Egyptian Informatics Journal最新文献

{"title":"Impact of yoga asanas on primary dysmenorrhea-EEG band power analysis and deep learning based classification","authors":"Rathi G., Anuradha R., Pramila M.","doi":"10.1016/j.eij.2025.100741","DOIUrl":"10.1016/j.eij.2025.100741","url":null,"abstract":"<div><h3>Background and objective</h3><div>Women of all ages, starting from puberty, often encounter challenges related to premenstrual syndrome (PMS) and menstrual symptoms. These challenges can include abdominal pain and psychological effects such as stress and anxiety, which can significantly impact brain function. However, yoga has emerged as a promising method to alleviate these menstrual-related issues.</div></div><div><h3>Aim</h3><div>To study the impact of specific yoga asanas on primary dysmenorrhea in engineering college girl students with Electroencephalogram (EEG) signals.</div></div><div><h3>Method</h3><div>This interventional study was conducted from July 2023 to December 2023 with a group of 34 young female engineering college students aged 18 to 25, lasting for six months. Participants were selected for the control and intervention groups after getting informed consent. The intervention group underwent a supervised 24-week yoga program, focusing on five specific asanas designed to alleviate menstrual symptoms. This program was conducted five days a week, with each session lasting 40 min.EEG recordings were carried out during the 1st week, 12th week, and 24th week of the program using an 16-channel OpenBCI system for both groups. Power spectral density (PSD) analysis was performed for different frequency bands across various time bins in different brain lobes, and the classification of the signals was conducted using deep learning techniques. Participants’ subjective responses to the asana practice were also collected, and suitable statistical tests were performed as needed. The control group did not participate in any yoga practice.</div></div><div><h3>Results</h3><div>Practicing yoga asanas in the sequence of Nadi Shudhana, followed by Marjaryasana, Ustrasana, Paschimottanasana, Virasana, and Savasana over six months has led to significant changes. The yoga group experienced decreased pain severity compared to the control group. The Age and EEG power levels between both groups (N = 34) were statistically comparable. Power Spectral Density (PSD) analysis indicates an increase in alpha brainwave activity after six months of practicing yoga asanas. Bidirectional Long Short-Term Memory (BI-LSTM) a deep learning model, demonstrated an impressive ability to accurately classify the signals as pain, normal, or yoga, achieving a high accuracy rate of 93.5 %, which surpassed previous studies. Additionally, 91 % of the participants reported a reduction in menstrual abdominal pain as well as associated psychological symptoms like anxiety and stress through the survey conducted after the intervention study.</div></div><div><h3>Conclusion</h3><div>This study’s findings indicate that yoga asanas can effectively reduce menstrual pain and enhance cognitive functions, as demonstrated through EEG PSD analysis and participant feedback. This suggests that yoga may serve as a viable alternative treatment for primary dysmenorrhea in young women.</div><","PeriodicalId":56010,"journal":{"name":"Egyptian Informatics Journal","volume":"31 ","pages":"Article 100741"},"PeriodicalIF":5.0,"publicationDate":"2025-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144632796","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":"Eeg-based detection of epileptic seizures in patients with disabilities using a novel attention-driven deep learning framework with SHAP interpretability","authors":"Tawfeeq Shawly ,&nbsp;Ahmed A. Alsheikhy","doi":"10.1016/j.eij.2025.100734","DOIUrl":"10.1016/j.eij.2025.100734","url":null,"abstract":"<div><div>Epileptic seizures are neurological events caused by abnormal electrical activity in the brain, frequently resulting in loss of consciousness, involuntary movements, or cognitive deficits. Electroencephalograms (EEGs) are essential for diagnosing epilepsy, but conventional detection techniques depend on manual analysis, which can be labor-intensive and susceptible to inaccuracies. Recent developments in artificial intelligence (AI) and deep learning have facilitated the automation of seizure detection from EEG signals with improved accuracy. Nevertheless, current models frequently face challenges related to feature selection, interpretability, and computational demands. In this research, we introduce a cutting-edge deep learning methodology for the automated prediction of epilepsy, incorporating a Novel Attention Module (NAM) into a new Convolutional Neural Network (CNN) to improve the extraction of features from EEG signals. The proposed system employs Fourier Transform for feature extraction, utilizes Principal Component Analysis (PCA) for reducing dimensionality, and applies an optimized stochastic gradient descent approach with the Adam optimizer to enhance the learning process. We articulate the