Pub Date : 2025-12-24DOI: 10.1016/j.eij.2025.100878
Jeffin Gracewell , P. Ramya , S. Venkatesh Babu
The Enhanced Data Placement Policy (EDPP) offers a novel approach to optimising data storage in Hadoop-based Big Data systems that utilise the Hadoop Distributed File System (HDFS). Efficient data placement is essential for maximising data retrieval speed and overall system performance. EDPP leverages the combined power of MapReduce (MR) and Particle Swarm Optimisation (PSO) to address this challenge effectively. In these systems, files are divided into chunks, which can be either duplicates (pointing to existing data copies) or unique (requiring strategic placement). EDPP uses MR to identify the most suitable Data Nodes (DNs) for storing unique chunks, enhancing data retrieval efficiency. Furthermore, EDPP addresses the issue of maintaining balanced data distribution in heterogeneous clusters. By utilising PSO, it intelligently selects DNs based on their storage capacity and response times, ensuring optimal resource utilisation and load balancing. This research presents a practical and efficient solution to the complex problem of data placement in Big Data systems, offering significant benefits to organisations with diverse hardware and software configurations in their Hadoop clusters. Finally, experimental results demonstrate that the Enhanced Data Placement Policy (EDPP) significantly improves performance in Hadoop-based Big Data systems. The EDPP reduces data retrieval time by an average of 33 % compared to traditional methods and achieves a throughput of 35.03 MB/s with a 98 GB dataset, more than doubling the performance of the existing methods. Additionally, it ensures even data distribution, preventing node overload and optimising resource utilization.
{"title":"Catalyzing big data excellence: the enhanced Data Placement Policy (EDPP) revolution","authors":"Jeffin Gracewell , P. Ramya , S. Venkatesh Babu","doi":"10.1016/j.eij.2025.100878","DOIUrl":"10.1016/j.eij.2025.100878","url":null,"abstract":"<div><div>The Enhanced Data Placement Policy (EDPP) offers a novel approach to optimising data storage in Hadoop-based Big Data systems that utilise the Hadoop Distributed File System (HDFS). Efficient data placement is essential for maximising data retrieval speed and overall system performance. EDPP leverages the combined power of MapReduce (MR) and Particle Swarm Optimisation (PSO) to address this challenge effectively. In these systems, files are divided into chunks, which can be either duplicates (pointing to existing data copies) or unique (requiring strategic placement). EDPP uses MR to identify the most suitable Data Nodes (DNs) for storing unique chunks, enhancing data retrieval efficiency. Furthermore, EDPP addresses the issue of maintaining balanced data distribution in heterogeneous clusters. By utilising PSO, it intelligently selects DNs based on their storage capacity and response times, ensuring optimal resource utilisation and load balancing. This research presents a practical and efficient solution to the complex problem of data placement in Big Data systems, offering significant benefits to organisations with diverse hardware and software configurations in their Hadoop clusters. Finally, experimental results demonstrate that the Enhanced Data Placement Policy (EDPP) significantly improves performance in Hadoop-based Big Data systems. The EDPP reduces data retrieval time by an average of 33 % compared to traditional methods and achieves a throughput of 35.03 MB/s with a 98 GB dataset, more than doubling the performance of the existing methods. Additionally, it ensures even data distribution, preventing node overload and optimising resource utilization.</div></div>","PeriodicalId":56010,"journal":{"name":"Egyptian Informatics Journal","volume":"33 ","pages":"Article 100878"},"PeriodicalIF":4.3,"publicationDate":"2025-12-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145841261","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}
Recommendation systems have become crucial in recent years, particularly in the travel industry, helping travelers discover appealing destinations. Special interest travelers seeking unique experiences require tailored activity-based recommendations. However, relying solely on search engines tends to yield generic results, often leading to repetitive information streams. To address this, our paper proposes a framework for extracting tourism activities and linking them to tourism types and destinations. We employed grammar-based techniques and n-gram characteristics to effectively extract these activities. The concept of the T–A–P Triangle connects tourism type (T), tourism activity (A), and tourism place (P), providing a comprehensive understanding of these associations. The study assesses the effectiveness of the feature combination used by the Conditional Random Fields (CRF) model to improve the extraction process. Our experiments reveal that our framework successfully extracts tourism-related activities. In particular, the three features of the model — word characteristics, part of speech (PoS), and named entity recognition (NER) — outperformed the single baseline feature, which is only word characteristics, with improvements of 5.26% in precision, 14.68% in recall, and 10.13% in the F1-score.
