Egyptian Informatics Journal最新文献

{"title":"Automatic identification method of foreign body intrusion in railway transportation track based on improved LeaderRank identification of key points","authors":"Linjie Niu","doi":"10.1016/j.eij.2025.100682","DOIUrl":"10.1016/j.eij.2025.100682","url":null,"abstract":"<div><div>To accurately identify foreign object intrusion behaviors in key areas of railway transport tracks, an automatic recognition method is proposed. This method is based on an improved LeaderRank algorithm and is designed to detect foreign object intrusions on railway tracks. First, the improved LeaderRank algorithm identifies key points of trajectories, which are then used as layout points for installing monitoring equipment. Real-time monitoring devices collect video images of key track areas. Next, an improved Gaussian mixture model is used for image segmentation in track monitoring, extracting potential foreground images containing foreign object intrusions. These images are then input into a hybrid deep learning-based automatic recognition model for foreign object intrusion. The firefly algorithm trains this model, constructing a structurally stable hybrid deep learning model that learns the relationship between image combination features and foreign object intrusion behaviors, enabling accurate recognition of foreign object intrusions. Experimental results demonstrate that this method accurately identifies foreign object intrusion, enhancing detection accuracy and reliability. The proposed method, combining the improved LeaderRank algorithm with hybrid deep learning, offers an efficient and accurate solution, providing a new technical approach for railway transport safety management.</div></div>","PeriodicalId":56010,"journal":{"name":"Egyptian Informatics Journal","volume":"30 ","pages":"Article 100682"},"PeriodicalIF":5.0,"publicationDate":"2025-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143838397","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":"Effectiveness of Teachable Machine, mobile net, and YOLO for object detection: A comparative study on practical applications","authors":"Sheikh Muhammad Saqib ,&nbsp;Muhammad Iqbal ,&nbsp;Tehseen Mazhar ,&nbsp;Tariq Shahzad ,&nbsp;Khmaies Ouahada ,&nbsp;Habib Hamam","doi":"10.1016/j.eij.2025.100680","DOIUrl":"10.1016/j.eij.2025.100680","url":null,"abstract":"<div><div>In this comparative study, the effectiveness of three prominent object detection models—Teachable Machine, MobileNet, and YOLO—was evaluated using a diverse dataset consisting of images from four distinct categories: bird, horse, laptop, and sandwich. The objective was to identify the most efficient model in terms of accuracy, speed, and usability for practical applications in fields such as self-driving vehicles, robotics, security systems, and augmented reality. The dataset was meticulously curated and subjected to training across the three models. Results from the comprehensive analysis indicated that the Teachable Machine model surpassed both MobileNet and YOLO in performance, demonstrating superior accuracy and effectiveness in detecting objects across the specified categories. This research contributes significantly to the domain of artificial intelligence by providing detailed insights and comparisons of model performances, offering a valuable resource for further advancements in object detection technologies. The study not only showcases the Teachable Machine’s superiority in handling multi-class object detection problems but also sets a benchmark for future explorations in enhancing object detection methodologies.</div></div>","PeriodicalId":56010,"journal":{"name":"Egyptian Informatics Journal","volume":"30 ","pages":"Article 100680"},"PeriodicalIF":5.0,"publicationDate":"2025-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143825671","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":"Temporal record linkage for heterogeneous big data records","authors":"Reham I. Abdel Monem,&nbsp;Ehab E. Hassanein,&nbsp;Ali Z. El Qutaany","doi":"10.1016/j.eij.2025.100642","DOIUrl":"10.1016/j.eij.2025.100642","url":null,"abstract":"<div><div>Temporal Record Linkage (TRL) or Temporal Entity Matching (TEM) is the process of identifying records/entities that refer to the same real-world object in different lifetime states. TRL is a well-known problem in different data engineering contexts e.g. data analysis, data warehousing, data mining, and/or machine learning to identify entities denoting the same real-world object over time. Unlike traditional record linkage which considers differences between records of the same entity as contradictions; temporal record linkage considers such differences as normal entity growth over time. Existing frameworks which are limited to, No model, Decay, Disprob, Mixed, and Agreement First Dynamic Second (AFDS) which deal with temporal record linkage achieve high accuracy but with high computation cost. They condition the presence of the time dimension to detect similar entities that refer to the same real-world object. In this research, we present a framework called Tracking Similar