Egyptian Informatics Journal最新文献

{"title":"Optimized deep intelligent features for root cause analysis in industrial applications","authors":"Venkata Satya Kaladhar Darbha ,&nbsp;Venkata Muneendra Prasad Chintakayala ,&nbsp;Kiran Mannem","doi":"10.1016/j.eij.2026.100992","DOIUrl":"10.1016/j.eij.2026.100992","url":null,"abstract":"<div><div>In industrial systems, operational effectiveness and machine availability are improved through root cause analysis (RCA). Typically, RCA techniques encounter multiple challenges when dealing with complex, high-dimensional sensor and industrial control system data, which often struggle with scalability, interpretability, and real-time performance. To enhance the accuracy and efficiency of RCA, this research proposes a new system that incorporates improved deep, intelligent features derived from lean CNNs along with attentional architectures. Specifically, the proposed system extracts and ranks significant features in real time through an enhanced Armadillo MobileNet Prediction Framework (AMPF) The proposed approach is superior to popular methods, such as Genetic Algorithms, Gradient Boosting Machines, and Bayesian Networks, in terms of accuracy (96.21%), error rate (0.0379%), and F-score while maintaining resource efficiency on closed devices. Results indicate that smart feature optimization enhances the predictive ability of smart manufacturing systems and improves the clarity of the fault diagnosis system for industrial tools.</div></div>","PeriodicalId":56010,"journal":{"name":"Egyptian Informatics Journal","volume":"34 ","pages":"Article 100992"},"PeriodicalIF":4.3,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148184382","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Two-phase integrated multi-criteria and multi-objective framework for green and resilient food supply chains under uncertainty","authors":"Pavan Sharma ,&nbsp;Jagannath Roy ,&nbsp;Dragan Pamucar","doi":"10.1016/j.eij.2026.100996","DOIUrl":"10.1016/j.eij.2026.100996","url":null,"abstract":"<div><div>Green and resilient supplier selection and order allocation (SSOA) is becoming increasingly challenging because decision data are often incomplete, vague, or conflicting. Many fuzzy multi-attribute decision making (MADM) and multi-objective decision making (MODM) methods still face two key limitations: uncertainty may not be captured sufficiently, and SSOA are frequently handled as separate steps, which can lead to inconsistent or sub-optimal decisions. To overcome these issues, this study proposes a two-phase decision-support framework developed in the p,q-quasirung orthopair fuzzy set (p,q-QOFS) environment. In Phase I, suppliers are evaluated using a hybrid MADM approach under p,q-QOFS. Reliable criteria weights are computed via a p,q-QOFS-based fuzzy weighted zero-inconsistency (FWZIC) method, and suppliers are then ranked using a p,q-QOFS-based DOmbi-Bonferroni weighted ASsessment (DOBAS) method incorporating traditional, environmental, and resilience criteria. In Phase II, a multi-objective programming model is formulated for order allocation with cost, capacity, and resilience constraints. NSGA-III is employed to generate Pareto-optimal solutions, and a TOPSIS-based search–filter step is used to select the best compromise solution. The framework is tested using a real case of food manufacturing company that want to solve SSOA problem involving multiple suppliers and several materials. Results show that resilience criteria strongly influence order allocation, and sensitivity analyses confirm that the solutions remain stable under different settings. Pareto analysis indicates that Total Relevant Cost (TRC) and Environmental Impact (EI) often increase together; in contrast, higher Resilient Sourcing Value (RSV) usually requires higher TRC and EI, with diminishing gains at higher RSV levels. These findings suggest selecting a balanced solution that improves resilience without a large rise in TRC and EI for practical decision-making. Although the case study is limited to one sector, the proposed framework can be adapted to SSOA problems in other industries.