Ain Shams Engineering Journal最新文献

筛选
英文 中文
Efficient nitrogen recovery from domestic wastewater through struvite precipitation: Optimizing process parameters and characterization analysis 鸟粪石沉淀法高效回收生活污水中的氮:工艺参数优化及表征分析
IF 5.9 2区 工程技术
Ain Shams Engineering Journal Pub Date : 2025-09-23 DOI: 10.1016/j.asej.2025.103760
Raghda Hamdi , Hassimi Abu Hasan , Mohd Hafizuddin Muhamad , Nur Aisyah Nazairi
{"title":"Efficient nitrogen recovery from domestic wastewater through struvite precipitation: Optimizing process parameters and characterization analysis","authors":"Raghda Hamdi ,&nbsp;Hassimi Abu Hasan ,&nbsp;Mohd Hafizuddin Muhamad ,&nbsp;Nur Aisyah Nazairi","doi":"10.1016/j.asej.2025.103760","DOIUrl":"10.1016/j.asej.2025.103760","url":null,"abstract":"<div><div>Recovery of nitrogen from domestic wastewater through struvite precipitation enables the circular economy with revenue generation to treatment plants. Struvite formation factors (pH, magnesium mass, and reagent type) were investigated in the present study. Struvite is formed via a reaction involving NH<sub>4</sub><sup>+</sup>-N, Mg, and P. Magnesium sources (MgCl<sub>2</sub>, MgSO<sub>4</sub>, MgO), pH (5–11), and magnesium mass (0.5–1.25 g) were identified using response surface methodology (RSM). The optimal condition was pH 8.53 with 1.13 g MgO, resulting in 97.0 % NH<sub>3</sub>-N removal and 2.66 g struvite production. The quality of struvite was characterized by scanning electron microscopy (SEM), X-ray diffraction (XRD), and Fourier-transform infrared spectroscopy (FTIR), indicating an irregular rod-shaped morphology, 12.2 nm crystalline size, and 98.9 % crystallinity. The findings highlight the necessity to enhance nitrogen recovery efficiency for large-scale wastewater treatment considering the future potential of struvite.</div></div>","PeriodicalId":48648,"journal":{"name":"Ain Shams Engineering Journal","volume":"16 12","pages":"Article 103760"},"PeriodicalIF":5.9,"publicationDate":"2025-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145118850","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}
引用次数: 0
Robust open-set partial discharge diagnosis based on hybrid supervised contrastive learning and SVM framework 基于混合监督对比学习和支持向量机框架的鲁棒开集局部放电诊断
IF 5.9 2区 工程技术
Ain Shams Engineering Journal Pub Date : 2025-09-23 DOI: 10.1016/j.asej.2025.103762
H.P.D.Shiran Madhuranga, Wong Jee Keen Raymond, Hazlee Azil Illias, Nurulafiqah Nadzirah Binti Mansor
{"title":"Robust open-set partial discharge diagnosis based on hybrid supervised contrastive learning and SVM framework","authors":"H.P.D.Shiran Madhuranga,&nbsp;Wong Jee Keen Raymond,&nbsp;Hazlee Azil Illias,&nbsp;Nurulafiqah Nadzirah Binti Mansor","doi":"10.1016/j.asej.2025.103762","DOIUrl":"10.1016/j.asej.2025.103762","url":null,"abstract":"<div><div>Automated partial discharge (PD) diagnosis using machine learning models is useful for high-voltage equipment (HVE) insulation condition monitoring. However, without a mechanism to identify unknown PD classes (defined as new classes not present in the training data), models will misclassify unknown classes as one of the known classes. To address this, a novel hybrid open-set recognition (OSR) framework based on Supervised Contrastive Learning (SupCon) is proposed to address a previously unexplored direction in the PD diagnosis domain. The framework integrates discriminative representation learning with both unified and per-class rejection strategies using one-class classification, enabling effective separation of known and unknown PD classes. The main contribution is the synergistic integration of SupCon for constructing structured latent spaces, SVM for precise closed-set classification, and dual OCSVMs for adaptive unknown rejection, together forming a unified pipeline that achieves both fine-grained discrimination and robust unknown detection. To evaluate the effectiveness of the proposed framework, comprehensive experiments are conducted across 30 OSR tasks, covering 12 PD classes from three types of high-voltage equipment under varying openness levels. The proposed framework is benchmarked against five state-of-the-art approaches, including ArcFace, GAN-Flow, a convolutional neural network (CNN), Autoencoder, and Vision Transformer. Experimental results demonstrate that the proposed framework achieved the best performance, with a mean normalized accuracy of 97.66 % and a Youden’s index of 0.953, confirming its robustness, generalization capability, and potential to advance open-set PD diagnostic methodologies.</div></div>","PeriodicalId":48648,"journal":{"name":"Ain Shams Engineering Journal","volume":"16 12","pages":"Article 103762"},"PeriodicalIF":5.9,"publicationDate":"2025-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145118854","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}
引用次数: 0
Patented AI tool and method for evaluating building quality - Analysis of indoor environment and human comfort a case study 建筑质量评估的专利人工智能工具和方法——室内环境和人体舒适度分析案例研究
IF 5.9 2区 工程技术
Ain Shams Engineering Journal Pub Date : 2025-09-19 DOI: 10.1016/j.asej.2025.103756
