Weiwei Jiang, Ao Liu, Yang Zhang, Haoyu Han, Jianbin Mu, Shang Liu, Weixi Gu, Sai Huang
{"title":"Coverage Prediction in Mobile Communication Networks: A Deep Learning Approach With a Tabular Foundation Model","authors":"Weiwei Jiang, Ao Liu, Yang Zhang, Haoyu Han, Jianbin Mu, Shang Liu, Weixi Gu, Sai Huang","doi":"10.1002/itl2.70034","DOIUrl":"https://doi.org/10.1002/itl2.70034","url":null,"abstract":"<div>\u0000 \u0000 <p>Accurate coverage prediction in mobile communication networks is crucial for optimizing performance and ensuring reliable service. However, traditional methods often struggle with the complexity and dynamic nature of wireless environments. This study introduces a novel approach leveraging a deep learning model with a tabular foundation model, TabPFN, which utilizes in-context learning and a transformer-based architecture to surpass existing techniques. Experimental validation on a real-world dataset demonstrates the model's superior prediction accuracy and adaptability, outperforming gradient boosting decision trees and supervised deep learning models in terms of root mean square error (RMSE), mean absolute error (MAE), and coefficient of determination (<i>R</i><sup>2</sup>).</p>\u0000 </div>","PeriodicalId":100725,"journal":{"name":"Internet Technology Letters","volume":"8 3","pages":""},"PeriodicalIF":0.9,"publicationDate":"2025-04-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143888887","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
R. P. Sujith Kanna, B. Vasudevan, S. Gyana Guru Prasanth, R. C. Omkareswar
{"title":"Performance Analysis of Mode Division Multiplexing-Based Underwater Optical Wireless Communication Systems in Varied Water Types","authors":"R. P. Sujith Kanna, B. Vasudevan, S. Gyana Guru Prasanth, R. C. Omkareswar","doi":"10.1002/itl2.70019","DOIUrl":"https://doi.org/10.1002/itl2.70019","url":null,"abstract":"<div>\u0000 \u0000 <p>Underwater optical wireless communication (UOWC) employs light signals to transmit data at high speeds in aquatic environments, enabling rapid and low-latency connectivity. This technology supports critical applications such as marine exploration, environmental monitoring, and underwater robotics, despite challenges like light absorption and scattering. UOWC systems have gained significant attention for their high data rate capabilities in underwater environments. This paper presents a comprehensive performance analysis of a mode division multiplexing (MDM)-based UOWC system employing four distinct Hermite-Gaussian (HG) modes, each supporting independent 10 Gbps data streams. The study evaluates the system's performance in diverse water conditions, including Pure Sea, Coastal Sea, Clear Sea, and Harbor waters. Key performance metrics such as bit error rate (BER) and <i>Q</i> factor are analyzed against increasing link ranges for each water type. The results demonstrate that all the 4-HG beams perform similarly under the effect of oceanic turbulence. The results demonstrate that the proposed system transmits 40 Gbps data up to 21.5 m under pure sea conditions which reduces to 15 m under clear ocean, 9.8 m under coastal ocean, and 5.6 m under Harbor I conditions, and 3.6 m for Harbor II conditions with acceptable <i>Q</i> factor <span></span><math>\u0000 <semantics>\u0000 <mrow>\u0000 <mo>˜</mo>\u0000 </mrow>\u0000 <annotation>$$ sim $$</annotation>\u0000 </semantics></math> 4 dB and BER <span></span><math>\u0000 <semantics>\u0000 <mrow>\u0000 <mo>≤</mo>\u0000 <msup>\u0000 <mn>10</mn>\u0000 <mrow>\u0000 <mo>−</mo>\u0000 <mn>3</mn>\u0000 </mrow>\u0000 </msup>\u0000 </mrow>\u0000 <annotation>$$ le {10}^{-3} $$</annotation>\u0000 </semantics></math>. Results demonstrate the impact of varying absorption and scattering properties of water on system performance, providing valuable insights into the feasibility and optimization of MDM-based UOWC systems for underwater environments. The findings highlight the potential of MDM techniques to enhance data transmission efficiency and reliability across diverse underwater conditions, paving the way for advanced underwater communication networks.