Egyptian Informatics Journal最新文献

{"title":"Standardization of expected value in gap statistic using Gaussian distribution for optimal number of clusters selection in K-means","authors":"Iliyas Karim Khan ,&nbsp;Hanita Binti Daud ,&nbsp;Nooraini Binti Zainuddin ,&nbsp;Rajalingam Sokkalingam ,&nbsp;Noor Naheed ,&nbsp;Aftab Alam Janisar ,&nbsp;Agha Inayat ,&nbsp;Md Shohel Rana","doi":"10.1016/j.eij.2025.100701","DOIUrl":"10.1016/j.eij.2025.100701","url":null,"abstract":"<div><div>K-means clustering is a widely used unsupervised learning technique for partitioning data into distinct groups. However, determining the Optimal Number of Clusters (ONC) remains a significant challenge due to the subjective nature of existing methods. The Gap Statistic is a common approach for ONC selection, yet it has limitations across various data scenarios. To address these challenges, this paper introduces the Enhanced Gap Statistic (EGS), which improves the traditional Gap Statistic by incorporating a Gaussian distribution to standardize reference data and integrating an adjustment factor to enhance ONC selection accuracy. In this study, we apply the Gaussian distribution to generate the reference dataset in the Gap Statistic due to its stability, efficiency, and robustness in handling outliers. While Gaussian assumptions work well in many cases, we acknowledge that they may not always be suitable, particularly for skewed, heavy-tailed, or multimodal data. In such scenarios, alternative approaches, such as t-distribution and kernel density estimation, may provide better adaptability. Furthermore, we recognize that the computational complexity of incorporating Gaussian standardization could impact scalability for large datasets, necessitating further optimizations. To evaluate EGS, we compare its performance against widely used clustering validation metrics, including the Davies-Bouldin index, Calinski-Harabasz index, Silhouette index, Elbow curve, and the conventional Gap Statistic. Experimental results demonstrate that EGS consistently outperforms traditional methods in both accuracy and computational efficiency. Specifically, EGS achieved efficiency values of 0.0500, 0.21, 0.12, 3.340 and 4.34 s and accuracy values of 89.35 %, 95.35 %, 80.35 %, 74.3 % and 97.3 for Time Series, Well Log, Hitter, the large-scale Traffic Crash dataset and the high dimensional Darwin Dataset, respectively. The findings shows that EGS as a highly effective and computationally efficient method for ONC selection, making it a valuable tool for complex and large-scale data environments.</div></div>","PeriodicalId":56010,"journal":{"name":"Egyptian Informatics Journal","volume":"30 ","pages":"Article 100701"},"PeriodicalIF":5.0,"publicationDate":"2025-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144169445","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 multiple sclerosis diagnosis by MRI image retrieval using convolutional autoencoders","authors":"R.M. Haggag ,&nbsp;Eman M. Ali ,&nbsp;M.E. Khalifa ,&nbsp;Mohamed Taha","doi":"10.1016/j.eij.2025.100698","DOIUrl":"10.1016/j.eij.2025.100698","url":null,"abstract":"<div><div>Multiple sclerosis (MS) is an autoimmune disorder characterized by damage to the central nervous system (CNS), leading to neuronal degeneration and affecting over 2.8 million individuals globally. Early and accurate diagnosis of MS is critical, given its significant social and economic consequences. Magnetic resonance imaging (MRI) remains the gold standard for MS diagnosis and monitoring. This study introduces a novel Content-Based Medical Image Retrieval (CBMIR) framework that leverages a newly designed Convolutional Autoencoder (CAE) model to improve the diagnostic evaluation of MS-related MRI scans. The proposed system extracts latent features from query and reference MRI images using the CAE. Extensive ablation studies involving nine distance metrics and diverse feature space dimensions identify 64 as the optimal latent feature size and validate the Mahalanobis distance as the superior similarity measure. Evaluated on four publicly available MS MRI datasets, the framework achieves Mean Average Precision (MAP) scores of 91.23%, 98.68%, 99.88%, and 99.69%, respectively, demonstrating enhanced diagnostic accuracy. The system also outperforms existing similar CBMIR frameworks for other diseases in MAP scores and generalizes effectively without requiring extensive preprocessing or segmentation. The primary contribution of this work is the development of a CAE-driven CBMIR system optimized for MS diagnosis, achieving state-of-the-art MAP performance while maintaining an average retrieval latency of 780 ms outperforming the compared systems.