</div></div>","PeriodicalId":56010,"journal":{"name":"Egyptian Informatics Journal","volume":"34 ","pages":"Article 100996"},"PeriodicalIF":4.3,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148184887","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Smart requirements modeling: AI-assisted automated generation of UML diagrams from software specifications","authors":"Ahmed Hassan Abase,&nbsp;Hesham Ahmed Hassan,&nbsp;Fatma Abd-Elstar Omara","doi":"10.1016/j.eij.2026.101003","DOIUrl":"10.1016/j.eij.2026.101003","url":null,"abstract":"<div><div>The proposed intelligent framework combines artificial intelligence with traditional programming to automatically transform natural language software requirements into formal UML representations. It uses a pre-trained spaCy model to extract key entities and relationships, which are then transformed into UML diagrams. The evaluation results demonstrate high accuracy, with precision, recall, and F1-scores averaging 0.92. The framework offers benefits such as formal representation, improved requirement management, enhanced stakeholder communication, and potentially improved software development quality. However, it has limitations in handling complex requirements and is dependent on input quality. This study contributes to software engineering by addressing the challenges of requirement representation and improving development processes.</div></div>","PeriodicalId":56010,"journal":{"name":"Egyptian Informatics Journal","volume":"34 ","pages":"Article 101003"},"PeriodicalIF":4.3,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148230978","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Conversational recommendation identification with internal knowledgeable prompt-tuning","authors":"Xin Zou ,&nbsp;Tongyu Wu ,&nbsp;Qinqin Han ,&nbsp;Guo Wei ,&nbsp;Yi Zhu","doi":"10.1016/j.eij.2026.101000","DOIUrl":"10.1016/j.eij.2026.101000","url":null,"abstract":"<div><div>Recommendation systems have evolved from static preference modeling to interactive paradigms, where conversational recommendation enable dynamic preference elicitation through multi-turn dialogue. Most existing works in conversational recommendation primarily focus on identifying what items to recommend during interactions, essentially framing the task as a form of static personalized recommendation. However, with the rapid development of Large Language Models (LLMs), user-service interactions increasingly involve casual, exploratory, or non-goal-oriented dialogue, which raises a critical and emerging challenge: determining when to provide recommendations during a conversation, a task known as conversational recommendation identification. Although there have already been some efforts on devoting prompt-tuning techniques to this task, most existing methods rely heavily on general-purpose external knowledge, which often fails to capture conversation-specific semantics and may suffer from domain mismatch, semantic ambiguity, or noise. To address these limitations, we propose a novel conversational recommendation identification method based on internal knowledgeable prompt-tuning, which enhances soft prompt construction by integrating a self-resource knowledge expansion mechanism that captures task-specific conversational features. Instead of depending on the implicit knowledge of pre-trained models or external resources, we retrieve contextual knowledge in a self-supervised manner to guide verbalizer construction. The resulting soft prompts are tailored to guide conversational recommendation identification, which effectively balance automatic template generation with improved recognition performance. Extensive experiments on both English and Chinese datasets demonstrate that our method consistently outperforms all baselines, including state-of-the-art LLMs, in terms of identification accuracy and robustness.</div></div>","PeriodicalId":56010,"journal":{"name":"Egyptian Informatics Journal","volume":"34 ","pages":"Article 101000"},"PeriodicalIF":4.3,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148230980","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Enhanced RFID tag detection in IoT environments using improved FCM–DFSA approach","authors":"Sathish Kumar P. ,&nbsp;Gopinath R. ,&nbsp;Vijay Sai R. ,&nbsp;Sakthivel S.","doi":"10.1016/j.eij.2026.100995","DOIUrl":"10.1016/j.eij.2026.100995","url":null,"abstract":"<div><div>The rapid growth of information technology has integrated the Internet of Things (IoT) into everyday life, with Radio Frequency Identification (RFID) serving an essential role in this evolution. RFID technology has been critical across multiple industries, particularly in optimizing airport baggage handling procedures, thereby enhancing efficiency and safety of the process. A significant challenge in RFID systems is tag collision, which occurs when numerous tags simultaneously respond to a reader, leading to signal interference and increasing the likelihood of undetected tags in the reader range. This necessitates the use of anti-collision algorithms that facilitate the sequential identification of tags, reduce data loss, and improve tracking precision. Detection of missing tags and anti-collision algorithms are crucial in RFID systems, which ensure precise tracking and inventory management by preventing data loss during consecutive tag responses. These methods optimize