mathematical characteristics of feature selection driven by NAM, delineate the convergence attributes of the loss function, and present measures of explainability through Shapley Additive Explanations (SHAP). The model underwent training, validation, and testing with three publicly accessible EEG datasets sourced from PhysioNet and ResearchGate, thereby ensuring strong generalization across various datasets. A series of experiments were carried out to assess the effectiveness of the model by utilizing key performance metrics such as accuracy, sensitivity, specificity, and F1-score. The proposed methodology attained an accuracy of 99.3 %, an F1-score of 99.5 %, and both sensitivity and specificity at 99 %, showcasing its superior performance compared to existing models. Additionally, the computational complexity of the proposed framework was evaluated in terms of floating-point operations per second (FLOPs) and the total number of parameters, ensuring its efficiency for real-time biomedical applications. The incorporation of explainability techniques, including Shapley Additive Explanations (SHAP), enhances model transparency, which is beneficial for clinical decision-making. These findings suggest that the proposed attention-enhanced CNN framework serves as a reliable and interpretable tool for the early detection of epilepsy and patient monitoring.</div></div>","PeriodicalId":56010,"journal":{"name":"Egyptian Informatics Journal","volume":"31 ","pages":"Article 100734"},"PeriodicalIF":5.0,"publicationDate":"2025-07-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144623833","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":"5G network mobility analysis for user equipment","authors":"Umar Danjuma Maiwada ,&nbsp;Kamaluddeen Usman Danyaro ,&nbsp;Aliza Bt Sarlan ,&nbsp;Ayman Meidan ,&nbsp;Aftab Alam Janisar","doi":"10.1016/j.eij.2025.100744","DOIUrl":"10.1016/j.eij.2025.100744","url":null,"abstract":"<div><div>The rapid proliferation of 5G networks necessitates advanced techniques for analyzing and managing user equipment (UE) mobility. Efficient mobility estimation is critical for optimizing network performance, enhancing user experience, and supporting seamless connectivity. This study focuses on 5G network mobility analysis for user equipment, aiming to develop robust methodologies for predicting and understanding UE movement patterns. Hence, leveraging network-based data, including signal strength, handover events, and location information, our approach provides a comprehensive framework for mobility estimation. One important aspect of 5G and the next networks is the coexistence of small and mega cells. Due to this heterogeneity and the greater portability of user devices, there may be a high handover frequency, which may result in an unreasonable call drop probability or an unsatisfactory user experience. The network can ensure smooth and seamless cell transitions by proactively adapting to the user through smart mobility management. In this research, we establish an algorithm that estimates the user’s mobility level with minimal computational overhead and without requiring any changes to the consumer device/equipment (UE) side, using sounded reference signal (SRS) evaluations that are readily accessible from the base location (eNodeB in 4G systems). We utilize a combination of statistical models, machine learning algorithms, and real-time network data to predict UE movement with high accuracy. Key metrics such as handover frequency, dwell time, and path prediction are analyzed to understand mobility patterns. The integration of these metrics into the network management system allows for proactive resource allocation and improved quality of service (QoS). The efficacy of the method is demonstrated with real-world information including mobility patterns. Our findings indicate that network-based mobility analysis can significantly enhance the performance of 5G networks. By accurately estimating UE mobility, network operators can optimize handovers, reduce latency, and ensure stable connections even at high speeds. Furthermore, this approach aids in the efficient management of network resources, reducing congestion and enhancing overall network efficiency. According to the results, it is possible to classify UE speed into three mobility groups with a success rate of 90 % for minimal mobility, 89 % for moderate mobility, while 98 % for extreme mobility.