</div></div>","PeriodicalId":56010,"journal":{"name":"Egyptian Informatics Journal","volume":"30 ","pages":"Article 100698"},"PeriodicalIF":5.0,"publicationDate":"2025-05-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144124497","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":"Refining digital security with EfficientNetV2-B2 deepfake detection techniques","authors":"G.N. Vivekananda ,&nbsp;T.R. Mahesh ,&nbsp;Muskan Gupta ,&nbsp;Arastu Thakur ,&nbsp;Anu Sayal","doi":"10.1016/j.eij.2025.100699","DOIUrl":"10.1016/j.eij.2025.100699","url":null,"abstract":"<div><div>The rise in digitally altered images has made research on robust solutions for real image verification across sectors, including media and cybersecurity very essential. Deepfake technology’s development compromises digital media’s validity and calls for advanced detection to address. With EfficientNetV2-B2, a novel improvement in convolutional neural networks that is considered efficient and effective, the present research proposes a strong method for separating deepfake and real images. To ensure equal ratio, the paper utilized a balanced dataset consisting of 100,000 photos divided equally between real-world and deepfake classes. Methodology involved image preprocessing to the same dimensions, model strength augmentation techniques, and a rigorous training process with parameter optimization for precision. Interestingly, the study employed an independent learning rate adjustment method for enhancing training performance, resulting in better model calibration. Experiment setup results showed a staggering 99.885 % in classification accuracy and a corresponding high F1 score, thereby establishing the capability of the model in deepfake detection. Extensive exploration also confirmed there were evident cases of misclassification, which indicated areas where training model and image processing procedures should be improved. The results illustrate the prospect of applying EfficientNetV2-B2 in situations where high accuracy is needed in photo verification.</div></div>","PeriodicalId":56010,"journal":{"name":"Egyptian Informatics Journal","volume":"30 ","pages":"Article 100699"},"PeriodicalIF":5.0,"publicationDate":"2025-05-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144107880","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":"A novel approach for efficient resource allocation in 6G V2V networks using neighbor-aware greedy algorithm and sweep line model","authors":"Spandana Mande,&nbsp;Nandhakumar Ramachandran","doi":"10.1016/j.eij.2025.100693","DOIUrl":"10.1016/j.eij.2025.100693","url":null,"abstract":"<div><div>Advances in vehicular networks are attracting the attention of academic institutions and corporate groups who see them as a means of facilitating smart cities, autonomous driving, and the Intelligent Transportation System (ITS). This system can display highly dynamic features because of its portability and speed. The growing number of applications is placing pressure on 6G vehicle networks’ Quality of Service (QoS). A new era of customized user experiences, significantly increased road safety, and vehicle-to-vehicle (V2V) communication is quickly approaching with the introduction of connected autonomous vehicles. To achieve this ambitious goal, a greatly improved vehicle-to-everything (V2X) communication network is required, one that can facilitate massive data interchange rapidly, extremely reliably, and with low latency between vehicles and Road Side Units (RSUs). V2X is vulnerable to resource depletion because of its low processing capacity, which can result in harmful delays in communication between V2V, V2V and RSU, and RSU and ITS. This work analyses a sweep line algorithm that utilizes the concept of a sweep area to address issues in Euclidean space for enhanced V2V communication. In our research, we present an Enhanced Neighbor Node Associated Greedy-based Resource Distributed V2V Model with Sweep Line Model (NNAGbRD-V2V-SLM) for secure resource handling and management in V2V and V2X communication. The resource distribution strategy for V2V users participating in the exchange of information is based on the greedy method. The recommended algorithm determines which resource is optimal for each V2V user by taking a multi-level approach. The proposed model shows better resource management efficiency when compared to the current approach.