Entities in Heterogeneous Temporal Records (TSE-HTR) to track similar entities in heterogeneous, big, low-quality, and temporal data regardless of the presence of the time dimension. It introduces data cleansing and state ranking modules to detect anomalies within similar entities, find the final and accurate set of them, and explain anomalies to the users or domain experts in a comprehensible manner that not only offers increased business intelligence but also opens opportunities for improved solutions. It presents to the user the records of different states of the same real-world object ranked according to different quality measures like completeness, validity, and accuracy. Performance evaluation of the proposed framework against existing frameworks over real and big data shows a great improvement in both effectiveness and efficiency.</div></div>","PeriodicalId":56010,"journal":{"name":"Egyptian Informatics Journal","volume":"30 ","pages":"Article 100642"},"PeriodicalIF":5.0,"publicationDate":"2025-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143830022","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":"The application and performance optimization of multi-controller-based load balancing algorithm in computer networks","authors":"Fengfeng Guo ,&nbsp;Ailing Ye","doi":"10.1016/j.eij.2025.100678","DOIUrl":"10.1016/j.eij.2025.100678","url":null,"abstract":"<div><div>This paper addresses the critical issue of network congestion caused by the increase in network traffic in contemporary society. The computer networks serve as the foundation for information exchange and online services, and their efficiency is essential. Traditional load-balancing algorithms face challenges in handling dynamic workloads, leading to inefficient resource utilization and extended response time. To address this problem, a novel method called Genetic-Bird Swarm Optimization (GBSO) is introduced, focusing on multi-controller-based load balancing. This method involves problem modeling, analysis, and selection processes, including the selection of switches and target controllers within the network segment. The results showed that the throughput of the proposed GBSO method was about 3800, and the load index after load balancing was 0.6, indicating that the workload distribution was balanced. The accuracy of the proposed GBSO algorithm was 92.15 %, the precision was 89 %, the recall rate was 88 %, and the F1 score was 85 %, all of which were higher than the existing Naive Bayes algorithm. This study emphasizes the importance of load balancing in optimizing computer network performance. The new algorithm proposed in this article provides a reliable solution for uniform network traffic distribution, reducing the limitations of existing methods.</div></div>","PeriodicalId":56010,"journal":{"name":"Egyptian Informatics Journal","volume":"30 ","pages":"Article 100678"},"PeriodicalIF":5.0,"publicationDate":"2025-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143830021","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":"TFKAN: Transformer based on Kolmogorov–Arnold Networks for Intrusion Detection in IoT environment","authors":"Ibrahim A. Fares ,&nbsp;Mohamed Abd Elaziz ,&nbsp;Ahmad O. Aseeri ,&nbsp;Hamed Shawky Zied ,&nbsp;Ahmed G. Abdellatif","doi":"10.1016/j.eij.2025.100666","DOIUrl":"10.1016/j.eij.2025.100666","url":null,"abstract":"<div><div>This work proposes a novel Transformer based on the Kolmogorov–Arnold Network (TFKAN) model for Intrusion Detection Systems (IDS) in the IoT environment. The TFKAN Transformer is developed by implementing the Kolmogorov–Arnold Networks (KANs) layers instead of the Multi-Layer Perceptrons (MLP) layers. Unlike the MLPs feed-forward layer, KAN layers have no fixed weights but use learnable univariate function components, enabling a more compact representation. This means a KAN can achieve comparable performance with fewer trainable parameters than a larger MLP. The RT-IoT2022, IoT23, and CICIoT2023 datasets were used in the evaluation process. The proposed TFKAN Transformer outperforms and obtains higher accuracy scores of 99.96%, 98.43%, and 99.27% on the RT-IoT2022, IoT23, and CICIoT2023 datasets, respectively. The results indicate that the developed Transformer using KAN shows promising performance in IDS within IoT environments compared to MLP layers.Transformers based on KANs are on average 78% lighter, in parameter count, than Transformers using MLPs. This makes KANs promising to be a replacement for MLPs.