Meqdad Hamdan Hasan , Othman S. Alshamrani , Emhiedy S. Gharaibeh
{"title":"Patented AI tool and method for evaluating building quality - Analysis of indoor environment and human comfort a case study","authors":"Meqdad Hamdan Hasan ,&nbsp;Othman S. Alshamrani ,&nbsp;Emhiedy S. Gharaibeh","doi":"10.1016/j.asej.2025.103756","DOIUrl":"10.1016/j.asej.2025.103756","url":null,"abstract":"<div><div>Ensuring indoor environmental quality and occupant comfort in buildings is critical to enhancing productivity and well-being, yet existing assessment methods often fail to integrate objective measurements (collected by sensors on an autonomous robot, representing measurable environmental parameters such as air quality and temperature) with subjective feedback (gathered via online surveys). This study addresses this gap by developing an autonomous tool for evaluating the quality of buildings and building systems. The objective is to compare the effectiveness of Bayesian Belief Networks, a novel artificial intelligence-based approach, with a classical Linear Additive Method that incorporates Analytic Hierarchy Process and Multi-Attribute Utility Theory. Data collection is achieved using an autonomous robot for objective measurements and Bluetooth-guided occupant surveys for subjective feedback. Two Bayesian Belief network models and one Linear Additive Method model were developed and evaluated using data from an educational building in the Eastern Province of Saudi Arabia. Results show that while the Bayesian Belief Networks algorithm requires more computational time, it effectively handles complexities in hybrid data and provides more reliable predictions for indoor environmental quality. The comparison revealed that one Bayesian Belief Networks closely matches Linear Additive Method results with a correlation coefficient of 0.92, while the other did not converge, highlighting challenges in model optimization. This novel framework offers significant potential for scalable and accurate building quality assessments across diverse building types and climates.</div></div>","PeriodicalId":48648,"journal":{"name":"Ain Shams Engineering Journal","volume":"16 12","pages":"Article 103756"},"PeriodicalIF":5.9,"publicationDate":"2025-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145096583","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}
引用次数: 0
Food safety risk analysis utilising K-lexicographic-max product of neutrosophic graph 利用k -词典-嗜中性图最大产品进行食品安全风险分析
IF 5.9 2区 工程技术
Ain Shams Engineering Journal Pub Date : 2025-09-18 DOI: 10.1016/j.asej.2025.103761
M. Kaviyarasu , M. Rajeshwari , Nasreen Kausar , Dragan Pamucar , Vladimir Simic , Nasser El-Kanj
{"title":"Food safety risk analysis utilising K-lexicographic-max product of neutrosophic graph","authors":"M. Kaviyarasu ,&nbsp;M. Rajeshwari ,&nbsp;Nasreen Kausar ,&nbsp;Dragan Pamucar ,&nbsp;Vladimir Simic ,&nbsp;Nasser El-Kanj","doi":"10.1016/j.asej.2025.103761","DOIUrl":"10.1016/j.asej.2025.103761","url":null,"abstract":"<div><div>In this study, we introduce the concept of the <span><math><mi>K</mi></math></span>-Lexicographic Max Product (<span><math><mi>K</mi><mo>−</mo><mi>LMP</mi></math></span>) of neutrosophic graphs and explore its associated degree structure to enhance decision-making frameworks in food safety applications related to risk assessment, including freshness, contamination, and spoilage. Neutrosophic graphs, capable of handling indeterminacy, inconsistency, and incompleteness, provide a flexible mathematical foundation for modelling complex systems. By incorporating the <span><math><mi>K</mi><mo>−</mo><mi>LMP</mi></math></span> into neutrosophic graphs, we offer a novel approach to comparing and ranking food safety scenarios where multiple attributes and uncertain information coexist. We present example graphs and theorems related to <span><math><mi>K</mi><mo>−</mo><mi>LMP</mi></math></span> and further define the <span><math><mi>K</mi></math></span>-Lexicographic degree to quantify node significance within the context of neutrosophic graphs. To validate the practical utility of this approach, a food safety analysis is implemented, demonstrating how the model identifies critical control points and supports more robust, transparent decision-making under uncertainty. This work contributes to the advancement of neutrosophic graph theory and its interdisciplinary application in food quality and safety management.</div></div>","PeriodicalId":48648,"journal":{"name":"Ain Shams Engineering Journal","volume":"16 12","pages":"Article 103761"},"PeriodicalIF":5.9,"publicationDate":"2025-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145096582","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}
引用次数: 0
Dip-DARK: A smart and innovative classifier for enhanced intrusion detection and security in heterogeneous IoT networks Dip-DARK:一种智能和创新的分类器,用于增强异构物联网网络中的入侵检测和安全性
IF 5.9 2区 工程技术
Ain Shams Engineering Journal Pub Date : 2025-09-18 DOI: 10.1016/j.asej.2025.103692
Mani V.R. , Vivekanandan P.