近年来，推荐系统变得至关重要，尤其是在旅游业，它帮助旅行者发现有吸引力的目的地。特殊兴趣的旅行者寻求独特的体验需要量身定制的活动为基础的建议。然而，仅仅依靠搜索引擎往往会产生通用的结果，经常导致重复的信息流。为了解决这个问题，本文提出了一个提取旅游活动并将其与旅游类型和目的地联系起来的框架。我们使用基于语法的技术和n-gram特征来有效地提取这些活动。T - A - P三角的概念将旅游类型(T)、旅游活动(A)和旅游地点(P)联系起来，提供了对这些关联的全面理解。该研究评估了条件随机场（CRF）模型所使用的特征组合的有效性，以改进提取过程。实验表明，我们的框架成功地提取了与旅游相关的活动。特别是，模型的三个特征——词特征、词性特征（PoS）和命名实体识别（NER）——优于单一基线特征（只有词特征），准确率提高了5.26%，召回率提高了14.68%，f1得分提高了10.13%。
{"title":"Tailored experiences: Unraveling T–A–P dynamics in activity-driven tourism recommendations for special interest travelers","authors":"Nattapong Tongtep, Kritamook Binabdullah, Chanachai Siriphunwaraphon","doi":"10.1016/j.eij.2025.100875","DOIUrl":"10.1016/j.eij.2025.100875","url":null,"abstract":"<div><div>Recommendation systems have become crucial in recent years, particularly in the travel industry, helping travelers discover appealing destinations. Special interest travelers seeking unique experiences require tailored activity-based recommendations. However, relying solely on search engines tends to yield generic results, often leading to repetitive information streams. To address this, our paper proposes a framework for extracting tourism activities and linking them to tourism types and destinations. We employed grammar-based techniques and n-gram characteristics to effectively extract these activities. The concept of the T–A–P Triangle connects tourism type (T), tourism activity (A), and tourism place (P), providing a comprehensive understanding of these associations. The study assesses the effectiveness of the feature combination used by the Conditional Random Fields (CRF) model to improve the extraction process. Our experiments reveal that our framework successfully extracts tourism-related activities. In particular, the three features of the model — word characteristics, part of speech (PoS), and named entity recognition (NER) — outperformed the single baseline feature, which is only word characteristics, with improvements of 5.26% in precision, 14.68% in recall, and 10.13% in the F1-score.</div></div>","PeriodicalId":56010,"journal":{"name":"Egyptian Informatics Journal","volume":"33 ","pages":"Article 100875"},"PeriodicalIF":4.3,"publicationDate":"2025-12-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145841359","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}
This paper presents a novel method for movie rating prediction and recommendation systems based on similarity between movies with an uncertainty score to control prediction confidence. The two traditional recommendation approaches, namely collaborative filtering and content-based, rely on the concept of similarity between movies and users. Although similarity plays a crucial role in recommendation systems, it has not been sufficiently explored in existing research. To bridge this gap, we propose a dissimilarity function for movies based on a thorough analysis of movie features. We also introduce an uncertainty score that quantifies the confidence in predictions based on the dissimilarity between the unseen movie and the nearest rated movie. The proposed method uses the uncertainty score for two purposes. First, it adjusts the predicted rating by shifting it toward the user’s mean rating when the uncertainty exceeds a predefined threshold. Second, it prioritizes recommendations based on the uncertainty score, allowing the system to recommend only movies with high prediction certainty. The experimental results show that the proposed method is significantly accurate at lower uncertainty thresholds (≤12%). Furthermore, the method also performs well in top-K movie recommendations, providing consistent performance regardless of the number of recommended movies when uncertainty is low. The proposed method is also compared with state-of-the-art machine learning models, such as Support Vector Machine Regression, Random Forest Regressor, and Gradient Boosting Regressor. The comparison shows that our approach outperforms these models at low uncertainty levels and provides more reliable and accurate recommendations.