</div></div>","PeriodicalId":56010,"journal":{"name":"Egyptian Informatics Journal","volume":"30 ","pages":"Article 100693"},"PeriodicalIF":5.0,"publicationDate":"2025-05-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144107879","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":"Federated learning-based semantic segmentation framework for sustainable development","authors":"Deepthi Godavarthi ,&nbsp;Deepa Jose ,&nbsp;Sachi Nandan Mohanty ,&nbsp;Mohamed Medani ,&nbsp;Mohamed Kallel ,&nbsp;Sherzod Abdullaev ,&nbsp;M. Ijaz Khan","doi":"10.1016/j.eij.2025.100702","DOIUrl":"10.1016/j.eij.2025.100702","url":null,"abstract":"<div><div>More than a third (38% to be exact) of all inhabited land is covered by forests, which serve many purposes including nutrient cycling, water, climate management, water purification, primary production, fuel wood, etc. They play a vital role in sequestering carbon and providing a home for a wide range of plant and animal life. Agriculture relies on the services provided by forests. Changes in land cover can be easily detected by using satellite imagery, which provides a wealth of useful information. Sustainable development and human well-being rely on effective forest utilization and management, which is the subject of this effort. Federated Learning protects user privacy by processing data locally on client devices rather than storing it centrally on a server. Instead of sending the same model to all clients at once, as is done in traditional training paradigms, we suggest a new paradigm called FedStv, in which the model trained on the active client in each round is used to train the next active client, as chosen by the server, in the following round. All of the clients use the derived server average once more for subsequent training. Finally, the uncertainty map estimate standard deviation for the projected segmentations has been calculated. The experimental results demonstrate that the suggested model can produce higher Dice Scores and Intersection over Union (IoU) values when applied to the dataset of Forest aerial pictures for segmentation.</div></div>","PeriodicalId":56010,"journal":{"name":"Egyptian Informatics Journal","volume":"30 ","pages":"Article 100702"},"PeriodicalIF":5.0,"publicationDate":"2025-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144107875","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":"A robust tuned EfficientNet-B2 using dynamic learning for predicting different grades of brain cancer","authors":"A. A. Abd El-Aziz ,&nbsp;Mohammed Elmogy ,&nbsp;Sameh Abd El-Ghany","doi":"10.1016/j.eij.2025.100694","DOIUrl":"10.1016/j.eij.2025.100694","url":null,"abstract":"<div><div>The brain is the central nervous system component, consisting of nerve cells called neurons. Neurons play a vital role in transmitting signals throughout the body. When cells within the brain undergo abnormal and uncontrolled growth, it can lead to the formation of brain tumors. Prompt detection and treatment of these tumors are crucial to prevent serious consequences, including death. The location and size of a brain tumor can impact a person’s facial and head symmetry. Accurately diagnosing brain tumors requires the expertise of doctors who can manually assess and categorize them using magnetic resonance imaging (MRI) scans. This precise diagnosis is crucial for planning effective treatment options and enhancing the patient’s quality of life. Deep learning (DL) has the potential to greatly assist in the diagnosis and treatment of brain cancers. We can ensure more accurate clinical diagnoses and improve treatment outcomes by utilizing DL techniques to analyze MRI images and classify brain tumors. In this paper, we propose a DL technique utilizing the EfficientNet-B2, which leverages the power of deep neural networks (DNN) for brain tumor detection. Our model incorporates the adaptive learning rate (ALR) technique, where the learning rate (LR) adjusts automatically at the beginning of each step based on the training accuracy and loss value from the previous step. Moreover, our proposed model utilizes the gradient-weighted class activation mapping (Grad-CAM) algorithm to identify specific areas impacted by ground glass opacities (GGO) that are linked to brain tumors. The proposed DL model aids in the early detection of brain tumors, allowing for timely intervention and improved patient outcomes, and it streamlines the diagnostic process, resulting in reduced time and cost for patients. We conducted tests using two public datasets, Br35H and brain tumor (BT), for binary and multiclass classification tasks, respectively. They were preprocessed using resizing and normalization