International Journal of Communication Systems最新文献

Optimizing USV AoI for RIS-Assisted UAV–USV MEC Network ris辅助无人机- USV MEC网络的USV AoI优化

IF 1.8 4区计算机科学

International Journal of Communication Systems Pub Date : 2025-10-13 DOI: 10.1002/dac.70292

Chao Ma, Quan Liu, Yangzhe Liao

{"title":"Optimizing USV AoI for RIS-Assisted UAV–USV MEC Network","authors":"Chao Ma, Quan Liu, Yangzhe Liao","doi":"10.1002/dac.70292","DOIUrl":"https://doi.org/10.1002/dac.70292","url":null,"abstract":"<div>\u0000 \u0000 <p>Aiming to promise timely data delivery and quantify the information freshness of unmanned surface vehicles (USVs), age of information (AoI) is proposed as a novel metric regarding exploring implementations for reconfigurable intelligent surface (RIS)–assisted unmanned aerial vehicle (UAV)–USV multiaccess edge computing network. In this paper, a set of RIS-carried UAVs serves USVs via time division multiple access; each RIS is capable of delivering a single reflection per USV within its service duration. USV long-term time-averaged AoI (AAoI) minimization problem is investigated under USV service duration indicators, UAV-mounted RIS phase shift vector, terrestrial base station (TBS) beamforming vector, and UAV trajectory constraints. To efficiently solve the formulated problem, Lyapunov framework is applied to decompose the original problem into an array of per-slot problems, where each of which can be divided into numerous subproblems, for example, TBS beamforming vector subproblem, RIS phase shift subproblem, and the joint UAV trajectories and USV service duration indicator subproblem. Then, each subproblem can be solved using the proposed successive convex approximation, semidefinite relaxation method, and the enhanced differential evolution algorithm iteratively. Consequently, one can efficiently obtain the feasible solution. The proposed solution reduces USV AAoI by up to 55% while maintaining lower UAV power consumption compared with benchmarks. Also, the proposed solution can promise adequate network queue backlogs under typical USV task data size.</p>\u0000 </div>","PeriodicalId":13946,"journal":{"name":"International Journal of Communication Systems","volume":"38 17","pages":""},"PeriodicalIF":1.8,"publicationDate":"2025-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145284555","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Spectrum Management: The Case of 5G-Based NG-ETC in Japan 频谱管理：以日本基于5g的NG-ETC为例

IF 1.8 4区计算机科学

International Journal of Communication Systems Pub Date : 2025-10-11 DOI: 10.1002/dac.70284

Yung-Chang Hsiao, Shiu-Li Huang

{"title":"Spectrum Management: The Case of 5G-Based NG-ETC in Japan","authors":"Yung-Chang Hsiao, Shiu-Li Huang","doi":"10.1002/dac.70284","DOIUrl":"https://doi.org/10.1002/dac.70284","url":null,"abstract":"<div>\u0000 \u0000 <p>The pervasive wireless network facilitates connectivity across a wide range of devices and extends its applications to both vertical and horizontal industries in future smart cities. The intelligent transportation system (ITS) capitalizes on this connectivity to enhance the capabilities and diversity of interactions among vehicles, networks, infrastructure, and pedestrians. Although the architectures and use cases for smart cities and vehicle-to-everything (V2X) have been extensively discussed, the coexistence of rapidly growing numbers of devices within overlapping spectrum bands presents a novel challenge. This study analyzes and evaluates current electronic toll collection (ETC) systems from a spectrum management perspective and aims to propose a spectrum-manageable ETC system capable of providing long-range coverage, resisting interference, and reliable availability, ensuring signal quality for sufficient throughput by using emerging wireless system through a spectrum management approach. It leverages the advanced features of fifth-generation (5G) technology, including bandwidth part (BWP), millimeter wave, beamforming, and beam ID, to predict the impact of potential harmful interference caused by a vast number of devices, using the Monte Carlo statistical methodology. Moreover, the prediction results, combined with additional protection criteria, are used to design a modern ETC system that performs BWP switching based on interference. The results demonstrate that the proposed approach is resistant to interference and meets the requirements of use cases in the next generation of ITSs.</p>\u0000 </div>","PeriodicalId":13946,"journal":{"name":"International Journal of Communication Systems","volume":"38 16","pages":""},"PeriodicalIF":1.8,"publicationDate":"2025-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145272442","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

AI-Enhanced AODV Routing for Intelligent Traffic Management in Smart City Internet of Things Networks 面向智慧城市物联网智能交通管理的ai增强AODV路由

IF 1.8 4区计算机科学

International Journal of Communication Systems Pub Date : 2025-10-09 DOI: 10.1002/dac.70271