</p>\u0000 </div>","PeriodicalId":100725,"journal":{"name":"Internet Technology Letters","volume":"8 3","pages":""},"PeriodicalIF":0.9,"publicationDate":"2025-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143880057","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A Hybrid Multicriteria Decision-Making Algorithm for Energy-Efficient Clustering in Industrial Wireless Sensor Networks","authors":"G. Yogarajan, T. Revathi, A. S. Karthik Kannan","doi":"10.1002/itl2.70030","DOIUrl":"https://doi.org/10.1002/itl2.70030","url":null,"abstract":"<div>\u0000 \u0000 <p>Industrial wireless sensor networks allow the use of battery-operated sensor nodes for environmental monitoring in harsh industrial environments. Optimal usage of the sensor node's battery energy and balanced energy consumption among sensor nodes is essential to prolong the lifetime of the network. This letter proposes a hybrid multi-criteria decision-making algorithm for an industrial wireless sensor network with heterogeneous energy levels and traffic patterns among sensor nodes to be optimally grouped into energy-efficient clusters. The simulation results demonstrate that the proposed approach achieves 70% improvement in network lifetime and a 75.5% improvement in packets delivered to the base station over other existing algorithms.</p>\u0000 </div>","PeriodicalId":100725,"journal":{"name":"Internet Technology Letters","volume":"8 3","pages":""},"PeriodicalIF":0.9,"publicationDate":"2025-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143883801","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Load Balancing Routing Algorithm for LEO Satellite Networks Based on Ant Colony Optimization","authors":"Ruxin Zhi, Jiahui Wang, Zhan Xu","doi":"10.1002/itl2.70031","DOIUrl":"https://doi.org/10.1002/itl2.70031","url":null,"abstract":"<p>To address the problem of the unbalanced load and optimize the traffic distribution of large-scale low earth orbit (LEO) satellite networks, this paper proposes a load-balancing routing algorithm for LEO satellite networks based on ant colony optimization. The algorithm establishes the global optimal initial path through the improved ant colony algorithm to bypass the network bottleneck, makes local adjustments to cope with burst traffic changes to avoid congestion, and optimizes the “inferior” paths through regular rerouting to improve the overall network performance. The results show that the algorithm performs well in terms of packet loss rate, throughput, and load balancing, which can effectively alleviate the link utilization imbalance problem and provide a more stable and efficient service for the satellite network. Among them, the packet loss rate is reduced by 7.8%, and the load distribution index is improved by 30%.</p>","PeriodicalId":100725,"journal":{"name":"Internet Technology Letters","volume":"8 3","pages":""},"PeriodicalIF":0.9,"publicationDate":"2025-04-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/itl2.70031","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143879866","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
S. Premalatha, D. Sunitha, B. Manojkumar, G. Kavitha, Manjunathan Alagarsamy
{"title":"Point-Wise Activations and Steerable Convolutional Networks for DDoS-Attack Detection in Cyber-Physical Systems Over 5G Networks","authors":"S. Premalatha, D. Sunitha, B. Manojkumar, G. Kavitha, Manjunathan Alagarsamy","doi":"10.1002/itl2.70026","DOIUrl":"https://doi.org/10.1002/itl2.70026","url":null,"abstract":"<div>\u0000 \u0000 <p>The growth in DDoS attacks in CPS over 5G networks has emerged as the major risks affecting the reliability and continuity of car supply chain systems. Old school approaches to detection fail to work properly within 5G environments because of large and constantly changing volumes of traffic data that cannot be easily filtered for malicious patterns. In order to overcome these problems, this research work suggests a new framework that combines Point-Wise Activations with Steerable Convolutional Networks (PSCNs) with Circulatory System-Based Optimization (CSBO) for DDoS attack detection. The PSCNs excel in extracting both global and local information from network traffic, while the CSBO is tasked with optimizing the hyperparameters and weights of the network, thereby enhancing its performance. The current method proficiently addresses the issue and achieves an accuracy of 99.9% in comparison to other heuristics. Consequently, the CSBO, which employs adaptive and efficient optimization, ensures that the proposed framework delivers highly accurate real-time DDoS detection methods and is dependable for enhancing security in both current and future 5G-enabled Cyber-Physical Systems (CPS).</p>\u0000 </div>","PeriodicalId":100725,"journal":{"name":"Internet Technology Letters","volume":"8 3","pages":""},"PeriodicalIF":0.9,"publicationDate":"2025-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143852700","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Kama Ramudu, Arun Kumar Udayakumar, Arun Kumar, Aziz Nanthaamornphong, S. Gopinath