{"title":"Dip-DARK: A smart and innovative classifier for enhanced intrusion detection and security in heterogeneous IoT networks","authors":"Mani V.R. ,&nbsp;Vivekanandan P.","doi":"10.1016/j.asej.2025.103692","DOIUrl":"10.1016/j.asej.2025.103692","url":null,"abstract":"<div><div>Presently, significant research works focused on the design and development of security methods for protecting Heterogeneous Internet of Things (HetIoT) networks. Yet, the conventional approaches suffer with the problems of high processing time, lower accuracy, increased system designing complexity, and reduced efficiency. Therefore, in the proposed study, a novel and unique framework known as Dip-DARK—Dipper Throated Optimization integrated Deep Activation based Runge Kutta Classifier—is developed to safeguard the HetIoT network from potentially dangerous intrusions. Some of the well-known and most recent intrusion datasets, including as CIC-DDoS 2019, ToN-IoT, Edge-IIoT, and In-SDN, have been used for system development and validation. The proposed model is validated and tested by using these datasets. Then, to effectively shrink the dataset, the most important features are best selected using the Dipper Throated Optimization (DipTO) model, an intelligent optimization method. As a result, the Deep Activation based Runge Kutta (DARK) classifier was able to precisely predict the type of intrusion using the set of optimized features. Additionally, using a variety of performance measures, the proposed Dip-DARK model’s intrusion detection findings are evaluated and contrasted with current state-of-the-art model methodologies.</div></div>","PeriodicalId":48648,"journal":{"name":"Ain Shams Engineering Journal","volume":"16 11","pages":"Article 103692"},"PeriodicalIF":5.9,"publicationDate":"2025-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145104545","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}
引用次数: 0
Mechanical design and motion planning of a centipede-inspired robot 仿蜈蚣机器人的机械设计与运动规划
IF 5.9 2区 工程技术
Ain Shams Engineering Journal Pub Date : 2025-09-18 DOI: 10.1016/j.asej.2025.103754
Ziqiang Zhang , Xiaoshuo Liu , Yiming Wang , Zongtian Liu , Jinnong Liao
{"title":"Mechanical design and motion planning of a centipede-inspired robot","authors":"Ziqiang Zhang ,&nbsp;Xiaoshuo Liu ,&nbsp;Yiming Wang ,&nbsp;Zongtian Liu ,&nbsp;Jinnong Liao","doi":"10.1016/j.asej.2025.103754","DOIUrl":"10.1016/j.asej.2025.103754","url":null,"abstract":"<div><div>Motion planning for hyper-redundant robots in complex terrains has always been a research hotspot in robotics. The main difficulty faced by hyper-redundant robots lies in motion planning on complex terrains such as steps. This study took the centipede as the simulation object and developed a centipede-inspired robot (CeRob). The CeRob consists of 7 independent modules, where each inter-module joint provides two independently controllable DOFs (pitch and yaw). Each module is symmetrically equipped with two single degree-of-freedom (DOF) cam-linkage leg mechanisms, which provide good reliability while meeting trajectory requirements. Subsequently, a front-planning and rear-following motion planning method was proposed. By combining the established objective function and constraints for motion planning of the front joints and achieving smooth following of subsequent motions through the joints, the motion planning efficiency of the robot was improved. The robot designed in this study has broad application prospects in fields such as post-disaster rescue, planetary exploration, and military reconnaissance.</div></div>","PeriodicalId":48648,"journal":{"name":"Ain Shams Engineering Journal","volume":"16 12","pages":"Article 103754"},"PeriodicalIF":5.9,"publicationDate":"2025-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145096580","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}
引用次数: 0
Synergistic control mechanism and engineering practice of full-profile support in karst roadways under dual-wing mining disturbance 双翼采动扰动下岩溶巷道全断面支护协同控制机理及工程实践
IF 5.9 2区 工程技术
Ain Shams Engineering Journal Pub Date : 2025-09-16 DOI: 10.1016/j.asej.2025.103767
Bin Li , Shoukun Chen , Youlin Xu , Bo Zhou , Zhisong Chen , Jitao Zhang