system efficiency by reducing collisions, thereby enhancing identification rates in high-density settings. Existing anti-collision techniques, such as tree-based and Aloha-based algorithms, demonstrate deficiencies in high-density settings, particularly for dynamic tag populations and mobile readers. These methods frequently encounter challenges regarding scalability and efficiency, resulting in increased latencies and operational costs. This framework presents a new anti-collision algorithm: the Improved FCM–DFSA-Based Anti-Collision Algorithm. The proposed method effectively clusters tags according to the signal properties by integrating enhanced Fuzzy C-Means clustering with the Dynamic Frame Slotted Aloha protocol (DFSA), thereby minimizing collision occurrences. It dynamically modifies the frame dimensions based on real-time assessments, enhancing the communication intervals for faster and more dependable tag readings. The enhanced method exhibits substantial advancements in throughput and energy efficiency, making it suitable for resource-limited IoT applications. The experimental findings demonstrate that the proposed method significantly reduces collisions, resulting in enhanced identification rates and a lower likelihood of tag misses. This work provides significant insights into the formulation of effective anti-collision solutions essential for advancing the realm of RFID applications within the IoT framework.</div></div>","PeriodicalId":56010,"journal":{"name":"Egyptian Informatics Journal","volume":"34 ","pages":"Article 100995"},"PeriodicalIF":4.3,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148230981","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Design of a semantic segmentation and intelligent processing system for monitoring signals based on a knowledge-enhanced large model","authors":"Meng Ren,&nbsp;Yunhui Zeng,&nbsp;Ruifeng Shi,&nbsp;Wenxuan Dai,&nbsp;Defa Cao","doi":"10.1016/j.eij.2026.100993","DOIUrl":"10.1016/j.eij.2026.100993","url":null,"abstract":"<div><div>Semantic segmentation, a fundamental task in computer vision, involves the pixel-level classification of images and is critical for real-time scene understanding and precise object localization in surveillance systems. However, surveillance signals often present substantial challenges to conventional segmentation methods due to the presence of textual noise, complex scenes, and stringent real-time requirements. To address these issues, this paper proposes a knowledge-enhanced large model-based system for semantic segmentation and intelligent processing of surveillance signals. The proposed system first employs the Soft Masked BERT model to perform deep parsing and error correction on short texts within surveillance signals, thereby alleviating the impact of text noise. Subsequently, a support vector machine (SVM) is utilized to achieve precise semantic classification of the parsed signal objects. Based on this, the semantic segmentation results are incorporated as constraints and combined with SIFT feature point extraction and Euclidean distance matching, which significantly improves the accuracy of feature point matching. Furthermore, by constructing a knowledge-enhanced large model and a semantic-guided fusion module (SGFM), the system achieves accurate semantic segmentation of surveillance signals. In addition, a distributed big data center based on Hadoop technology is established to support intelligent processing tasks. Experimental results demonstrate that the proposed system achieves over 90% accuracy in signal text error recognition, a feature point matching accuracy between 0.97 and 0.99, a mean intersection over union exceeding 40%, and a processing time of less than 5 s. It consistently outperforms several comparative methods across multiple key metrics, effectively validating its accuracy, robustness, and real-time performance in complex surveillance scenarios.</div></div>","PeriodicalId":56010,"journal":{"name":"Egyptian Informatics Journal","volume":"34 ","pages":"Article 100993"},"PeriodicalIF":4.3,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148184891","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Machine Learning Models for Emergency Department Layout Prediction Using Graph Metrics","authors":"Ola Sarhan ,&nbsp;Manal Abdel Wahed ,&nbsp;Muhammad Ali Rushdi","doi":"10.1016/j.eij.2026.100989","DOIUrl":"10.1016/j.eij.2026.100989","url":null,"abstract":"<div><div>Challenges in healthcare facilities, especially emergency departments (EDs), persistently arise from increasing patient volumes, pandemics, and complex operational factors. This study explores the use of graph-theoretic methods as powerful tools for optimizing hospital layouts. Initially, we introduced