</div></div>","PeriodicalId":56010,"journal":{"name":"Egyptian Informatics Journal","volume":"30 ","pages":"Article 100666"},"PeriodicalIF":5.0,"publicationDate":"2025-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143816963","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 control-driven transition strategy for enhanced multi-level threshold image segmentation optimization","authors":"Laith Abualigah ,&nbsp;Mohammad H. Almomani ,&nbsp;Saleh Ali Alomari ,&nbsp;Raed Abu Zitar ,&nbsp;Vaclav Snasel ,&nbsp;Kashif Saleem ,&nbsp;Aseel Smerat ,&nbsp;Absalom E. Ezugwu","doi":"10.1016/j.eij.2025.100646","DOIUrl":"10.1016/j.eij.2025.100646","url":null,"abstract":"<div><div>This work proposes an image segmentation approach based on a multi-threshold segmentation method and the enhanced Flood Algorithm combined with the Non-Monopolize search (named Improved IFLANO). The introduced approach, depending on IFLANO, offers much better segmentation quality for various images. Based on the existing structure, two different types of optimization techniques are added within IFLANO to enhance the update dynamics during optimization. The random strategy used in the Aquila optimization procedure enhances the performance of FLA, and a self-transition adaptation enhances the exploration ability of the image analysis. IFLANO framework is implemented for multi-level threshold image segmentation wherein the evaluation metric is Kapur’s entropy-based between-class variance. Benchmarking studies against standard test images show that IFLANO works not only faster but also yields better, more stable outcomes in image segmentations within similar time frames. IFLANO is shown to put any solution a step forward in its search for more accurate alternatives than any of the considered techniques by getting 96% improvement. We also find that the proposed method got better results in solving large medical clustering applications.</div></div>","PeriodicalId":56010,"journal":{"name":"Egyptian Informatics Journal","volume":"30 ","pages":"Article 100646"},"PeriodicalIF":5.0,"publicationDate":"2025-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143817029","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 and efficient algorithm for graph coloring problem based on Malatya centrality and sequent independent sets","authors":"Selman Yakut","doi":"10.1016/j.eij.2025.100676","DOIUrl":"10.1016/j.eij.2025.100676","url":null,"abstract":"<div><div>The Graph Coloring Problem (GCP) is an NP-hard problem that aims to color the vertices of a graph using the minimum number of distinct colors, ensuring that adjacent vertices do not share the same color. GCP is widely applied in real-world scenarios and graph theory problems. Despite numerous studies on solving GCP, existing methods face limitations, often performing well on specific graph types but failing to deliver efficient solutions across diverse structures. This study introduces the Malatya Sequent Independent Set Coloring Algorithm as an effective solution for GCP. The algorithm utilizes the Malatya Centrality Algorithm to compute Malatya Centrality (MC) values for graph vertices, where an MC value is defined as the sum of the ratios of a vertex’s degree to its neighbors’ degrees. The algorithm selects the vertex with the lowest MC value, adds it to an independent set, and removes it along with its neighbors and edges. This process repeats until the first sequent independent set is identified. The removed set is then excluded from the original graph, and the process continues on the remaining structure to determine additional sequent independent sets, ensuring that each set corresponds to a single color group in GCP. The algorithm was tested on social network graphs, random graphs, and benchmark datasets, supported by mathematical analyses and proofs. The results confirm that the algorithm provides efficient, polynomial-time solutions for GCP and maintains high performance across various graph types, independent of constraints.</div></div>","PeriodicalId":56010,"journal":{"name":"Egyptian Informatics Journal","volume":"30 ","pages":"Article 100676"},"PeriodicalIF":5.0,"publicationDate":"2025-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143816964","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":"Enhancing security in social computing systems through knowledge learning techniques","authors":"Anitha Rajesh ,&nbsp;Ramamurthy DineshKumar ,&nbsp;Saranya Shanmugam ,&nbsp;Jaehyuk Cho ,&nbsp;Sathishkumar Veerappampalayam Easwaramoorthy","doi":"10.1016/j.eij.2025.100675","DOIUrl":"10.1016/j.eij.2025.100675","url":null,"abstract":"<div><div>Social computing systems (SCS) integrate social behaviour with computational hardware to enable conversations among technologies and individuals. To protect the integrity of behavioural integration from illegal device communications, it is essential to ensure that security is maintained inside SCS. This study aims to provide a Coherent Authorization and Authentication Technique (CA2T) specifically designed to ensure the safety of SCS connections. CA2T uses various user credentials to approve interactions while guaranteeing that authentication is not replicated. Computed and behavioural data authentications are separated through knowledge-based learning to reduce the amount of security overheads. Credential verification that is adaptable and based on different calculation needs is the initial step in the device authorization process. After that, end-to-end authentication uses a lightweight signature based on two factors for verifying interactions between devices. The experimental findings show that when compared to the leading baseline approach, NTSC, CA2T reduces false positives by 9.48 %, computational overhead by 12.28 %, authentication time by 11.38 %, and failure rates by 11.48 %. With these improvements CA2T has emerged as much more effective than previous security frameworks for protecting SCS environments; it remains scalable, has minimal latency, and can adapt to new environments.