{"title":"An accurate similarity-based model for movie rating prediction and recommendation using an uncertainty score","authors":"Youssef Hanyf , Hassan Silkan , Abdellatif Dahmouni , Abdelkaher Ait Abdelouahad","doi":"10.1016/j.eij.2025.100860","DOIUrl":"10.1016/j.eij.2025.100860","url":null,"abstract":"<div><div>This paper presents a novel method for movie rating prediction and recommendation systems based on similarity between movies with an uncertainty score to control prediction confidence. The two traditional recommendation approaches, namely collaborative filtering and content-based, rely on the concept of similarity between movies and users. Although similarity plays a crucial role in recommendation systems, it has not been sufficiently explored in existing research. To bridge this gap, we propose a dissimilarity function for movies based on a thorough analysis of movie features. We also introduce an uncertainty score that quantifies the confidence in predictions based on the dissimilarity between the unseen movie and the nearest rated movie. The proposed method uses the uncertainty score for two purposes. First, it adjusts the predicted rating by shifting it toward the user’s mean rating when the uncertainty exceeds a predefined threshold. Second, it prioritizes recommendations based on the uncertainty score, allowing the system to recommend only movies with high prediction certainty. The experimental results show that the proposed method is significantly accurate at lower uncertainty thresholds (≤12%). Furthermore, the method also performs well in top-K movie recommendations, providing consistent performance regardless of the number of recommended movies when uncertainty is low. The proposed method is also compared with state-of-the-art machine learning models, such as Support Vector Machine Regression, Random Forest Regressor, and Gradient Boosting Regressor. The comparison shows that our approach outperforms these models at low uncertainty levels and provides more reliable and accurate recommendations.</div></div>","PeriodicalId":56010,"journal":{"name":"Egyptian Informatics Journal","volume":"33 ","pages":"Article 100860"},"PeriodicalIF":4.3,"publicationDate":"2025-12-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145791744","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}
Pub Date : 2025-12-19DOI: 10.1016/j.eij.2025.100877
P. Sajitha , A. Diana Andrushia , N. Anand , Eva Lubloy
Fruits are the most vital items of global diets because of their rich nutritional value, thereby providing very high demand and agricultural revenues to the economy. Among the fruit crops, pomegranate is a valuable one due to its highest antioxidant potential. However, most crops of pomegranate suffer from diseases, which greatly reduce agricultural yield and productivity. Thus, along with the increasing demand of the fruit, early detection as well as classification of diseases will prove very crucial in boosting the yield and taking appropriate measures for prevention. We propose a segmentation-based model using deep learning in this paper to conduct disease identification in pomegranates The process begins with pre-processing images that is primarily an activity of cropping and resizing of the images, followed by enhanced Wiener filtering, which eliminates noise and enhances the clarity of the images The preprocessed images are then further segmented using a CA_YV5GC algorithm, (Channel Attentive YOLOv5-based Grab Cut), which isolates diseased regions from the images. Then the optimized ResNet-152 network is applied to acquire the fundamental features embedding the texture along with the shape characteristics which could identify ailments related symptoms. Coati Optimization is applied to choose the most dominant features in the lower dimensional representation of the extracted information for the classification of the disease. Ultimately, classification is performed using a Deep Capsule Canonical Auto-encoder (DC_CAENet) to classify the disease type with higher accuracy. Adaptive Osprey Optimization is used to optimize the parameters of the model. The existing methods are compared with that results proved this technique to be more accurate and efficient as compared to traditional techniques.