techniques to ensure consistent input. Our proposed DL model was then compared with traditional classifiers. For the multiclass classification task, our proposed model achieved accuracy, specificity, precision, recall, and F1-score of 99.81 %, 99.87 %, 99.62 %, 99.62 %, and 99.62 %, respectively. Additionally, the model achieved a perfect accuracy score of 100 % for the binary classification task. The assessment of our proposed classifier revealed that the proposed DL model based on EfficientNet-B2, incorporating the ADL rate technique, shows promising potential in accurately and efficiently diagnosing brain tumors. Its high performance and ability to reduce diagnosis time and cost make it a valuable instrument for clinicians in the realm of neurology.</div></div>","PeriodicalId":56010,"journal":{"name":"Egyptian Informatics Journal","volume":"30 ","pages":"Article 100694"},"PeriodicalIF":5.0,"publicationDate":"2025-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144090265","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":"ADAMAEX—Alzheimer’s disease classification via attention-enhanced autoencoders and XAI","authors":"Doorgeshwaree Bootun ,&nbsp;Muhammad Muzzammil Auzine ,&nbsp;Noor Ayesha ,&nbsp;Salma Idris ,&nbsp;Tanzila Saba ,&nbsp;Maleika Heenaye-Mamode Khan","doi":"10.1016/j.eij.2025.100688","DOIUrl":"10.1016/j.eij.2025.100688","url":null,"abstract":"<div><div>To bring a new contribution in the area of classification of Alzheimer’s Disease (AD) we introduce a deep learning model, ADAMAEX, which is based on a convolutional autoencoder with four convolutions in the encoder part and a Squeeze and Excitation block for channel attention applied after each convolution. Additionally, we utilised fully connected layers (dense layers) for AD image classification. To conduct our study, we specifically chose axial brain scans acquired through sMRI in T2-weighted mode from the ADNI database, which were augmented using colour jitter, rotations, and flipping techniques. Before feeding the images to the model, we applied pre-processing steps such as re-sampling, normalisation, Contrast-Limited Adaptive Histogram Equalisation (CLAHE), and sharpening using the Unsharp Mask technique. For visualisation, we integrated Grad-CAM, an Explainable AI (XAI) technique, to highlight the brain regions responsible for the model’s classification decisions, a method underutilised by other authors in the context of AD classification. This model achieved an impressive accuracy of 96.2% and shows great promise for adoption in the medical sector, providing valuable assistance to doctors in validating their predictions based on brain scans.</div></div>","PeriodicalId":56010,"journal":{"name":"Egyptian Informatics Journal","volume":"30 ","pages":"Article 100688"},"PeriodicalIF":5.0,"publicationDate":"2025-05-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144084631","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":"Cloud based collaborative data compression technology for power Internet of Things","authors":"Qiong Wang ,&nbsp;Yongbo Zhou ,&nbsp;Jianyong Gao","doi":"10.1016/j.eij.2025.100696","DOIUrl":"10.1016/j.eij.2025.100696","url":null,"abstract":"<div><div>To address the challenge of explosive data growth in power IoT systems, this study develops a cloud-edge collaborative multi-task computing framework for efficient compression of heterogeneous data. The proposed system builds upon a “microservice-containerization-Kubernetes” architecture that enables parallel processing of multi-source IoT data collected through perception layer devices. At the edge layer, a hybrid performance ontology algorithm first integrates diverse data sources, followed by a two-stage compression approach: wavelet transforms perform initial data aggregation, while tensor Tucker decomposition enables secondary compression for optimized data reduction. Experimental results demonstrate the framework’s effectiveness in maintaining stable IoT network operations while achieving compression ratios below 40%, significantly improving upon traditional methods in both efficiency and reliability for power IoT applications.</div></div>","PeriodicalId":56010,"journal":{"name":"Egyptian Informatics Journal","volume":"30 ","pages":"Article 100696"},"PeriodicalIF":5.0,"publicationDate":"2025-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144070478","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":"A strong algorithm for randomly hiding a secret files inside true color image using large primary secret key","authors":"Aamer Tahseen Suhail,&nbsp;Harith Ghanim Ayoub,&nbsp;Ammar Abdulmajeed Gharbe","doi":"10.1016/j.eij.2025.100692","DOIUrl":"10.1016/j.eij.2025.100692","url":null,"abstract":"<div><div>Hiding in image files is one of the widespread techniques to achieve information security, as it has proven its efficiency.