a multi-objective optimization framework informed by graphs for the design of ED layouts, utilizing NSGA-II and GDE3, with the objectives of minimizing patient flow costs and enhancing the spatial proximity of service areas. We propose and confirm the application of both local and global graph-theoretic metrics, including centrality metrics, clustering coefficients, and network efficiency, to assess and rank Pareto-optimal layouts. Simulation results on the layout of an ED in Dalian, China, show that the best-ranked layouts exhibit superior graph-theoretic values, with the NSGA-II and GDE3 solutions reducing patient flow cost by 18.32% and 11.42%, respectively, and improving service area closeness by 14.5% and 18.02%, respectively. Subsequently, we present a layout prediction method based on machine learning that employs multi-output regression models trained on graph-theoretic features extracted from a large set of optimization-based layout solutions. The proposed models, particularly decision trees and random forests, demonstrated impressive prediction accuracies of up to 98.18% and 88.06%, respectively, showcasing their effectiveness in efficiently producing optimal layouts. Collectively, these findings highlight the potential of graph-theoretic models in enhancing hospital design and operational decision-making.</div></div>","PeriodicalId":56010,"journal":{"name":"Egyptian Informatics Journal","volume":"34 ","pages":"Article 100989"},"PeriodicalIF":4.3,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148184383","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"PVT-MSFF: A Pyramid Vision Transformer with Multi-Scale Feature Fusion for polyp segmentation in endoscopic images","authors":"Jian Zhang ,&nbsp;Ze Ji ,&nbsp;Changdong Zhao ,&nbsp;Meng Huang ,&nbsp;Xufei Hu ,&nbsp;Qilin Li ,&nbsp;Ming Li ,&nbsp;Heng Zhang","doi":"10.1016/j.eij.2026.101001","DOIUrl":"10.1016/j.eij.2026.101001","url":null,"abstract":"<div><div>Colorectal cancer (CRC) is one of the most fatal malignancies worldwide, and its early diagnosis relies on the accurate detection and segmentation of polyps in endoscopic images. However, existing methods are often challenged by the diverse morphology of polyps, ambiguous boundaries, and differences in data centers, which can lead to missed detections and limited generalization. Here, we propose a novel Pyramid Vision Transformer with Multi-Scale Feature Fusion network (PVT-MSFF), which combines a Pyramid Vision Transformer encoder with a cooperative multi-module strategy. Our method introduces a Feature Enhancement Module (FEM) with cross-attention mechanism, a Multi-Scale Fusion Module (MSFM) for hierarchical feature expression, and a Global Context Sensing (GCS) module to enhance boundary sensitivity and semantic integration. We evaluate PVT-MSFF on five public polyp segmentation benchmark datasets, including Kvasir-SEG, ClinicDB, ColonDB, ETIS, and CVC-300. Experimental results demonstrate that our method achieves highly competitive segmentation performance, with mDice scores of 0.921, 0.949, 0.813, 0.809, and 0.878 on the respective datasets. Although SAM2-UNet attains 0.928 mDice on Kvasir-SEG and ASPS reaches 0.950 mDice on CVC-ClinicDB, showing results closely comparable to ours, our model exhibits significant advantages in computational efficiency, with parameter count (25.16M) and computational cost (10.12 GFLOPs) substantially lower than these large-scale model-based approaches. This excellent balance between high accuracy and efficiency makes PVT-MSFF particularly valuable for practical clinical applications. Moreover, validation on a clinical dataset (G-endoscope) further confirms robust generalization and accuracy, highlighting the potential of PVT-MSFF for intelligent endoscopy systems and computer-assisted diagnosis. Our code will be available at: <span><span>https://github.com/jize123457/PVT-MSFF</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":56010,"journal":{"name":"Egyptian Informatics Journal","volume":"34 ","pages":"Article 101001"},"PeriodicalIF":4.3,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148230982","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Data-driven artistic expression: transforming complex datasets into visual narratives with AI models","authors":"Xi Cao","doi":"10.1016/j.eij.2026.100967","DOIUrl":"10.1016/j.eij.2026.100967","url":null,"abstract":"<div><div>Artificial Intelligence (AI) has become a strong tool in the practice of “data-driven artistic expression,” therefore allowing the artists to use even complex data as a creative resource. It is an approach wherein information gets changed into visual forms, creating works that merge the sense of reality and imagination, changing the boundaries