Najah Kalifah Almazmomi

{"title":"AI-Enhanced AODV Routing for Intelligent Traffic Management in Smart City Internet of Things Networks","authors":"Najah Kalifah Almazmomi","doi":"10.1002/dac.70271","DOIUrl":"https://doi.org/10.1002/dac.70271","url":null,"abstract":"<div>\u0000 \u0000 <p>The rapid expansion of smart cities has increased reliance on the Internet of Things (IoT) to manage urban infrastructure efficiently. However, traditional communication protocols often face challenges in dynamic, high-density environments, particularly regarding routing stability and real-time traffic control. To address these limitations, this study proposes an AI-enhanced ad hoc on-demand distance vector (AODV) routing protocol integrated with intelligent, real-time traffic management tailored for smart city IoT networks. The system combines distributed AODV-based communication with a gated recurrent unit (GRU) model that predicts traffic flow patterns using real-time sensor input and historical data. GRU is selected for its computational efficiency and ability to model temporal dependencies, making it well suited for time-sensitive smart city applications. The model is trained on the Traffic4Cast dataset—comprising real-world spatiotemporal traffic data from major European cities—and optimized using the Adam optimizer to ensure fast convergence and high prediction accuracy. The proposed framework follows four phases: (1) traffic data acquisition and preprocessing, (2) GRU-based traffic forecasting, (3) congestion-aware route optimization, and (4) dynamic AODV route adjustment based on predicted traffic conditions. Simulation experiments conducted in NS-3 demonstrate that the framework improves the packet delivery ratio by 13.8%, reduces end-to-end latency by 17.6%, and boosts throughput by 20.9% compared with baseline AODV implementations. Continuous real-time integration of GRU predictions enables the system to adapt efficiently to evolving traffic conditions. This work presents a scalable, AI-driven communication infrastructure designed to enhance urban mobility, reduce congestion, and advance sustainable smart city development.</p>\u0000 </div>","PeriodicalId":13946,"journal":{"name":"International Journal of Communication Systems","volume":"38 16","pages":""},"PeriodicalIF":1.8,"publicationDate":"2025-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145272247","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Optimizing QoS-Based Communication Protocol in Wireless Sensor Networks Using Genetic Algorithms With AI/ML Mechanisms for IoT Environment 物联网环境下基于AI/ML机制的遗传算法优化无线传感器网络中基于qos的通信协议

IF 1.8 4区计算机科学

International Journal of Communication Systems Pub Date : 2025-10-08 DOI: 10.1002/dac.70289

K. Janani, K. B. Gurumoorthy

{"title":"Optimizing QoS-Based Communication Protocol in Wireless Sensor Networks Using Genetic Algorithms With AI/ML Mechanisms for IoT Environment","authors":"K. Janani, K. B. Gurumoorthy","doi":"10.1002/dac.70289","DOIUrl":"https://doi.org/10.1002/dac.70289","url":null,"abstract":"<div>\u0000 \u0000 <p>Wireless sensor networks (WSNs) designed for the Internet of Things (IoT) need to satisfy the service quality demands of real-time applications. The communication and routing from WSN to IoT are adaptable to meet the service demands. To aid such a process, this article introduces a learning-assisted genetic process for communication assistance (LGP-CA) method. The proposed method identifies quality demands for the applications through intense requests and tenure. Based on the prolonged tenure, service degradations are identified to improve the back-end application communication support. The prolonging tenures are identified using the genetic algorithm that generates time-based remaining requests for the service intervals. In this case, the pending/prolonged service demands are serviced by allocating idle resources. This process is monitored using deep learning that executes the chances of request offloading or shared allocations. The communication assistance for prolonged service demands is handled by the WS nodes connected to the resources. Based on the learning suggestions, the node selection and discard processes are formulated. This process enhances the application service throughput, and service delivery, and reduces the service latency. The proposed method improves service throughput, delivery, and shared allocations by 9.83%, 8.99%, and 7.28%, respectively, for the maximum requests.</p>\u0000 </div>","PeriodicalId":13946,"journal":{"name":"International Journal of Communication Systems","volume":"38 16","pages":""},"PeriodicalIF":1.8,"publicationDate":"2025-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145272046","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Energy Usage Patterns in Smart Campus With STM32 and GreenLoRaWAN Communication Protocol-Based Temporal Attention Recurrent Graph Convolutional Neural Network on Edge Computing 基于STM32和GreenLoRaWAN通信协议的智能校园能源使用模式

IF 1.8 4区计算机科学

International Journal of Communication Systems Pub Date : 2025-10-07 DOI: 10.1002/dac.70262

