Egyptian Informatics Journal最新文献

{"title":"Analytical residual network architecture with semi-supervision for sonar-based ship classification in underwater defense systems","authors":"Ruiling Fu ,&nbsp;Chunlai Yu ,&nbsp;Liqin Yue ,&nbsp;Yangyang Zhang ,&nbsp;Guizhou Cao","doi":"10.1016/j.eij.2025.100768","DOIUrl":"10.1016/j.eij.2025.100768","url":null,"abstract":"<div><div>Sonar-based ship classification is vital for underwater defense systems, enabling effective surveillance, threat detection, and autonomous navigation. However, challenges such as high noise levels, low resolution, and complex acoustic scattering in sonar data necessitate the use of advanced algorithms. This study aims to develop a novel semi-supervised framework, Attention-ResNet, to enhance ship classification accuracy by integrating residual networks (ResNets) and attention mechanisms, thereby leveraging both labeled data (LD) and unlabeled data to address the scarcity of LD. The proposed Attention-ResNet framework combines ResNets with attention mechanisms to improve feature extraction and discriminative capability. It processes sonar signals as single-channel images, utilizing skip connections in ResNets to learn complex acoustic features and attention gates to focus on relevant signal regions. The framework is evaluated on two benchmark sonar datasets, DeepShip and ShipsEar, using semi-supervised learning with only 25% LD. Ablation studies assess the contributions of ResNet and attention components in both the image domain (ID) and audio domain (AD). The Attention-ResNet framework achieves a classification accuracy of 70.17% on the test dataset, a 10.59% improvement over the baseline. The alternative Attention-ResNet_2 architecture further improves accuracy to 71.92%, a 12.34% enhancement. Comprehensive ablation studies confirm the synergistic effect of ResNet and attention mechanisms in enhancing classification performance in both ID and AD. The Attention-ResNet framework demonstrates significant improvements in sonar-based ship classification, offering a robust solution for underwater surveillance and navigation systems. Its ability to leverage unlabeled data makes it particularly suitable for scenarios with limited LD. Future work will explore its application to diverse datasets and real-world implementations to enhance its practical utility further.</div></div>","PeriodicalId":56010,"journal":{"name":"Egyptian Informatics Journal","volume":"32 ","pages":"Article 100768"},"PeriodicalIF":4.3,"publicationDate":"2025-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145107956","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":"Efficient and fully outsourced privacy-preserving decision tree training and prediction based on homomorphic encryption","authors":"Nawal Almutairi","doi":"10.1016/j.eij.2025.100766","DOIUrl":"10.1016/j.eij.2025.100766","url":null,"abstract":"<div><div>Outsourcing machine learning models to cloud servers allows data owners to train and utilize models without investing in dedicated hardware. However, this approach raises significant concerns regarding the proprietary nature of the models and the data privacy, including the confidentiality of training data, intermediate computations, input queries, and prediction results. In this paper, we propose Secure Decision Tree (SDT), a secure and efficient framework for outsourcing decision tree training and inference. The proposed solution leverages homomorphic encryption and introduces a novel structure called the encrypted decimal matrix to enable computations on encrypted data without disclosing sensitive information. Unlike existing solutions, SDT ensures data privacy without involving the data owner during training or inference, avoids reliance on secure multi-party computation, and prevents exposure of secret keys to external parties. Furthermore, SDT protects the proprietary rights of trained models and conceals statistical properties of the data and model from the cloud. Experimental evaluations on benchmark datasets from the UCI data repository demonstrate that SDT achieves classification accuracy comparable to standard (unencrypted) approach while maintaining strong privacy guarantees and incurring minimal computational overhead.</div></div>","PeriodicalId":56010,"journal":{"name":"Egyptian Informatics Journal","volume":"32 ","pages":"Article 100766"},"PeriodicalIF":4.3,"publicationDate":"2025-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145107957","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":"Deep learning for sustainable agriculture: automating rice and paddy ripeness classification for enhanced food security","authors":"Entesar Hamed I. Eliwa ,&nbsp;Tarek Abd El-Hafeez","doi":"10.1016/j.eij.2025.100785","DOIUrl":"10.1016/j.eij.2025.100785","url":null,"abstract":"<div><div>Accurate and timely classification of rice paddy ripeness is critical for optimizing harvest decisions, improving grain quality, and strengthening global food security. Traditional manual assessments remain subjective, labor-intensive, and poorly scalable, underscoring the need for automated solutions. This study presents a rigorous comparative evaluation of five fine-tuned deep learning architectures for real-time rice maturity assessment: YOLOv11 enhanced with an Attention-Guided Multi-Scale Feature Fusion (AGMS-FF) module, baseline YOLOv11, ResNet18, EfficientNet-B0, and MobileNetV3. Two publicly available datasets were utilized: one augmented to simulate diverse field conditions and another comprising raw, uncontrolled imagery to assess real-world generalizability. To ensure robustness and