{"title":"Optimized Neuro-Adaptive Twin Pulse-Coupled Estimators for Efficient Channel Estimation in Heterogeneous 5G MIMO-OFDM Communication Systems","authors":"Kama Ramudu, Arun Kumar Udayakumar, Arun Kumar, Aziz Nanthaamornphong, S. Gopinath","doi":"10.1002/itl2.70013","DOIUrl":"https://doi.org/10.1002/itl2.70013","url":null,"abstract":"<div>\u0000 \u0000 <p>Optimal performance in 5G and beyond MIMO-OFDM systems is achieved by channel estimation, which is crucial due to the enormous hurdles posed by dynamic and frequency-selective channel circumstances. Advanced methods of neural networks and optimization are gradually being applied in order to solve these difficulties. The heterogeneous nature of 5G-and-beyond networks introduces severe multipath fading, high mobility, and interference, complicating accurate Channel State Information (CSI) estimation. Existing techniques are sometimes difficult to compute efficiently while at the same time providing a precise estimation of interference in such scenarios. This research develops an Optimized Neuro-Adaptive Twin Pulse-Coupled Estimators for Efficient Channel Estimation in Heterogeneous 5G-and-Beyond MIMO-OFDM Communication Systems (STEB-Twin-APCNet) to improve the channel estimation by integrating Twin Adaptive Pulse Coupled Network with Sooty Tern Evolutionary Boost optimization. The objective of this study is to design and optimize a neuro-adaptive channel estimator capable of real-time CSI acquisition with high accuracy and minimal complexity in diverse 5G environments. To test the model in different channel scenarios, MATLAB simulations were run with the help of deep learning and 5G toolboxes. The results show that the suggested STEB-Twin-APCNet outperforms the standard approaches with a channel estimate accuracy of over 99.8%, dependability of 99.5% in high-mobility situations, and a decrease of 99.3% in estimation error. These measures demonstrate how efficient and resilient the system is. As a result, channel prediction for next-gen wireless networks is made easier using this adaptive framework.</p>\u0000 </div>","PeriodicalId":100725,"journal":{"name":"Internet Technology Letters","volume":"8 3","pages":""},"PeriodicalIF":0.9,"publicationDate":"2025-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143852701","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Rahamat Basha, Pankaj Pathak, M. Sudha, K. V. Soumya, J. Arockia Venice
{"title":"Optimization of Quantum Dilated Convolutional Neural Networks: Image Recognition With Quantum Computing","authors":"Rahamat Basha, Pankaj Pathak, M. Sudha, K. V. Soumya, J. Arockia Venice","doi":"10.1002/itl2.70027","DOIUrl":"https://doi.org/10.1002/itl2.70027","url":null,"abstract":"<div>\u0000 \u0000 <p>As computer vision tasks increasingly rely on Convolutional Neural Networks (CNNs) with ever-expanding parameter counts, the need for computational resources for model training is growing unsustainable, surpassing traditional computing hardware's progress. To address this challenge, emerging paradigms such as quantum computing are gaining attention as prospective alternatives for the future. This manuscript proposes Quantum Dilated Convolutional Neural Networks Revolutionizing Image Recognition with Quantum Computing (QDCNN-IR-QC). The first step is to use the MNIST dataset for the input pictures. Subsequently, Improved Bilateral Texture Filtering (IBTF) is used to preprocess the input pictures. Subsequently, E-LBP is used to extract pertinent features from the preprocessed pictures. In most cases, E-LBP does not show that optimization methods for picture recognition have been adjusted. Therefore, in order to adjust the E-LBP weight parameter, this paper suggests an ISMO optimization approach. Lastly, a new quantum architecture for picture identification is developed using QDCNN. To implement the proposed approach, Python is used. This is where metrics like F-Measure, accuracy, sensitivity, specificity, and precision are assessed. When compared to current techniques such as QOCNN-IR-QC, ANN-IR-QC, and QKNN-IR-QC, the proposed approaches provide 5.27%, 7.21%, and 8.23% greater accuracy, respectively, in terms of efficiency.</p>\u0000 </div>","PeriodicalId":100725,"journal":{"name":"Internet Technology Letters","volume":"8 3","pages":""},"PeriodicalIF":0.9,"publicationDate":"2025-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143852699","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A Selective Data Sharing and Retrieval Scheme in Edge-Enabled IoV","authors":"Hongbo Qu, Yi Cao, Shuaipeng Li","doi":"10.1002/itl2.70028","DOIUrl":"https://doi.org/10.1002/itl2.70028","url":null,"abstract":"<div>\u0000 \u0000 <p>The swift advancement of the Internet of Vehicles (IoV) has generated a vast amount of valuable data, leading to an increasing demand for IoV data sharing. Given the substantial volume of data that often contains sensitive information about vehicle owners, storing such data in an encrypted format is common practice to ensure its confidentiality. However, this storage method presents a significant data-sharing challenge: retrieving