undertaken to explore its fundamental thermophysical properties specifically viscosity and as well as thermal conductivity. This research emphasizes the significance of hybrid nanofluids and investigates the effect of Brownian motion and thermophoretic phenomena on the characteristics of the Agrawal flow that tends to a stagnation point adjacent to a moving porous disk. The model also accounts for the effects of Smoluchowski temperature and Maxwell velocity slip conditions. Through the utilization of similarity ansatz, the governing partial differential equations are simplified into a class of ordinary differential (similarity) equations. Subsequently, these simplified equations achieved numerical solutions by employing the bvp4c solver, which is specifically designed for fourth-ordered boundary value problems. The study delves into the remarkable impacts of the pertinent embedded parameters on key parameters such as mass transfer rate, heat transfer rate, and shear stress. These effects are brilliantly depicted through a combination of graphs and tables. Graphical analyses disclose the presence of dual solutions within a particular range of the stretching/shrinking parameter. Also, enhancing the solid volume fraction of nanoparticles leads to a notable rise in the shear stress and heat transfer for both solution branches, whereas the mass transfer rate experiences a reduction.

纳米流体是现代传热流体之一，具有大幅提高传统流体传热效率的潜力。人们对其基本热物理性质，特别是粘度和导热性能进行了广泛的研究。本研究强调了混合纳米流体的重要性，并研究了布朗运动和热泳现象对阿格拉瓦尔流特性的影响。该模型还考虑了斯莫卢霍夫斯基温度和麦克斯韦速度滑移条件的影响。通过使用相似性等式，支配偏微分方程被简化为一类常微分（相似性）方程。随后，这些简化方程通过使用专为四阶边界值问题设计的 bvp4c 求解器实现了数值求解。研究深入探讨了相关嵌入参数对传质速率、传热速率和剪切应力等关键参数的显著影响。这些影响通过图表和表格相结合的方式得到了很好的描述。图形分析表明，在特定的拉伸/收缩参数范围内存在双重解决方案。此外，提高纳米粒子的固体体积分数会导致两种溶液分支的剪切应力和传热显著增加，而传质速率则会降低。

{"title":"Two-phase Agrawal hybrid nanofluid flow for thermal and solutal transport fluxes induced by a permeable stretching/shrinking disk","authors":"Hatem Gasmi , Muhammad Waqas , Umair Khan , Aurang Zaib , Anuar Ishak , Imtiaz Khan , Ali Elrashidi , Mohammed Zakarya","doi":"10.1016/j.aej.2024.10.075","DOIUrl":"10.1016/j.aej.2024.10.075","url":null,"abstract":"<div><div>Nanofluid is one of the modern heat transfer fluids that offer the potential to substantially enhance the heat transfer efficiency of conventional fluids. Extensive research has been undertaken to explore its fundamental thermophysical properties specifically viscosity and as well as thermal conductivity. This research emphasizes the significance of hybrid nanofluids and investigates the effect of Brownian motion and thermophoretic phenomena on the characteristics of the Agrawal flow that tends to a stagnation point adjacent to a moving porous disk. The model also accounts for the effects of Smoluchowski temperature and Maxwell velocity slip conditions. Through the utilization of similarity ansatz, the governing partial differential equations are simplified into a class of ordinary differential (similarity) equations. Subsequently, these simplified equations achieved numerical solutions by employing the bvp4c solver, which is specifically designed for fourth-ordered boundary value problems. The study delves into the remarkable impacts of the pertinent embedded parameters on key parameters such as mass transfer rate, heat transfer rate, and shear stress. These effects are brilliantly depicted through a combination of graphs and tables. Graphical analyses disclose the presence of dual solutions within a particular range of the stretching/shrinking parameter. Also, enhancing the solid volume fraction of nanoparticles leads to a notable rise in the shear stress and heat transfer for both solution branches, whereas the mass transfer rate experiences a reduction.</div></div>","PeriodicalId":7484,"journal":{"name":"alexandria engineering journal","volume":"111 ","pages":"Pages 566-578"},"PeriodicalIF":6.2,"publicationDate":"2024-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142537768","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Advanced modeling of seepage dynamics and control strategies in thick coal seams under high-confined aquifer conditions: A case study 高封闭含水层条件下厚煤层渗流动力学和控制策略的高级建模：案例研究

IF 6.2 2区工程技术 Q1 ENGINEERING, MULTIDISCIPLINARY

alexandria engineering journal

Pub Date : 2024-10-26 DOI: 10.1016/j.aej.2024.09.069

Xuyang Chen , Xufeng Wang , Dongsheng Zhang , Liang Chen , Jiyao Wang , Zechao Chang , Dongdong Qin , Hao Lv