mitigate overfitting, we employed 5-fold cross-validation alongside a held-out test evaluation. Models were assessed across Accuracy, Precision, Recall, F1-score, ROC-AUC, and PR-AUC metrics. The AGMS-FF YOLOv11 achieved superior performance, with up to 99.6 % cross-validation accuracy (±0.21), ROC-AUC = 0.9877 and PR-AUC = 0.9526 on the augmented dataset, and 98.0 % test accuracy with perfect ROC-AUC and PR-AUC (1.000) on the raw dataset. Statistical validation confirmed the significance of these results through ANOVA (Dataset 1: F(4,20) = 158.4, p &lt; 0.001; Dataset 2: F(4,20) = 92.7, p &lt; 0.001) and McNemar’s paired tests (p &lt; 0.05). These findings provide robust comparative benchmarks across lightweight and state-of-the-art models, reinforcing the viability of deep learning-based computer vision systems for sustainable rice farming and their potential for scalable field deployment.</div></div>","PeriodicalId":56010,"journal":{"name":"Egyptian Informatics Journal","volume":"32 ","pages":"Article 100785"},"PeriodicalIF":4.3,"publicationDate":"2025-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145107955","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":"Proposed machine learning technique based on RIME algorithm for gas prediction: A case study of the Messinian Abu Madi Reservoir, Nile Delta Basin, Egypt","authors":"Mohammad Abdelfattah Sarhan ,&nbsp;Mohamed Abd Elaziz ,&nbsp;Ahmad O. Aseeri ,&nbsp;Ahmed T. Sahlol","doi":"10.1016/j.eij.2025.100772","DOIUrl":"10.1016/j.eij.2025.100772","url":null,"abstract":"<div><div>Accurate prediction of hydrocarbon presence in subsurface formations remains an open problem in petroleum exploration, particularly in complicated geology and petrophysical datasets with imbalance. Conventional machine learning algorithms such as the Random Vector Functional Link (RVFL) network have shown promise but are prone to performance sensitivity due to human-based parameter adjustment and the inability to effectively address class imbalance. This study avoids these limitations by proposing an optimization approach based on swarm intelligence that integrates the RIME algorithm and RVFL for better predictability. This study introduces a novel approach utilizing swarm optimization techniques for determining the presence of oil in wells. The method is based on the principles of Swarm Intelligence (SI), a well-known machine learning methodology inspired by the collective behavior of decentralized, self-organized systems. This research particularly harnesses SI for analyzing geological data for the prediction of whether a well contains oil or not. The core of the swarm-based approach lies in its ability to efficiently process vast and complex datasets to identify patterns indicative of oil presence. This is achieved by estimating and predicting the key petrophysical parameters for hydrocarbon reservoirs (e.g., water saturation, total porosity, &amp; shale volume). This swarm-optimized approach benefits from the space-searching capability of the swarm algorithms, leading to more accurate and speedy predictions. Random Vector Functional Link (RVFL) algorithm is used to optimize the selection of relevant geological features and parameters, enhancing the model’s predictive accuracy. RVFL processes well log data to predict gas-bearing intervals, while RIME automates parameter selection (e.g., hidden nodes, activation function), achieving up to 99.1% accuracy on imbalanced datasets. Applied to well log data from the Abu Madi Formation, the hybrid model optimizes key petrophysical parameters (e.g., water saturation, porosity, shale volume), offering superior accuracy, sensitivity, and computational efficiency compared to existing methods like AHA and GWO. This approach represents a significant advancement for hydrocarbon exploration workflows, enabling scalable gas prediction in complex geological settings.</div></div>","PeriodicalId":56010,"journal":{"name":"Egyptian Informatics Journal","volume":"31 ","pages":"Article 100772"},"PeriodicalIF":4.3,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145048928","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":"Optimizing AI-generated image metadata with hybrid color analysis and semantic keyword structuring","authors":"Akara Thammastitkul","doi":"10.1016/j.eij.2025.100775","DOIUrl":"10.1016/j.eij.2025.100775","url":null,"abstract":"<div><div>Effective metadata optimization is crucial for improving the retrieval and classification of AI-generated images, with color playing a significant role in visual perception and searchability. This study proposes a hybrid metadata optimization framework integrating color-based feature extraction (K-Means clustering and Saliency Detection) with semantic keyword structuring to enhance metadata accuracy and keyword relevance. By combining global color distributions, subject-focused visual attributes, and AI-driven contextual analysis, the proposed method ensures structured and comprehensive image content representation. The methodology comprises three primary stages: (1) Hybrid Color Extraction, (2) AI-based Keyword Generation, and (3) Structured Keyword Optimization. The hybrid extraction process initially employs K-Means clustering to identify globally dominant colors, followed by Saliency Detection to highlight subject-specific hues. Extracted colors are then mapped to descriptive keywords, complemented by context-based keywords generated through an AI captioning model. The final keyword optimization phase systematically categorizes these terms into subject-based, color-based, and descriptive-emotional keywords. The effectiveness of the proposed approach is quantitatively evaluated using several performance metrics, including precision, recall, F1-score, false positive rate, top-10 retrieval accuracy, cosine similarity, Jaccard similarity, and coverage score. Experimental results demonstrate that the proposed framework achieves a precision of 92.10%, significantly enhancing retrieval accuracy and keyword structuring compared to conventional approaches and outperforming state-of-the-art baseline methods, including the Google Cloud Vision API. This research provides a scalable and efficient metadata enrichment solution applicable to digital libraries, image search engines, and content management systems, ensuring accurate, structured, and contextually relevant metadata for effective image retrieval.