encrypted data. In this paper, we address the issue of private data sharing and retrieval by proposing a selective data sharing and retrieval scheme for edge-enabled IoV. Our approach introduces a novel IoV architecture based on blockchain and edge computing, which delegates most computational tasks to edge nodes, thus conserving the computational resources of vehicles and users. Additionally, we design an attribute-based searchable encryption scheme that supports users in performing fine-grained data retrieval and outsourced data decryption. Our scheme accommodates a large attribute universe, offers a flexible access policy, and conserves computational resources during user decryption. Finally, an in-depth evaluation of the proposed scheme's performance is conducted, showcasing its feasibility and practicality through experimental results. The results confirm our scheme's effectiveness and reinforce its viability for real-world applications.</p>\u0000 </div>","PeriodicalId":100725,"journal":{"name":"Internet Technology Letters","volume":"8 3","pages":""},"PeriodicalIF":0.9,"publicationDate":"2025-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143840590","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Multi-Scale Context-Aware Sentiment Analysis for Language Teaching Applications in 6G Network","authors":"Yunhe Zhu","doi":"10.1002/itl2.70018","DOIUrl":"https://doi.org/10.1002/itl2.70018","url":null,"abstract":"<div>\u0000 \u0000 <p>With the advent of 6G technology, which promises ultralow latency and unprecedented data transmission speeds, the potential for real-time sentiment analysis on a global scale becomes increasingly feasible, which has emerged as an indispensable tool for deciphering user opinions and emotions across a broad spectrum of domains, including language teaching. In response to these challenges, this work explores the theoretical framework and proposes practical implementations for context-aware and multi-scale sentiment analysis, which involve using advanced natural language processing techniques for teaching data preprocessing. Then, the recurrent neural networks (RNNs) are utilized for handling sequential dependencies in text, so as to further revolutionize sentiment analysis by enabling simultaneous consideration of entire contexts through self-attention mechanisms, making them highly effective for multi-scale and context-aware analysis. Our findings reveal significant improvements in the precision and recall rates of sentiment classification, underscoring the potential of multi-scale context-aware sentiment analysis to revolutionize how we understand and respond to human emotions across diverse sectors. By offering deeper insights into the sentiments expressed within textual data, this approach paves the way for more informed decision-making processes and tailored responses, ultimately contributing to enhanced user experiences and outcomes.</p>\u0000 </div>","PeriodicalId":100725,"journal":{"name":"Internet Technology Letters","volume":"8 3","pages":""},"PeriodicalIF":0.9,"publicationDate":"2025-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143831107","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Fog-Platform-Enabled Controlled Music Generation via Transformer Networks With Integrated Style Analysis","authors":"Cui Cai","doi":"10.1002/itl2.70025","DOIUrl":"https://doi.org/10.1002/itl2.70025","url":null,"abstract":"<div>\u0000 \u0000 <p>This article introduces a novel fog-platform-based methodology for controlled music generation and prediction, integrating distributed computing with transformer-based models. The proposed system leverages fog computing architecture to distribute processing tasks between edge devices and cloud servers, enabling real-time feature extraction while maintaining high musicality. By implementing MFCCs calculation and rhythm analysis at fog nodes close to data sources, we achieve significant latency reduction compared to pure cloud architectures. The cloud-based Transformer core then utilizes these pre-processed features for style-controlled music generation through its self-attention mechanisms. Experimental results demonstrate our hybrid approach not only maintains high style accuracy but also reduces upstream bandwidth consumption significantly, addressing critical challenges in IoT-enabled music generation scenarios. This research pioneers a viable pathway for deploying AI music systems in latency-sensitive environments through fog-cloud collaboration.</p>\u0000 </div>","PeriodicalId":100725,"journal":{"name":"Internet Technology Letters","volume":"8 3","pages":""},"PeriodicalIF":0.9,"publicationDate":"2025-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143818735","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}