</div></div>","PeriodicalId":56010,"journal":{"name":"Egyptian Informatics Journal","volume":"31 ","pages":"Article 100744"},"PeriodicalIF":5.0,"publicationDate":"2025-07-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144623834","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":"Improving and simulating urban landscape image recognition using combination optimization and fuzzy K-means algorithm","authors":"Lihua Yang,&nbsp;Yuhui Zheng","doi":"10.1016/j.eij.2025.100736","DOIUrl":"10.1016/j.eij.2025.100736","url":null,"abstract":"<div><div>Modern image recognition systems are pivotal in enhancing urban landscapes to support sustainable development and improving urban planning performance in a dynamic environment. Previous research focused on street-view panoramas is emerging as a new information source for urban studies due to the rapid advancements in image processing technology. However, challenges such as accuracy, feature extraction, uncertainty management, and a lack of approach integration remain unresolved. The research introduces a novel method combining a Combination Optimization (CO) strategy with a Fuzzy K-Means (FKM) clustering algorithm to address the challenges and achieve superior urban data analysis performance. CO specifically integrates the genetic algorithm (GA) to efficiently search for the optimal subset of features that maximize the performance of a convolutional neural network (CNN) based on extracted features. The Particle Swarm Optimization (PSO) aims to efficiently find the optimal feature subset by simulating the social behavior of particles, where each particle represents a feature combination to explore and exploit the solution space. The FKM allows for the clustering of mixed-use urban zones with greater accuracy, identifying complex patterns, and relationships that earlier research methods often overlook. It has proven highly effective in detecting and classifying mixed-use urban zones, delivering greater accuracy in recognition tasks than traditional clustering algorithms.</div></div>","PeriodicalId":56010,"journal":{"name":"Egyptian Informatics Journal","volume":"31 ","pages":"Article 100736"},"PeriodicalIF":5.0,"publicationDate":"2025-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144606017","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":"Improving scalability, energy efficiency, and cost-effectiveness in Kubernetes clusters using a nonlinear regression-based predictive replica model and ORLE algorithm","authors":"Indrani Vasireddy,&nbsp;Rajeev Wankar,&nbsp;Raghavendra Rao Chillarige","doi":"10.1016/j.eij.2025.100732","DOIUrl":"10.1016/j.eij.2025.100732","url":null,"abstract":"<div><div>Container-based deployments have transformed how modern applications are packaged, deployed, and scaled. They bring increasing benefits in terms of development agility, testing, and collaboration. Kubernetes is a famous container orchestration engine that manages the life cycle of containerized applications by automatically scaling the containers and load balancing among them. In this paper, we present an application-level leader election method known as ORLE(Optimal Replica Leader Election). After conducting a detailed performance analysis of ORLE, we also developed a nonlinear regression Predictive Replica Model that predicts the throughput in real time, which helps in the early identification of conditions that require replicas’ scaling up or down. We integrated the proposed ORLE with this nonlinear regression Predictive Replica Model to improve the performance of Kubernetes clusters. Our model autoscales replicas concerning real-time traffic measurements to maximize resource utilization and system scalability. ORLE selects the most suitable replica as the leader to optimize the load distribution and reduce the overall latency of the request. Our experimental results show that our proposed solution outperforms the original leader election mechanism (Default RAFT) of Kubernetes and an existing state-of-the-art algorithm Balanced Leader Distribution (BLD) by up to 25% throughput improvement, 40% latency reduction, optimization of energy consumed, and cost efficiency per working replica under real-time conditions. The proposed model is more beneficial for stateful applications and microservices architectures since consistent performance and fast leader election are crucial in ensuring the Kubernetes cluster reliability and performance and are highly suitable for Kubernetes clusters deployed in a cloud computing environment, which demands high scalability, low latency, and efficient resource management.</div></div>","PeriodicalId":56010,"journal":{"name":"Egyptian Informatics Journal","volume":"31 ","pages":"Article 100732"},"PeriodicalIF":5.0,"publicationDate":"2025-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144587745","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":"An ANN-based approach for estimating load capacity and strain in FRP confined concrete columns","authors":"Li Shang ,&nbsp;Haytham F. Isleem ,&nbsp;Saad A. Yehia ,&nbsp;Rupesh Kumar Tipu ,&nbsp;Khalil El Hindi","doi":"10.1016/j.eij.2025.100738","DOIUrl":"10.1016/j.eij.2025.100738","url":null,"abstract":"<div><div>This study introduces an innovative hybrid predictive model utilizing artificial neural network (ANN) techniques to accurately forecast the load-carrying capacity (<em>P</em>_cc) and confined strain (ε_cc) of Polyvinyl Chloride – Carbon Fiber Reinforced Plastic (PVC-CFRP) confined concrete columns under axial compression. The use of PVC-CFRP in civil engineering improves durability, strength and stiffness of structural components, and accurate prediction of these properties is needed for design and safety evaluations. Incorporating