{"title":"Channel-attentive YOLOv5 and capsule auto-encoder for pomegranate disease detection","authors":"P. Sajitha , A. Diana Andrushia , N. Anand , Eva Lubloy","doi":"10.1016/j.eij.2025.100877","DOIUrl":"10.1016/j.eij.2025.100877","url":null,"abstract":"<div><div>Fruits are the most vital items of global diets because of their rich nutritional value, thereby providing very high demand and agricultural revenues to the economy. Among the fruit crops, pomegranate is a valuable one due to its highest antioxidant potential. However, most crops of pomegranate suffer from diseases, which greatly reduce agricultural yield and productivity. Thus, along with the increasing demand of the fruit, early detection as well as classification of diseases will prove very crucial in boosting the yield and taking appropriate measures for prevention. We propose a segmentation-based model using deep learning in this paper to conduct disease identification in pomegranates The process begins with pre-processing images that is primarily an activity of cropping and resizing of the images, followed by enhanced Wiener filtering, which eliminates noise and enhances the clarity of the images The preprocessed images are then further segmented using a CA_YV5GC algorithm, (Channel Attentive YOLOv5-based Grab Cut), which isolates diseased regions from the images. Then the optimized ResNet-152 network is applied to acquire the fundamental features embedding the texture along with the shape characteristics which could identify ailments related symptoms. Coati Optimization is applied to choose the most dominant features in the lower dimensional representation of the extracted information for the classification of the disease. Ultimately, classification is performed using a Deep Capsule Canonical Auto-encoder (DC_CAENet) to classify the disease type with higher accuracy. Adaptive Osprey Optimization is used to optimize the parameters of the model. The existing methods are compared with that results proved this technique to be more accurate and efficient as compared to traditional techniques.</div></div>","PeriodicalId":56010,"journal":{"name":"Egyptian Informatics Journal","volume":"33 ","pages":"Article 100877"},"PeriodicalIF":4.3,"publicationDate":"2025-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145791746","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}
Pub Date : 2025-12-19DOI: 10.1016/j.eij.2025.100861
Wenyu Zhang , Yajing Li , Jiaxuan Hu , Ning Wang
With the continuous increase in vehicle ownership, the frequency of traffic accidents has risen significantly, and higher demands have consequently been placed on active vehicle safety technologies. To address the challenges of insufficient real-time performance and high model complexity in traditional object detection methods under complex traffic conditions, an improved front-vehicle collision warning system has been proposed by integrating YOLOv8 and DeepSort. In this approach, the original YOLOv8 backbone network is replaced by the lightweight MobileNet V4, and the Convolutional Block Attention Module (CBAM) is incorporated to enhance feature extraction capabilities. A comprehensive algorithmic framework has been constructed, integrating multi-object recognition, front-vehicle distance estimation, ego-vehicle speed calculation, and hierarchical warning level output. Experimental results on the KITTI dataset have demonstrated a detection accuracy of 95.5 % and a total detection time of 2.6 ms per frame. Additionally, a 2.6 % improvement in mAP50–95 has been observed, accompanied by only a 0.1 % decrease in the recall rate. These findings suggest that the proposed method provides effective technical support for front-vehicle collision warning in intelligent transportation environments.
随着机动车保有量的不断增加，交通事故的发生频率显著上升，对车辆主动安全技术提出了更高的要求。针对传统目标检测方法在复杂交通条件下实时性不足、模型复杂度高的问题，将YOLOv8与DeepSort相结合，提出了一种改进的前车碰撞预警系统。在这种方法中，原始的YOLOv8骨干网络被轻量级的MobileNet V4取代，并加入卷积块注意模块（CBAM）来增强特征提取能力。构建了集多目标识别、前车距离估计、自车速度计算、预警等级输出于一体的综合算法框架。在KITTI数据集上的实验结果表明，检测准确率为95.5%，总检测时间为2.6 ms /帧。此外，观察到mAP50-95有2.6%的改善，同时召回率仅下降0.1%。研究结果表明，该方法为智能交通环境下的前车碰撞预警提供了有效的技术支持。
{"title":"A study on front vehicle collision warning method based on lightweight YOLOv8 and DeepSort","authors":"Wenyu Zhang , Yajing Li , Jiaxuan Hu , Ning Wang","doi":"10.1016/j.eij.2025.100861","DOIUrl":"10.1016/j.eij.2025.100861","url":null,"abstract":"<div><div>With the continuous increase in vehicle ownership, the frequency of traffic accidents has risen significantly, and higher demands have consequently been placed on active vehicle safety technologies. To address the challenges of insufficient real-time performance and high model complexity in traditional object detection methods under complex traffic conditions, an improved front-vehicle collision warning system has been proposed by integrating YOLOv8 and DeepSort. In this approach, the original YOLOv8 backbone network is replaced by the lightweight MobileNet V4, and the Convolutional Block Attention Module (CBAM) is incorporated to enhance feature extraction capabilities. A comprehensive algorithmic framework has been constructed, integrating multi-object recognition, front-vehicle distance estimation, ego-vehicle speed calculation, and hierarchical warning level output. Experimental results on the KITTI dataset have demonstrated a detection accuracy of 95.5 % and a total detection time of 2.6 ms per frame. Additionally, a 2.6 % improvement in mAP50–95 has been observed, accompanied by only a 0.1 % decrease in the recall rate. These findings suggest that the proposed method provides effective technical support for front-vehicle collision warning in intelligent transportation environments.</div></div>","PeriodicalId":56010,"journal":{"name":"Egyptian Informatics Journal","volume":"33 ","pages":"Article 100861"},"PeriodicalIF":4.3,"publicationDate":"2025-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145791745","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}