The hydraulic behavior of the connection between the floor failure area and the aquifer water-conductive zone is considered to be the root cause of mine water inrush disasters. Therefore, unraveling the floor failure mechanism is particularly important for safe coal mining above the high-confined aquifer. This paper estimates the depth of the baseplate failure to be 18.4–27.3 m by combining network parallel electrical methods with drilling visualization technology. The FLAC3D-based numerical model considering the strain hardening of caved rock was established with rigorous calibration and verification. The results showed that the depth of damage to the floor is 23.1 m, and the dominating floor failure mechanism is shear failure caused by the vertical stress exceeding the rock bearing capacity. Moreover, the stress recovery process of the baseplate does not alter the failure morphology of the baseplate. Based on the above research findings, the in-situ floor control technique of the working face No. 4305 is proposed and practiced in the field. Field measurements show that floor control performance is satisfactory with water inflow in the goaf being roughly stable at 50 m³/h. Our results can provide useful reference for safe mining above confined aquifer and prevention and mitigation of water-related hazards.

底板破坏区与含水层导水带之间连接的水力行为被认为是矿井涌水灾害的根本原因。因此，揭示底板破坏机理对高封闭含水层上的煤矿安全开采尤为重要。本文通过将网络并行电法与钻孔可视化技术相结合，估算出底板破坏深度为 18.4-27.3 米。建立了基于 FLAC3D 的数值模型，考虑了空洞岩石的应变硬化，并进行了严格的校核和验证。结果表明，底板破坏深度为 23.1 米，主要的底板破坏机理是垂直应力超过岩石承载力导致的剪切破坏。此外，底板的应力恢复过程不会改变底板的破坏形态。根据上述研究成果，提出了 4305 号工作面的原位底板控制技术，并在现场进行了实践。现场测量结果表明，底板控制性能令人满意，巷道进水量基本稳定在 50 立方米/小时。我们的研究结果可为在承压含水层上安全采矿以及预防和减轻与水有关的危害提供有益的参考。

{"title":"Advanced modeling of seepage dynamics and control strategies in thick coal seams under high-confined aquifer conditions: A case study","authors":"Xuyang Chen , Xufeng Wang , Dongsheng Zhang , Liang Chen , Jiyao Wang , Zechao Chang , Dongdong Qin , Hao Lv","doi":"10.1016/j.aej.2024.09.069","DOIUrl":"10.1016/j.aej.2024.09.069","url":null,"abstract":"<div><div>The hydraulic behavior of the connection between the floor failure area and the aquifer water-conductive zone is considered to be the root cause of mine water inrush disasters. Therefore, unraveling the floor failure mechanism is particularly important for safe coal mining above the high-confined aquifer. This paper estimates the depth of the baseplate failure to be 18.4–27.3 m by combining network parallel electrical methods with drilling visualization technology. The FLAC3D-based numerical model considering the strain hardening of caved rock was established with rigorous calibration and verification. The results showed that the depth of damage to the floor is 23.1 m, and the dominating floor failure mechanism is shear failure caused by the vertical stress exceeding the rock bearing capacity. Moreover, the stress recovery process of the baseplate does not alter the failure morphology of the baseplate. Based on the above research findings, the in-situ floor control technique of the working face No. 4305 is proposed and practiced in the field. Field measurements show that floor control performance is satisfactory with water inflow in the goaf being roughly stable at 50 m<sup>3</sup>/h. Our results can provide useful reference for safe mining above confined aquifer and prevention and mitigation of water-related hazards.</div></div>","PeriodicalId":7484,"journal":{"name":"alexandria engineering journal","volume":"111 ","pages":"Pages 415-431"},"PeriodicalIF":6.2,"publicationDate":"2024-10-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142533043","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

MGScoliosis: Multi-grained scoliosis detection with joint ordinal regression from natural image MGScoliosis：利用自然图像的联合序数回归进行多粒度脊柱侧弯检测

IF 6.2 2区工程技术 Q1 ENGINEERING, MULTIDISCIPLINARY

alexandria engineering journal

Pub Date : 2024-10-24 DOI: 10.1016/j.aej.2024.10.066

Xiaojia Zhu , Rui Chen , Zhiwen Shao , Ming Zhang , Yuhu Dai , Wenzhi Zhang , Chuandong Lang