Random Forest for feature selection and Neural Network trained with the Beetle Antenna Search (BAS) algorithm, the proposed model is more precise and reliable in predicting the system response. Empirical validation was done by training the model on a dataset of 268 data points and the model achieved a test R squared (<em>R</em>²) of 0.971 with lower prediction errors (Root Mean Square Error (RMSE) of 25.05684, Mean Absolute Error (MAE) of 13.18642, Mean Absolute Percentage Error (MAPE) of 0.0178) than existing models. The level of accuracy in the study is high, indicating the robustness of the model and the possibility of using it in its practical engineering context. In addition, the research presents the development of a user interface platform for the easy application of the predictive model, enabling its usability by professionals in the field. The main novelty of this work is the way it tries to bridge the gap between the advancements in machine learning techniques and practical applications in engineering by giving an example of a future innovation in structural engineering analytics. In addition, this model has better predictive accuracy, yet also improves interpretability and usability, which are crucial for improving current design and assessment practice in civil engineering.</div></div>","PeriodicalId":56010,"journal":{"name":"Egyptian Informatics Journal","volume":"31 ","pages":"Article 100738"},"PeriodicalIF":5.0,"publicationDate":"2025-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144587744","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 planning based on improved dimensionality reduction strategy","authors":"Jinyong Chen ,&nbsp;Hui Li ,&nbsp;Zhiming Wu ,&nbsp;Xuanyan Li ,&nbsp;Yutao Sun","doi":"10.1016/j.eij.2025.100733","DOIUrl":"10.1016/j.eij.2025.100733","url":null,"abstract":"<div><div>This paper addresses the complex and challenging problem of task planning by formulating it as a high-dimensional multi-objective optimization problem and establishing the mathematical model. To address the shortcomings of traditional algorithms, the paper proposes improved algorithms, including an average weighted fitting of redundant objectives and a target dimensionality reduction method based on an improved Aggregation tree, aimed at enhancing the efficiency and robustness of the algorithm. The approach incorporates a Pointer Network and a roulette strategy to generate high-quality initial populations, thereby accelerating algorithm convergence and optimization. Article’s results show that the improved algorithm performs excellently concerning hypervolume and spatial metrics. Its effectiveness is further validated in practical applications, particularly in improving task completion rates, prioritization, time efficiency, and bandwidth utilization.</div></div>","PeriodicalId":56010,"journal":{"name":"Egyptian Informatics Journal","volume":"31 ","pages":"Article 100733"},"PeriodicalIF":5.0,"publicationDate":"2025-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144581196","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 hybrid deep learning-based model for enhanced feature representation in image retrieval systems","authors":"ZhiYuan Shen ,&nbsp;HaoDe Shen ,&nbsp;Feng He","doi":"10.1016/j.eij.2025.100717","DOIUrl":"10.1016/j.eij.2025.100717","url":null,"abstract":"<div><div>The exponential growth of image data volume has made the necessity of accurate and efficient retrieval systems more and more evident; in this regard, extracting comprehensive and meaningful features and their optimal selection has become a vital issue in image processing and machine learning research. The present study, with the aim of improving the representation of features in image retrieval systems, presents a novel hybrid model based on deep learning. In the proposed method, first, a rich set of image features is created by combining contextual features (Local Binary Pattern (LBP) and Histogram of Oriented Gradients (HOG) on image fragments), basic features (statistical features and Gray Level Cooccurrence Matrix (GLCM)), and deep features (extracted through a convolutional neural network). Then, in order to reduce the dimensions and select the most expressive features, a new feature selection algorithm based on reinforcement learning using learning automata is applied. Finally, the Fuzzy C-Means (FCM) clustering model is used to build a retrieval model and recall related images based on the selected features. The originality of this research lies in providing an integrated model that, by making intelligent integration of various methods of feature extraction and a reinforcement learning-based feature selection algorithm, attempts to break the bottleneck of current models in terms of diversity of image feature description and precision of retrieval. Evaluation of the proposed method on two datasets, Corel-1000 and ALOI, showed that this method provides significant performance compared to other methods, achieving average Precisions of 0.9711 and 0.8906 in these datasets, respectively. This indicates the efficiency of the proposed approach in extracting and selecting relevant and effective features for accurate image retrieval.