Pub Date : 2025-12-16DOI: 10.1016/j.eij.2025.100838
Yang Gao , Wenjie wang , Yangyang Li
The study introduces a novel sports analytics approach and, for the first time, applies the TabTransformer model to predict attendance at fitness classes. The main objective is to uncover potential sports talent and create in-depth financial planning based on attendance patterns. Compared to the deep model and traditional model, the TabTransformer performs better with an accuracy of 0.710, precision of 0.738, recall of 0.707, F1 score of 0.722, and an AUC-ROC of 0.818. This is because the model can make use of textual embeddings to handle categorical features and linear transformations for numerical features, which are able to capture complex interactions between data. The results depict the high ability of the model to identify committed members in well-attended groups (e.g., Aqua and HIIT), but the model’s moderate recovery in poor-attendance groups (e.g., Strength and Cycling) directs us towards further investigation of barriers to access. These insights pave the way for designing targeted interventions and inclusive financial strategies, including membership subsidies and flexible schedules. Despite limitations such as the moderate size of the dataset and the lack of financial features, this research lays a strong foundation for the application of Transformer models in sports analytics. Ultimately, this study emphasizes the importance of using Transformer-based analytics to generate creative and equitable outcomes in fitness programs and is a step forward in identifying talent and promoting inclusion in sports.
{"title":"Fostering Creative sports talents with transformer models for inclusive financial","authors":"Yang Gao , Wenjie wang , Yangyang Li","doi":"10.1016/j.eij.2025.100838","DOIUrl":"10.1016/j.eij.2025.100838","url":null,"abstract":"<div><div>The study introduces a novel sports analytics approach and, for the first time, applies the TabTransformer model to predict attendance at fitness classes. The main objective is to uncover potential sports talent and create in-depth financial planning based on attendance patterns. Compared to the deep model and traditional model, the TabTransformer performs better with an accuracy of 0.710, precision of 0.738, recall of 0.707, F1 score of 0.722, and an AUC-ROC of 0.818. This is because the model can make use of textual embeddings to handle categorical features and linear transformations for numerical features, which are able to capture complex interactions between data. The results depict the high ability of the model to identify committed members in well-attended groups (e.g., Aqua and HIIT), but the model’s moderate recovery in poor-attendance groups (e.g., Strength and Cycling) directs us towards further investigation of barriers to access. These insights pave the way for designing targeted interventions and inclusive financial strategies, including membership subsidies and flexible schedules. Despite limitations such as the moderate size of the dataset and the lack of financial features, this research lays a strong foundation for the application of Transformer models in sports analytics. Ultimately, this study emphasizes the importance of using Transformer-based analytics to generate creative and equitable outcomes in fitness programs and is a step forward in identifying talent and promoting inclusion in sports.</div></div>","PeriodicalId":56010,"journal":{"name":"Egyptian Informatics Journal","volume":"33 ","pages":"Article 100838"},"PeriodicalIF":4.3,"publicationDate":"2025-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145791747","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}
Pub Date : 2025-12-15DOI: 10.1016/j.eij.2025.100859
Nurzati Iwani Othman , Hassan Jamil Syed , Athirah Mohd Ramly , Nur Hanis Sabrina binti Suhaimi , Aitizaz Ali , Mohamed Abdulnabi , Ahmad Fadzil Ismail
The digital transformation of Industry 4.0 requires networking solutions that deliver ultra-low latency, energy efficiency, and robust security. Conventional 5G architectures face limitations such as high infrastructure costs, performance bottlenecks, and vulnerabilities in mission-critical environments. This study proposes the Private Hybrid Wireless Access Network (PHWAN) framework, a novel architecture that combines localized spectrum management, edge–cloud orchestration, and blockchain-based Zero Trust security. A comprehensive cost–benefit model and MATLAB-based simulation of an industrial IoT environment were used to evaluate PHWAN against traditional 5G deployments. Results show that PHWAN reduces latency by 50 % (0.5 ms to 0.25 ms), lowers energy consumption by 61 % (5.4 mJ to 2.1 mJ), and improves bandwidth utilization by 108 %. Security analysis further demonstrates improved access control and data integrity without incurring significant overhead. These findings establish PHWAN as a scalable and cost-effective alternative to 5G for delay-sensitive and resource-constrained industrial IoT applications. Future research will extend validation to standardized platforms such as NS-3 and 5G-LENA and explore integration with 6G spectrum slicing, quantum-secured communications, and industrial metaverse applications to enhance resilience and interoperability in next-generation smart factories.