</div></div>","PeriodicalId":56010,"journal":{"name":"Egyptian Informatics Journal","volume":"31 ","pages":"Article 100775"},"PeriodicalIF":4.3,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144932241","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":"AI-optimized breast cancer prognostics: Robust prediction with transformer-based lesion localization and hard voting classifier","authors":"Ayesha Jabbar ,&nbsp;Huang Jianjun ,&nbsp;Muhammad Kashif Jabbar ,&nbsp;Tariq Mahmood","doi":"10.1016/j.eij.2025.100774","DOIUrl":"10.1016/j.eij.2025.100774","url":null,"abstract":"<div><div>Breast cancer remains a significant threat to global health, driving the demand for more effective and prompt detection methods. AI-optimized deep learning models are revolutionizing mammography screening, by substantially improving breast lesion recognition and diagnosis accuracy. This research introduces a groundbreaking approach that leverages advanced deep-learning architectures to enable early and precise breast cancer prognostics. The study proposes a novel combination of scaling techniques, depth-wise convolution, and max pooling layers to enhance feature extraction from mammographic images, facilitating the detailed prognosis of intricate lesion patterns in both benign and malignant cases. The method efficiently eliminates redundant features, identifies the most important ones, and improves detection efficiency while reducing computational complexity compared to advanced models. To combat overfitting and integrate outputs from multiple models, a hard voting classifier is employed, ensuring fine-grained lesion detection and addressing the challenges of limited training data in medical imaging. The robust voting process leverages diverse augmentation techniques across large mammography datasets to provide comprehensive outcomes. Additionally, the Swin Transformer’s performance is evaluated against nonparametric statistical tests, validating its suitability for mammography image classification. The proposed model was evaluated using three public datasets, accurately detecting breast lesions with a sensitivity score of 99.31%. The approach achieved an impressive accuracy of 98.5%, with a standard deviation of 0.085 using 10-fold cross-validation, and an optimal AUC of 0.98. These results underscore the model’s effectiveness and robustness, particularly in data-constrained scenarios, making it a cost-effective solution for early breast cancer detection. Our findings highlight the transformative potential of AI-driven solutions in advancing breast cancer diagnostics and emphasize their importance in medical imaging applications.</div></div>","PeriodicalId":56010,"journal":{"name":"Egyptian Informatics Journal","volume":"31 ","pages":"Article 100774"},"PeriodicalIF":4.3,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145104674","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":"Optimal bidding strategy for virtual power plants in day-ahead markets: A quantile-based approach","authors":"Chusheng Wang ,&nbsp;Lu Zhang ,&nbsp;Xiaoli Zhu","doi":"10.1016/j.eij.2025.100771","DOIUrl":"10.1016/j.eij.2025.100771","url":null,"abstract":"<div><div>This study addressed the critical challenge of optimizing bidding strategies for virtual power plants (VPPs) with high renewable energy integration in the day-ahead market (DAM), a setting where balancing energy supply and demand is complicated by the variable output of renewable sources. The proposed framework was designed to minimize the financial impacts of uncertainties inherent in renewable energy sources like wind and solar power, which are increasingly prevalent in VPPs. To achieve this, a robust optimization approach was develop that models uncertainties in power output and incorporates economic penalties for deviations. Key elements included diverse energy sources within VPP—such as electric vehicles (EVs), energy storage, gas turbines (GT), photovoltaic (PV) systems, and hydropower stations—which were carefully managed to maintain reserve capacities for balancing fluctuations. The study utilized a mixed-integer nonlinear programming model combined with quantile and super-quantile theory to allocate reserve capacity more effectively, distinguishing the current work from previous models that lacked this level of adaptability and economic consideration. Results indicate that this approach not only enhances profit margins for VPPs but also improves operational stability. The findings highlighted the strategic advantage of using a multi-source, uncertainty-aware bidding strategy, offering a novel contribution to the field by advancing beyond conventional reserve and penalty models. This work demonstrated that a diversified VPP with an optimized bidding strategy could successfully navigate the complexities of renewable integration, presenting a significant advancement over existing methods in the literature.