</div><div>Because of the hiding technology has become the best way to maintain the confidentiality of private information, the attackers have doubts about any translated media, such as various image files, because the possibility of containing important confidential data, then trying to use different methods and algorithms to extract its containing. Therefore, the traditional methods of regular and sequential hiding have become at a steady pace within the media, weak and easy to detect by the attackers, so the trend was to find a new algorithm that adopts the method of random hiding scattered within those media.</div><div>During the research, a method was developed to hide secret files inside true color images, by distributing the content of it within the image elements in a way that makes the distance between the locations of the image elements in irregular and not fixed space, based on an algorithm random distribution depend on a large prim secret key that agreed upon paging coefficient among the authorized persons, which makes it difficult to extract the hiding locations of those parts within them using image analysis methods, or through statistical analyzes that used in this field.</div><div>This method succeeded in hiding the secret files without causing a state of distortion to the original image, or the possibility of noticing the changes that occurred in it as a result of the hiding process, and these files were easily retrieved without losing any of their components, in addition to the fact that this extracting process takes place without require the original cover image or need to create a table of shows hiding locations.</div></div>","PeriodicalId":56010,"journal":{"name":"Egyptian Informatics Journal","volume":"30 ","pages":"Article 100692"},"PeriodicalIF":5.0,"publicationDate":"2025-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143936736","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 and optimization of human-machine interaction interface for the intelligent Internet of Things based on deep learning and spatial computing","authors":"Wencong Wang,&nbsp;Ke Wang,&nbsp;Hui Du","doi":"10.1016/j.eij.2025.100685","DOIUrl":"10.1016/j.eij.2025.100685","url":null,"abstract":"<div><div>The Intelligent Internet of Things (IoT) is transforming interactions with smart devices, especially in a home environment, with lighting, security, and entertainment systems. Designing user-friendly interfaces for IoT systems presents difficulties, particularly for individuals with severe disabilities such as Amyotrophic Lateral Sclerosis (ALS), spinal cord injuries, and cerebral palsy. Existing user interfaces frequently restrict the capacity of individuals, particularly those with severe disabilities, to operate smart home gadgets efficiently. The study proposes that the NeuroSpatialIOT system solve this problem by combining 2D spatial mapping, deep learning, and eye tracking. The system’s innovative approach accurately interprets user intent through natural eye gaze and provides relevant controls based on the user’s viewpoint and environment. NeuroSpatialIOT leverages deep learning to gather data on eye movements, the 2D spatial configuration of the room, and user objectives. NeuroSpatialIOT functions by tracking eye movements, comprehending the room’s 2D layout, and employing deep learning to predict user intentions. The system then displays appropriate controls in the user’s field of view, enabling intuitive interaction with IoT devices. Testing on non-disabled and severely disabled people yielded positive findings. Non-disabled participants scored 88.9% and disabled individuals 91.5%, indicating great system usability. Subsequently took 40% less time for non-impaired users to complete tasks and 60% less for disabled users. With NeuroSpatialIOT, altering room temperature or illumination takes 10–15 s instead of 30–45. The results show that the system can improve autonomy and quality of life for varied users in IoT-enabled settings by making home operations easier to handle.</div></div>","PeriodicalId":56010,"journal":{"name":"Egyptian Informatics Journal","volume":"30 ","pages":"Article 100685"},"PeriodicalIF":5.0,"publicationDate":"2025-05-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143928599","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}