{"title":"Beyond 5G: PHWAN – A secure, low-latency, and cost-effective framework for Industry 4.0 smart manufacturing","authors":"Nurzati Iwani Othman , Hassan Jamil Syed , Athirah Mohd Ramly , Nur Hanis Sabrina binti Suhaimi , Aitizaz Ali , Mohamed Abdulnabi , Ahmad Fadzil Ismail","doi":"10.1016/j.eij.2025.100859","DOIUrl":"10.1016/j.eij.2025.100859","url":null,"abstract":"<div><div>The digital transformation of Industry 4.0 requires networking solutions that deliver ultra-low latency, energy efficiency, and robust security. Conventional 5G architectures face limitations such as high infrastructure costs, performance bottlenecks, and vulnerabilities in mission-critical environments. This study proposes the Private Hybrid Wireless Access Network (PHWAN) framework, a novel architecture that combines localized spectrum management, edge–cloud orchestration, and blockchain-based Zero Trust security. A comprehensive cost–benefit model and MATLAB-based simulation of an industrial IoT environment were used to evaluate PHWAN against traditional 5G deployments. Results show that PHWAN reduces latency by 50 % (0.5 ms to 0.25 ms), lowers energy consumption by 61 % (5.4 mJ to 2.1 mJ), and improves bandwidth utilization by 108 %. Security analysis further demonstrates improved access control and data integrity without incurring significant overhead. These findings establish PHWAN as a scalable and cost-effective alternative to 5G for delay-sensitive and resource-constrained industrial IoT applications. Future research will extend validation to standardized platforms such as NS-3 and 5G-LENA and explore integration with 6G spectrum slicing, quantum-secured communications, and industrial metaverse applications to enhance resilience and interoperability in next-generation smart factories.</div></div>","PeriodicalId":56010,"journal":{"name":"Egyptian Informatics Journal","volume":"33 ","pages":"Article 100859"},"PeriodicalIF":4.3,"publicationDate":"2025-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145791748","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}
Pub Date : 2025-12-11DOI: 10.1016/j.eij.2025.100850
Wei Zheng , Lili Huang , Haiqiang Liu , Fa Zhu , Achyut Shankar , Imad Rida , Davide Moroni
The angle-based outlier detection (ABOD) is proposed to tackle the “curse of dimensionality” that exists in distance-related or density-related outlier detectors. However, ABOD may fail on multimodal datasets since it only considers global information. Furthermore, ABOD needs to calculate the angles between difference vectors from an instance to each pair of instances in the dataset except itself. Its time complexity reaches O (n3). In order to address these two issues, this paper proposes localized angle-based outlier detection (LABOD) which first finds the influence set, and then calculates the variance of angles between the difference vector from an instance to the mean of its neighbors in the influence set and the difference vectors from the instance to its neighbors in the influence set. The influence set consists of the nearest neighbor set and the reverse nearest neighbor set. Because the variance is defined by the angles in a local region, the proposed method can overcome the drawbacks of ABOD. The experiments performed on both synthetic and benchmark datasets demonstrate that LABOD is superior to ABOD.