</div></div>","PeriodicalId":56010,"journal":{"name":"Egyptian Informatics Journal","volume":"31 ","pages":"Article 100771"},"PeriodicalIF":4.3,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145104778","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":"Task scheduling in fog computing systems using deep learning","authors":"ZhongYI Huang","doi":"10.1016/j.eij.2025.100757","DOIUrl":"10.1016/j.eij.2025.100757","url":null,"abstract":"<div><div>Optimal resource allocation is one of the fundamental challenges in fog computing systems. In this paper, a novel deep learning method is proposed for efficient task allocation and scheduling in fog computing systems. The proposed method consists of a three-phase structure. In the first phase, a stable communication structure between network components is established using a minimum spanning tree structure based on the distance between nodes. In the second phase, a deep neural network is used to determine the appropriate computational resources for each task, in which task characteristics and processing resources are analysed as inputs and the priority of assigning the task to each resource is determined. And finally, in the third phase, after assigning each task to resources, the order and processing time of the tasks are determined separately using an improved version of the round-robin algorithm, and this is done based on the dependencies between tasks. To check our method, we performed experiments by changing the number of running tasks and by altering the average time needed to complete each task. The method is measured against well-known algorithms such as enhanced round-robin, particle swarm optimization and deep reinforcement learning for multi-objective scheduling. The experiments conducted and the values obtained in terms of response time, turnaround time and waiting time show that the proposed method has achieved 9.96 %, 7.80 % and 8.69 % improvements in the first scenario, respectively. Moreover, in the second scenario, these successes have increased to 20.25 %, 8.94 %, and 7.33 %, respectively. These results represent the high efficiency of the proposed method for the optimization of different times and performance improvement of a system under various conditions.</div></div>","PeriodicalId":56010,"journal":{"name":"Egyptian Informatics Journal","volume":"31 ","pages":"Article 100757"},"PeriodicalIF":4.3,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144925006","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":"Edge computing optimization: an enhanced algorithm for efficient caching and latency reduction","authors":"Abdulmohsen Almalawi ,&nbsp;Shabbir Hassan ,&nbsp;Adil Fahad ,&nbsp;Asif Irshad Khan","doi":"10.1016/j.eij.2025.100781","DOIUrl":"10.1016/j.eij.2025.100781","url":null,"abstract":"<div><div>Digital transformation in the healthcare sector has witnessed a tremendous change in the last few years, which has allowed health care professionals to access and remotely monitor patient status using connected devices. Although digital healthcare is more convenient to patients, saves time and is more cost-effective, it also creates a problem of latency as the processing and storage of data is done on centralized cloud servers. Edge Computing (EC) presents an exciting opportunity as it brings data processing too near the source, and is challenged by limited storage capacity and complex infrastructure. To solve these problems, simulation research is proposed in this paper, called Dove Swarm Optimization-based Edge Caching (DSOA-EC), which combines the edge caching mechanism and swarm intelligence to reduce the latency cost and enhance the Quality of Service (QoS). The DSOA-EC is unique by having an intelligent caching strategy that can dynamically pick the best data point according to set caching criteria and current network conditions. The architecture consists of three layers: device, edge and cloud, each optimized to support data processing and transmission efficiency within the constraints of operational environment. Simulation results demonstrate that the DSOA-EC model significantly outperforms conventional caching protocols, achieving a 92% cache hit rate, 0.22-second sensing delay, 99% data freshness, 0.0021-second data retrieval latency, and energy efficiency of 155 J. The performance demonstrates that the DSOA-EC successfully reduces the latency of buffers and improves the QoS. Here its potential as a scalable, real time edge computing solution to a health care environment is demonstrated. These findings provide strong proof-of-concept evidence, and establish a strong footing in large multi-center trials and real-world application.</div></div>","PeriodicalId":56010,"journal":{"name":"Egyptian Informatics Journal","volume":"31 ","pages":"Article 100781"},"PeriodicalIF":4.3,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144996244","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":"Corrigendum to “Intrusion detection system framework for cyber-physical systems” [Egypt. Inform. J. 30 (2025) 100600]","authors":"Shafiqur Rehman ,&nbsp;Hisham Alhulayyil ,&nbsp;Taher Alzahrani ,&nbsp;Hatoon AlSagri ,&nbsp;Muhammad U. Khalid ,&nbsp;Volker Gruhn","doi":"10.1016/j.eij.2025.100780","DOIUrl":"10.1016/j.eij.2025.100780","url":null,"abstract":"","PeriodicalId":56010,"journal":{"name":"Egyptian Informatics Journal","volume":"31 ","pages":"Article 100780"},"PeriodicalIF":4.3,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145121123","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}