{"title":"Synergistic control mechanism and engineering practice of full-profile support in karst roadways under dual-wing mining disturbance","authors":"Bin Li ,&nbsp;Shoukun Chen ,&nbsp;Youlin Xu ,&nbsp;Bo Zhou ,&nbsp;Zhisong Chen ,&nbsp;Jitao Zhang","doi":"10.1016/j.asej.2025.103767","DOIUrl":"10.1016/j.asej.2025.103767","url":null,"abstract":"<div><div>With increasing mining depth and complex methods, roadways face severe geological challenges like intense deformation and soft rock layers. Support becomes especially difficult in karst regions, which feature fractures and cavities. This study analyzes mining methods, rock behavior, simulations, and field data to identify deformation causes, proving that combined high stress, gas, temperature, and mining disturbances compromise traditional support safety. Alternatively, an innovative full-profile spatial reinforcement technology is proposed, which effectively stabilizes weak, deformable roadways, enhancing long-term performance. The proposed integration of active and passive supports realized in the case study of Songhe Dongyi Mine, Guizhou, China, increased resistance, boosted rock self-bearing capacity, reduced deformation by 38.5 % and stress concentration factor more than twice (from 2.8 to 1.3), controlled floor heave (&lt;50 mm), and improved operation safety. The integrated approach was very effective in geologically complex mining environments, providing theoretically substantiated innovations and practical applications for karst terrain engineering.</div></div>","PeriodicalId":48648,"journal":{"name":"Ain Shams Engineering Journal","volume":"16 12","pages":"Article 103767"},"PeriodicalIF":5.9,"publicationDate":"2025-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145096579","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}
引用次数: 0
Optimization of steady-state target tracking for hybrid dual-type CV systems based on integral slope balance constraints 基于积分斜率平衡约束的混合双型CV系统稳态目标跟踪优化
IF 5.9 2区 工程技术
Ain Shams Engineering Journal Pub Date : 2025-09-16 DOI: 10.1016/j.asej.2025.103743
Hongrui Wang , Pengbin Zhang , Jingyang Wang , Mingzhe Yuan , Jingguang Li
{"title":"Optimization of steady-state target tracking for hybrid dual-type CV systems based on integral slope balance constraints","authors":"Hongrui Wang ,&nbsp;Pengbin Zhang ,&nbsp;Jingyang Wang ,&nbsp;Mingzhe Yuan ,&nbsp;Jingguang Li","doi":"10.1016/j.asej.2025.103743","DOIUrl":"10.1016/j.asej.2025.103743","url":null,"abstract":"<div><div>To address the application gap in target tracking for complex systems featuring hybrid integral-type and stable-type controlled variables, this paper proposes an improved steady-state target tracking method within a double-layer model predictive control framework. To overcome the challenge of accurately characterizing the integral properties of existing decision variables, novel decision variables <span><math><mi>Δ</mi><msub><mrow><mi>u</mi></mrow><mrow><mi>a</mi></mrow></msub></math></span> and <span><math><mi>Δ</mi><msub><mrow><mi>u</mi></mrow><mrow><mi>b</mi></mrow></msub></math></span> are introduced. These variables enable the precise characterization of integral-type controlled variables' steady-state predictions by indirectly expressing <span><math><mi>Δ</mi><msub><mrow><mi>u</mi></mrow><mrow><mi>s</mi></mrow></msub></math></span>. A novel feasibility determination and soft constraint adjustment strategy is subsequently proposed based on <span><math><mi>Δ</mi><msub><mrow><mi>u</mi></mrow><mrow><mi>a</mi></mrow></msub></math></span> and <span><math><mi>Δ</mi><msub><mrow><mi>u</mi></mrow><mrow><mi>b</mi></mrow></msub></math></span>. Furthermore, to resolve the infeasibility issues arising from the dynamic slope balance constraints of integral-type controlled variables, the paper introduces new steady-state slope balance constraints that ensure multi-period slope equilibrium. Simulation results demonstrate that the proposed double-layer model predictive control method significantly enhances the feasibility of the steady-state optimization problem compared to the traditional point-model-based approach. This study provides an innovative solution for steady-state optimization in target tracking of complex systems.</div></div>","PeriodicalId":48648,"journal":{"name":"Ain Shams Engineering Journal","volume":"16 12","pages":"Article 103743"},"PeriodicalIF":5.9,"publicationDate":"2025-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145096581","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}