{"title":"Localized angle-based unsupervised outlier detection","authors":"Wei Zheng , Lili Huang , Haiqiang Liu , Fa Zhu , Achyut Shankar , Imad Rida , Davide Moroni","doi":"10.1016/j.eij.2025.100850","DOIUrl":"10.1016/j.eij.2025.100850","url":null,"abstract":"<div><div>The angle-based outlier detection (ABOD) is proposed to tackle the “curse of dimensionality” that exists in distance-related or density-related outlier detectors. However, ABOD may fail on multimodal datasets since it only considers global information. Furthermore, ABOD needs to calculate the angles between difference vectors from an instance to each pair of instances in the dataset except itself. Its time complexity reaches <em>O</em> (<em>n<sup>3</sup></em>). In order to address these two issues, this paper proposes localized angle-based outlier detection (LABOD) which first finds the influence set, and then calculates the variance of angles between the difference vector from an instance to the mean of its neighbors in the influence set and the difference vectors from the instance to its neighbors in the influence set. The influence set consists of the nearest neighbor set and the reverse nearest neighbor set. Because the variance is defined by the angles in a local region, the proposed method can overcome the drawbacks of ABOD. The experiments performed on both synthetic and benchmark datasets demonstrate that LABOD is superior to ABOD.</div></div>","PeriodicalId":56010,"journal":{"name":"Egyptian Informatics Journal","volume":"33 ","pages":"Article 100850"},"PeriodicalIF":4.3,"publicationDate":"2025-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145719068","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}
<div><div>Many sectors of the economy are impacted by embedded computer systems including tools, basic architecture and a range of other features that contribute to the success of these systems. It is vital to guarantee these systems’ functionality and dependability. However, instances in which drifting behaviour can occur in embedded systems as a result of things such as software upgrades, hardware deterioration, and environmental changes over time, which can lead to drifting behaviour. As a result, test cases may become antiquated or less effective in identifying important areas of concern. This study offers a new technique for the multi-output realm of Temperature Monitoring Nuclear Reactor Systems (TMCNRS) predictive analysis of drifting test cases and key regions in embedded systems using Gaussian distribution. The examination makes use of artificial intelligence practices and statistical tools to perceive and adjust to variations in the system’s behaviour. The suggested approach’s preliminary step is gathering historic test case and system behaviour data. Using this data, a baseline Gaussian distribution that replicates the anticipated behaviour of the embedded system and the test cases that go along with it is established. In the subsequent phase, the performance of the embedded system will be continuously monitored, and renewed data will gradually be collected as to its performance. Drift is the nonconformity of the system’s behaviour with the reference line distribution that has been set. Exploiting a multi-output Gaussian distribution model, the technique forecasts conceivable drift in every test case and crucial region. Advanced learning practices are incorporated in the third phase, which modifies the test cases and critical area recognition criteria based on identified drift. The algorithm may adaptively change test cases to increase their efficiency and more correctly identify new key regions by assessing the deviations from the baseline distribution. In order to authenticate the efficacy of the suggested methodology, a multitude of real-world embedded systems across diverse fields of application are subjected to intensive experimentation. According to our results, even in the face of drifting action, the predictive analysis that manipulates the multi-output Gaussian distribution greatly increases the accuracy of the test case as well as strengthens the capacity of the system to detect important locations within the system in the presence of drifting action. The creation of a reliable and flexible technique for identifying drifting test cases and crucial regions in integrated systems is where this study contributes. Through the use of Optimal Gaussian distribution (OGD) in the context of multiple outputs, the suggested methodology presents a novel way to preserve the dependability and efficiency of embedded systems, guaranteeing their capacity to function efficiently even in constantly evolving and dynamic surroundings. This study s
{"title":"Predictive analysis of drifting test cases and critical areas for enhancing embedded systems using a Gaussian distribution methodology for multi-output analysis","authors":"M.Lakshmi Prasad , R.Obulakonda Reddy , Sandeep Kautish , G.Suresh Reddy , Abdulaziz S. Almazyad , Ali Wagdy Mohamed , Seyed Jalaleddin Mousavirad","doi":"10.1016/j.eij.2025.100857","DOIUrl":"10.1016/j.eij.2025.100857","url":null,"abstract":"<div><div>Many sectors of the economy are impacted by embedded computer systems including tools, basic architecture and a range of other features that contribute to the success of these systems. It is vital to guarantee these systems’ functionality and dependability. However, instances in which drifting behaviour can occur in embedded systems as a result of things such as software upgrades, hardware deterioration, and environmental changes over time, which can lead to drifting behaviour. As a result, test cases may become antiquated or less effective in identifying important areas of concern. This study offers a new technique for the multi-output realm of Temperature