Scoliosis is among the most prevalent diseases affecting teenagers. However, traditional scoliosis screening methods often resort to physical examination or radiographic imaging. The two ways both rely on experts with high costs, which are not suitable for wide-range screening. Besides, estimating Cobb angle level only using natural images are challenging. To tackle these issues, we propose a multi-grained scoliosis detection framework by jointly estimating severity level and Cobb angle level of scoliosis from a natural image instead of a radiographic image, which has not been explored before. Specifically, we regard scoliosis estimation as an ordinal regression problem, and transform it into a series of binary classification sub-problems. Besides, we adopt the visual attention network with large kernel attention as the backbone for feature learning, which can model local and global correlations with efficient computations. The feature learning and the ordinal regression is put into an end-to-end framework, in which the two tasks of scoliosis severity level estimation and scoliosis angle level estimation are jointly learned and can contribute to each other. Extensive experiments demonstrate that our approach outperforms state-of-the-art methods as well as human performance, which provides a promising and economical solution to wide-range scoliosis screening. Particularly, our approach achieves accuracies of 94.90% and 79.62% in estimating severity level and Cobb angle level, improving large margins of 4.90% and 12.15% over existing natural image based scoliosis detection performance, respectively. The code is available at https://github.com/RuiChen-stack/MGScoliosis.

脊柱侧弯是影响青少年的最常见疾病之一。然而，传统的脊柱侧弯筛查方法通常采用体格检查或放射成像。这两种方法都依赖专家，成本高昂，不适合大范围筛查。此外，仅使用自然图像估计 Cobb 角水平也具有挑战性。为了解决这些问题，我们提出了一个多粒度脊柱侧弯检测框架，通过自然图像而不是放射图像来联合估计脊柱侧弯的严重程度和 Cobb 角度水平。具体来说，我们将脊柱侧弯估计视为一个顺序回归问题，并将其转化为一系列二元分类子问题。此外，我们还采用了具有大核注意力的视觉注意力网络作为特征学习的骨干，它能以高效的计算方式建立局部和全局相关模型。特征学习和顺序回归被放入一个端到端的框架中，其中脊柱侧弯严重程度估计和脊柱侧弯角度估计这两个任务是共同学习的，并且可以相互促进。广泛的实验证明，我们的方法优于最先进的方法，也优于人类的表现，这为大范围脊柱侧弯筛查提供了一个有前景且经济的解决方案。特别是，我们的方法在估计脊柱侧弯严重程度和 Cobb 角度水平方面的准确率分别达到 94.90% 和 79.62%，比现有的基于自然图像的脊柱侧弯检测性能分别提高了 4.90% 和 12.15%。代码见 https://github.com/RuiChen-stack/MGScoliosis。

{"title":"MGScoliosis: Multi-grained scoliosis detection with joint ordinal regression from natural image","authors":"Xiaojia Zhu , Rui Chen , Zhiwen Shao , Ming Zhang , Yuhu Dai , Wenzhi Zhang , Chuandong Lang","doi":"10.1016/j.aej.2024.10.066","DOIUrl":"10.1016/j.aej.2024.10.066","url":null,"abstract":"<div><div>Scoliosis is among the most prevalent diseases affecting teenagers. However, traditional scoliosis screening methods often resort to physical examination or radiographic imaging. The two ways both rely on experts with high costs, which are not suitable for wide-range screening. Besides, estimating Cobb angle level only using natural images are challenging. To tackle these issues, we propose a multi-grained scoliosis detection framework by jointly estimating severity level and Cobb angle level of scoliosis from a natural image instead of a radiographic image, which has not been explored before. Specifically, we regard scoliosis estimation as an ordinal regression problem, and transform it into a series of binary classification sub-problems. Besides, we adopt the visual attention network with large kernel attention as the backbone for feature learning, which can model local and global correlations with efficient computations. The feature learning and the ordinal regression is put into an end-to-end framework, in which the two tasks of scoliosis severity level estimation and scoliosis angle level estimation are jointly learned and can contribute to each other. Extensive experiments demonstrate that our approach outperforms state-of-the-art methods as well as human performance, which provides a promising and economical solution to wide-range scoliosis screening. Particularly, our approach achieves accuracies of 94.90% and 79.62% in estimating severity level and Cobb angle level, improving large margins of 4.90% and 12.15% over existing natural image based scoliosis detection performance, respectively. The code is available at <span><span>https://github.com/RuiChen-stack/MGScoliosis</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":7484,"journal":{"name":"alexandria engineering journal","volume":"111 ","pages":"Pages 329-340"},"PeriodicalIF":6.2,"publicationDate":"2024-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142532986","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0