</div></div>","PeriodicalId":56010,"journal":{"name":"Egyptian Informatics Journal","volume":"31 ","pages":"Article 100717"},"PeriodicalIF":5.0,"publicationDate":"2025-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144572154","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":"Purifying Kopi Luwak beans with precise RL-based proximal policy optimization using visual transformer with FRD","authors":"Raveena Selvanarayanan ,&nbsp;Surendran Rajendran ,&nbsp;Mohammad Zakariah ,&nbsp;Abeer Alnuaim","doi":"10.1016/j.eij.2025.100737","DOIUrl":"10.1016/j.eij.2025.100737","url":null,"abstract":"<div><div>Among the world’s rarest and costliest coffee beans, luwak beans, after being extracted from the Asian palm civet, a small mammal native to Southeast Asia, and Traditionally beans are harvested, washed, and roasted. Previously cleaning process of luwak beans was a traditional and meticulous practice through hand wash which involves collection, sorting, and pre-washing with water to remove larger pieces of debris and clinging pulp. Cleaning hand-luwak beans with the traditional methods might cause inconsistent quality, potential hygiene concerns, time-consuming and labor intensive. Integrated cleaning units will delicately de-pulp, wash, and dry beans in the proposed method. Features may include color, size, shape, and texture, which are crucial indicators of bean quality. Machine learning algorithms and vision transformers built on picture data will assist the robot’s arms in removing pulp without damaging beans delicately. Controlling drying settings precisely ensures quality and prevents over-drying. The proposed system leverages a Visual Transformer, a powerful image recognition architecture, enhanced with Feature Recombination and Distillation (FRD) for improved accuracy and efficiency. Combining RL with Proximal Policy Optimization (PPO) and a Visual Transformer with Feature Recombination and Distillation (FRD) for visual input processing. Training the RL agent to identify and select high-quality cleaned Kopi Luwak beans based on visual features. They achieved a purification accuracy of 97.57.</div></div>","PeriodicalId":56010,"journal":{"name":"Egyptian Informatics Journal","volume":"31 ","pages":"Article 100737"},"PeriodicalIF":5.0,"publicationDate":"2025-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144569875","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":"An encryption method for LAN feedback sharing information based on robust multi-view subspace clustering","authors":"Shicong Han","doi":"10.1016/j.eij.2025.100715","DOIUrl":"10.1016/j.eij.2025.100715","url":null,"abstract":"<div><div>With the purpose of capturing the complex structures and laws in the information, obtaining comprehensive and consistent information clustering results, improving the personalization of the generated key, preventing the attacker from cracking the encrypted information by analyzing the fixed key patterns, and increasing the difficulty of cracking for the attacker. In this paper, we study the encryption method of LAN feedback sharing information based on robust multi-view subspace clustering to improve the security of information encryption. In LAN environment, the sending node and receiving node measure the channel characteristics by sending ordinary pilots to each other in LAN to get the measurement of complex channel coefficients when transmitting feedback sharing information. Through robust multi-view subspace clustering algorithm, the values of the sending nodes measuring themselves are clustered to capture the complex structures and laws in the measured values, and to obtain the clustering results with comprehensive consistency of the measured values. Generate the initial key according to the clustering result and improve the personalization of the initial key. The dynamic composite chaotic system is used to process the LAN feedback sharing information, generate chaotic sequences, design S-boxes to combine the initial key, generate the wheel key, encrypt the LAN feedback sharing information, and provide an extra level of security for encryption. The experimental results show that the clustering normalization mutual information of this method reaches 0.92, which is 18% higher than single view clustering. It can effectively cluster the measurement values of the sending nodes themselves, effectively encrypting the shared information in the local area network and improving the security of shared information. Under different attack types, the avalanche effect value is 0.989–0.999, which means that the encryption effect is better and can effectively increase the difficulty for attackers to crack.</div></div>","PeriodicalId":56010,"journal":{"name":"Egyptian Informatics Journal","volume":"31 ","pages":"Article 100715"},"PeriodicalIF":5.0,"publicationDate":"2025-07-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144549760","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}