Monitoring Nuclear Reactor Systems (TMCNRS) predictive analysis of drifting test cases and key regions in embedded systems using Gaussian distribution. The examination makes use of artificial intelligence practices and statistical tools to perceive and adjust to variations in the system’s behaviour. The suggested approach’s preliminary step is gathering historic test case and system behaviour data. Using this data, a baseline Gaussian distribution that replicates the anticipated behaviour of the embedded system and the test cases that go along with it is established. In the subsequent phase, the performance of the embedded system will be continuously monitored, and renewed data will gradually be collected as to its performance. Drift is the nonconformity of the system’s behaviour with the reference line distribution that has been set. Exploiting a multi-output Gaussian distribution model, the technique forecasts conceivable drift in every test case and crucial region. Advanced learning practices are incorporated in the third phase, which modifies the test cases and critical area recognition criteria based on identified drift. The algorithm may adaptively change test cases to increase their efficiency and more correctly identify new key regions by assessing the deviations from the baseline distribution. In order to authenticate the efficacy of the suggested methodology, a multitude of real-world embedded systems across diverse fields of application are subjected to intensive experimentation. According to our results, even in the face of drifting action, the predictive analysis that manipulates the multi-output Gaussian distribution greatly increases the accuracy of the test case as well as strengthens the capacity of the system to detect important locations within the system in the presence of drifting action. The creation of a reliable and flexible technique for identifying drifting test cases and crucial regions in integrated systems is where this study contributes. Through the use of Optimal Gaussian distribution (OGD) in the context of multiple outputs, the suggested methodology presents a novel way to preserve the dependability and efficiency of embedded systems, guaranteeing their capacity to function efficiently even in constantly evolving and dynamic surroundings. This study s","PeriodicalId":56010,"journal":{"name":"Egyptian Informatics Journal","volume":"33 ","pages":"Article 100857"},"PeriodicalIF":4.3,"publicationDate":"2025-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145718906","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}
Pub Date : 2025-12-01DOI: 10.1016/j.eij.2025.100852
Ratheeshkumar A.M , D. Surendran
Accurate embryo stage classification is crucial for enhancing IVF success rates; however, existing automated methods often struggle to handle inter-stage similarity and class imbalance, leading to misclassification across morphologically similar developmental phases. Furthermore, conventional CNN-based approaches tend to lose fine-grained spatial details, which are critical for distinguishing closely related stages. The proposed EmbryoSwin++ model addresses these gaps by integrating a Swin Transformer backbone with a supervised contrastive learning head and a Balanced Batch Sampler, enabling the model to learn discriminative embeddings while ensuring equitable representation of all 15 developmental stages. This dual-loss framework, combining label-smoothed cross-entropy and contrastive loss, enhances robustness, mitigates overfitting, and improves generalization across datasets. Evaluated on the Human Embryo Time-Lapse Video Dataset, the model achieved a validation accuracy of 92.12 %, a macro F1-score of 0.9196, and high AUC values approaching 1.0 for all classes, demonstrating strong discriminative capability. Grad-CAM analysis confirmed the model’s focus on biologically relevant embryo regions, validating its interpretability.
{"title":"EmbryoSwin++: Enhanced swin transformer with supervised contrastive learning for embryo multi-stage classification in assisted reproductive technology","authors":"Ratheeshkumar A.M , D. Surendran","doi":"10.1016/j.eij.2025.100852","DOIUrl":"10.1016/j.eij.2025.100852","url":null,"abstract":"<div><div>Accurate embryo stage classification is crucial for enhancing IVF success rates; however, existing automated methods often struggle to handle inter-stage similarity and class imbalance, leading to misclassification across morphologically similar developmental phases. Furthermore, conventional CNN-based approaches tend to lose fine-grained spatial details, which are critical for distinguishing closely related stages. The proposed EmbryoSwin++ model addresses these gaps by integrating a Swin Transformer backbone with a supervised contrastive learning head and a Balanced Batch Sampler, enabling the model to learn discriminative embeddings while ensuring equitable representation of all 15 developmental stages. This dual-loss framework, combining label-smoothed cross-entropy and contrastive loss, enhances robustness, mitigates overfitting, and improves generalization across datasets. Evaluated on the Human Embryo Time-Lapse Video Dataset, the model achieved a validation accuracy of 92.12 %, a macro F1-score of 0.9196, and high AUC values approaching 1.0 for all classes, demonstrating strong discriminative capability. Grad-CAM analysis confirmed the model’s focus on biologically relevant embryo regions, validating its interpretability.</div></div>","PeriodicalId":56010,"journal":{"name":"Egyptian Informatics Journal","volume":"32 ","pages":"Article 100852"},"PeriodicalIF":4.3,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145746883","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}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号