</div></div>","PeriodicalId":56010,"journal":{"name":"Egyptian Informatics Journal","volume":"30 ","pages":"Article 100675"},"PeriodicalIF":5.0,"publicationDate":"2025-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143817030","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 deep learning-orchestrated garlic routing architecture for secure telesurgery operations in healthcare 4.0","authors":"Kavit Shah ,&nbsp;Nilesh Kumar Jadav ,&nbsp;Rajesh Gupta ,&nbsp;Sucheta Gupta ,&nbsp;Sudeep Tanwar ,&nbsp;Joel J.P.C. Rodrigues ,&nbsp;Fayez Alqahtani ,&nbsp;Amr Tolba","doi":"10.1016/j.eij.2025.100662","DOIUrl":"10.1016/j.eij.2025.100662","url":null,"abstract":"<div><div>Recently, the Internet of Things (IoT) has attracted different real-time services, predominantly in the healthcare domain. One such real-time IoT-based application is telesurgery, where surgeons remotely transmit surgery instructions to a robotic arm, enabling it to conduct surgical procedures on patients. Since these surgical instructions use conventional wireless networks, they can leveraged by the attackers to manipulate them and manoeuvre the entire telesurgery application. Therefore, in this paper, we used emerging technologies, such as Artificial Intelligence (AI), garlic routing (GR) networks, and blockchain, to propose an AI- and GR-based secure data instruction architecture for telesurgery applications in the healthcare 4.0 domain. A standard sensor dataset is utilized to train different AI algorithms, such as Long Short Term Memory (LSTM) and Gated Recurrent Neural Networks (GRU), for classifying malicious and non-malicious telesurgery data. Further, the non-malicious data is forwarded to the GR network that provides an end-to-end encrypted tunnel using ElGamal and Advanced Encryption Standard (AES). ElGamal encryption encrypts the session tags for each telesurgery data relayed between surgeons and the robotic arm. The tags are stored in the immutable blockchain nodes to avoid data tampering attacks that strengthen the legitimacy of the garlic routers. Among both, the GRU outperforms with test accuracy 96.89%, precision 97.32%, recall 96.46%, F1 score 96.86%, and training loss 3%. Furthermore, the telesurgery data is transmitted via an AES-based outbound tunnel and received via an AES-based inbound tunnel, offering robust security against the security threats associated with the telesurgery application. To improve the network performance, we used essential characteristics (ultra-low latency, high speed, and high reliability) of the 5G network interface between each layer of the proposed architecture. The proposed architecture is evaluated using different evaluation metrics, such as statistical analysis (training accuracy, training loss, optimizer performance, activation function performance), data compromisation rate (0.346), network throughput (1.44 Mbps), error rate, and latency comparison.</div></div>","PeriodicalId":56010,"journal":{"name":"Egyptian Informatics Journal","volume":"30 ","pages":"Article 100662"},"PeriodicalIF":5.0,"publicationDate":"2025-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143785258","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Advanced AI-driven intrusion detection for securing cloud-based industrial IoT","authors":"Saima Siraj Qureshi ,&nbsp;Jingsha He ,&nbsp;Siraj Uddin Qureshi ,&nbsp;Nafei Zhu ,&nbsp;Ahsan Wajahat ,&nbsp;Ahsan Nazir ,&nbsp;Faheem Ullah ,&nbsp;Abdul Wadud","doi":"10.1016/j.eij.2025.100644","DOIUrl":"10.1016/j.eij.2025.100644","url":null,"abstract":"<div><div>The rapid integration of smart devices with cloud services in the Industrial Internet of Things (IIoT) has exposed significant vulnerabilities in conventional security protocols, making them insufficient against sophisticated cyber threats. Despite advancements in intrusion detection systems (IDS), there remains a critical need for highly accurate, adaptive, and scalable solutions for cloud-based IIoT environments. Motivated by this necessity, we propose an advanced AI-powered IDS leveraging Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) networks. Developed using Python and the Kitsune dataset, our IDS demonstrates a remarkable detection accuracy of 98.68%, a low False Negative rate of 0.01%, and an impressive F1 score of 98.62%. Comparative analysis with other deep learning models validates the superior performance of our approach. This research contributes significantly to enhancing cybersecurity in cloud-based IIoT systems, offering a robust, scalable solution to mitigate evolving cyber threats.</div></div>","PeriodicalId":56010,"journal":{"name":"Egyptian Informatics Journal","volume":"30 ","pages":"Article 100644"},"PeriodicalIF":5.0,"publicationDate":"2025-04-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143768061","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}