between art and science. This paper is a new state-of-the-art using a variant of the Stable Diffusion model, supplemented with Bootstrapping Language-Image Pre-training (BLIP)-generated captions and custom style consistency loss, in the generation of high-quality and style-specific artworks. Our results show that this improved Stable Diffusion (pre-trained) model produces significantly better results than baseline approaches, such as BigGAN and VQ-VAE-2, in terms of essential image quality, semantic alignment, and style integrity for five creative categories, including painting, iconography, engraving, drawings, and sculpture. The model produces pictures featuring artistic styles matching exactly the target ones and always corresponds to the input linguistic description. The key feature of the current research is the introduction of a style consistency meter that checks how much the generated image keeps a specific artistic style of each category and, therefore, creates a realistic creation: sculptures, classical paintings, and engravings. Quantitative measures, such as Fréchet Inception Distance (FID) scores, Inception Scores (IS), and style consistency scores, further testify to the model’s strength in producing high-quality, diverse images. For instance, the style consistency score-0.88 for engravings-shows the proper mastery of the stylistic features by each category, while a very low FID score of 70.44 and a high IS of 7.3 suggest that the produced images are quite similar to the original works. In summary, this paper proves that great potential is possessed by using the corrected Stable Diffusion (pre-trained) model for advancing current state-of-the-art style-specific generated art.</div></div>","PeriodicalId":56010,"journal":{"name":"Egyptian Informatics Journal","volume":"34 ","pages":"Article 100967"},"PeriodicalIF":4.3,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148184890","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"SWOT-TOE framework to alleviate quality assurance in machine learning software system: human-agentic AI approaches","authors":"Sarra Ayouni ,&nbsp;Rafiq Ahmad Khan ,&nbsp;Hathal Salamah Alwageed ,&nbsp;Ismail Keshta ,&nbsp;Alaa Omran Almagrabi ,&nbsp;Musaad Alzahrani","doi":"10.1016/j.eij.2026.100991","DOIUrl":"10.1016/j.eij.2026.100991","url":null,"abstract":"<div><h3>Background</h3><div>The increased use of Machine Learning (ML) systems has posed critical Quality Assurance (QA) issues in areas of security, privacy and performance. Despite advances, QA frameworks for ML remain disjointed. The work examines QA through the Technological, Organizational, and Environmental (TOE) model and proposes human-agentic AI actions to enhance assurance mechanisms. This paper aims to identify, compare and model QA problems in ML software systems and recommend a SWOT-TOE (Strengths, Weaknesses, Opportunities, and Threats) matrix to enhance human-agentic AI-based QA problems.</div></div><div><h3>Methodology</h3><div>The study uses a mixed-method design, which includes systematic literature review (SLR), a quantitative survey, and comparative data modelling. QA issues are coded using the TOE structure and the association tests are linear-by-linear tests to investigate the relationship between the literature and survey results. A SWOT-TOE matrix and mathematical modelling are used to assess key QA issues and to solve them.</div></div><div><h3>Results</h3><div>The analysis shows that most of the QA problems revolve around interpretability of models, integrity of data, organizational readiness and regulatory limits. The linear-by-linear association results suggest that there is a strong correlation of the patterns of QA that are identified by the literature and those documented in the survey. Comparative data modeling shows the differences in priorities of QA between the regions. The suggested SWOT-TOE framework combines human-agentic solutions (e.g., adaptive auditing and explainable AI) to enhance QA and security.</div></div><div><h3>Conclusion</h3><div>The combination of the TOE framework and human-agentic AI practices and quantitative models allows a systematic approach to solving complex QA problems in ML systems. The research leads to the creation of human-centered, adaptive QA strategies, which foster trust, transparency, and sustainability in AI-powered settings. The framework assists developers, QA engineers, and policymakers to increase security, reliability, and accountability in ML ecosystems.</div></div>","PeriodicalId":56010,"journal":{"name":"Egyptian Informatics Journal","volume":"34 ","pages":"Article 100991"},"PeriodicalIF":4.3,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148184384","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}