引用次数: 0
Analysis of the application of generative artificial intelligence in interior design education 生成性人工智能在室内设计教育中的应用分析
IF 5.9 2区 工程技术
Ain Shams Engineering Journal Pub Date : 2025-09-15 DOI: 10.1016/j.asej.2025.103757
Yao Liu , Beiyuan Xu , Jiarong Feng , Pengjun Wu
{"title":"Analysis of the application of generative artificial intelligence in interior design education","authors":"Yao Liu ,&nbsp;Beiyuan Xu ,&nbsp;Jiarong Feng ,&nbsp;Pengjun Wu","doi":"10.1016/j.asej.2025.103757","DOIUrl":"10.1016/j.asej.2025.103757","url":null,"abstract":"<div><div>The rapid advancement of artificial intelligence (AI) has introduced generative AI tools as transformative resources in interior design education, enhancing creativity, aesthetic quality, and practical design outcomes. Traditional interior design education often limits students’ theoretical knowledge, aesthetic skills, and technical abilities development. Generative AI tools such as Stable Diffusion and Midjourney, which utilize big data and deep learning, offer innovative design concepts to address these limitations. This study applies established models—UTAUT and AHP—in a novel educational context to evaluate generative AI tools in terms of creativity, aesthetics, practicality, and feasibility, offering empirically grounded insights for interior design pedagogy. Results showed that Stable Diffusion excelled in creativity, while Midjourney outperformed in aesthetics and functionality, with both tools proved more feasible than traditional methods. Despite challenges such as limited technical support and high hardware requirements, generative AI tools can significantly enhance interior design education by fostering innovation and improving design efficiency.</div></div>","PeriodicalId":48648,"journal":{"name":"Ain Shams Engineering Journal","volume":"16 12","pages":"Article 103757"},"PeriodicalIF":5.9,"publicationDate":"2025-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145059926","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}
引用次数: 0
An explainable hybrid deep learning-optimization framework for robust phishing attack detection using GAN and transformer-based feature learning 一个可解释的混合深度学习优化框架,用于稳健的网络钓鱼攻击检测,使用GAN和基于变压器的特征学习
IF 5.9 2区 工程技术
Ain Shams Engineering Journal Pub Date : 2025-09-15 DOI: 10.1016/j.asej.2025.103745
Raheleh Ghadami (Melisa Rahebi) , Javad Rahebi
{"title":"An explainable hybrid deep learning-optimization framework for robust phishing attack detection using GAN and transformer-based feature learning","authors":"Raheleh Ghadami (Melisa Rahebi) ,&nbsp;Javad Rahebi","doi":"10.1016/j.asej.2025.103745","DOIUrl":"10.1016/j.asej.2025.103745","url":null,"abstract":"<div><div>This study proposes to improve accuracy of phishing detection by proposing a new hybrid deep learning framework that combines data augmentation, feature transformation, and optimization-based feature selection. The proposed approach integrates a Generative Adversarial Network (GAN) to generate synthetic phishing samples, followed by feature extraction using a combination of feature extraction using a combination of Convolutional Neural Network (CNN), Gated Recurrent Unit (GRU), Fully Modified Residual Convolutional Neural Network (FMRCNN), and Transformer models. To reduce feature dimensionality, <strong>the</strong> Black-Winged Kite Algorithm (BKA) <strong>is applied</strong>, while classification is performed using a Support Vector Machine (SVM). Experimental findings on Phishtank dataset demonstrate that the suggested model achieves an accuracy of 98.67%, outperforming other approaches in terms of precision, recall, and F1-score. The novelty of this work lies in the unique combination of GAN with <strong>CNN–GRU–FMRCNN</strong> architectures for phishing detection, further enhanced by hybrid optimization techniques and interpretability via SHAP (SHapley Additive exPlanations) analysis.</div></div>","PeriodicalId":48648,"journal":{"name":"Ain Shams Engineering Journal","volume":"16 12","pages":"Article 103745"},"PeriodicalIF":5.9,"publicationDate":"2025-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145059927","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}
引用次数: 0
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信