Thirunavukkarasu K, Leo Raju

{"title":"Energy Usage Patterns in Smart Campus With STM32 and GreenLoRaWAN Communication Protocol-Based Temporal Attention Recurrent Graph Convolutional Neural Network on Edge Computing","authors":"Thirunavukkarasu K, Leo Raju","doi":"10.1002/dac.70262","DOIUrl":"https://doi.org/10.1002/dac.70262","url":null,"abstract":"<div>\u0000 \u0000 <p>An effective smart campus energy management strategy requires precise monitoring and prediction of energy consumption across different facilities, which can vary under occupancy and operational conditions. In this paper, Energy Usage Patterns in Smart Campus with STM32 and GreenLoRaWAN Communication Protocol based Temporal Attention Recurrent Graph Convolutional Neural Network on Edge Computing (SC-STM32-LWAN-TRCNN) is proposed. Here, the input data are gathered from the smart campus using the sensor node. To execute this, the energy usage and environmental parameters across the smart campus are monitored using STM32-based sensor nodes in edge computing. By using GreenLoRaWAN Communication Protocol (GLoRaNCP), the sensor nodes communicate with data wirelessly to the central gateway. Then, the input data are pre-processed using Multiple Local Particle Filter (MLPF) to reduce or remove the noise from the gathered input data. The pre-processed data are given into the Temporal Attention Recurrent Graph Convolutional Neural Network (TRCNN) for predicting the energy usage pattern from the smart campus. Finally, Shrike Optimization Algorithm (SOA) is employed to optimize the weight parameter of the TRCNN classifier that predicts the energy usage pattern precisely from the smart campus. The proposed SC-STM32-LWAN-TRCNN method is implemented and analyzed with the help of performance metrics, such as accuracy, mean absolute error (MAE), root-mean-squared error (RMSE), energy consumption, communication efficiency, throughput, and computation time. The performance of the SC-STM32-LWAN-TRCNN approach achieves 22.74%, 20.86%, and 30.67% higher accuracy and 25.19%, 17.54%, and 33.79% lower computation time compared with existing methods, respectively.</p>\u0000 </div>","PeriodicalId":13946,"journal":{"name":"International Journal of Communication Systems","volume":"38 16","pages":""},"PeriodicalIF":1.8,"publicationDate":"2025-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145272199","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Optimal Power Allocation and CAR in Multiuser Dual-Hop RF/FSO DF Relaying Systems With CDF-Based Scheduling 基于cdf调度的多用户双跳RF/FSO DF中继系统的最优功率分配和CAR

IF 1.8 4区计算机科学

International Journal of Communication Systems Pub Date : 2025-10-07 DOI: 10.1002/dac.70280

Rekha Rani, N. Jayanthi, Anup K. Mandpura

{"title":"Optimal Power Allocation and CAR in Multiuser Dual-Hop RF/FSO DF Relaying Systems With CDF-Based Scheduling","authors":"Rekha Rani, N. Jayanthi, Anup K. Mandpura","doi":"10.1002/dac.70280","DOIUrl":"https://doi.org/10.1002/dac.70280","url":null,"abstract":"<div>\u0000 \u0000 <p>A multiuser dual-hop RF-FSO decode-and-forward (DF) relaying system with co-channel interference (CCI) is considered. The RF channel undergoes Rayleigh fading, while the FSO channel is modeled by using Fisher-Snedecor, <i>ℱ</i> distribution. A cumulative distribution function (CDF)-based scheduling scheme is employed to effectively control the channel access ratio (CAR) and ensure fairness among users. We derive unified analytical and asymptotic expressions for the outage probability (OP), accounting for independent and non-identically distributed (i.n.i.d) CCI with varying power and channel gain across users, relay and interferers. The asymptotic expression facilitates optimal power allocation, CAR optimization and their joint optimization to minimize the OP. Monte Carlo simulations validate the accuracy of the derived expressions. Results demonstrate that the CDF-based scheduling system with optimized CAR outperforms proportional fairness scheduling (PFS) scheme and closely matches the performance of greedy scheduling (GS) scheme. Additionally, joint optimization of power allocation and CAR yields further improvements in outage performance compared to optimizing either power allocation or CAR alone. It is also noted that OP saturates at high SNR due to CCI.</p>\u0000 </div>","PeriodicalId":13946,"journal":{"name":"International Journal of Communication Systems","volume":"38 16","pages":""},"PeriodicalIF":1.8,"publicationDate":"2025-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145272198","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A Novel Approach for Fuzzy Logic–Based Clustering With Optimized Energy Efficient Routing in Internet of Things–Based Wireless Sensor Networks 物联网无线传感器网络中基于模糊逻辑的优化节能路由聚类新方法

IF 1.8 4区计算机科学

International Journal of Communication Systems Pub Date : 2025-10-06 DOI: 10.1002/dac.70269

S. R. Menaka, M. Prabu

{"title":"A Novel Approach for Fuzzy Logic–Based Clustering With Optimized Energy Efficient Routing in Internet of Things–Based Wireless Sensor Networks","authors":"S. R. Menaka, M. Prabu","doi":"10.1002/dac.70269","DOIUrl":"https://doi.org/10.1002/dac.70269","url":null,"abstract":"<div>\u0000 \u0000 <p>Modern wireless sensor networks (WSN) and the internet of things (IoT) have received a lot of attention lately due to the proliferation of smart mobile devices and connected devices. An autonomous sensor-equipped device is the primary component of the WSN-based IoT architecture due to its disruptive nature, enabling it to grow into an even greater range of dynamic and sophisticated applications that face even greater difficulties. WSN performance is significantly impacted by the energy resources of nodes. To solve this issue, the suggested study used a fuzzy-based hybrid optimization model for clustering and increased routing optimization. Cluster heads (CHs) are chosen for routing when WSNs deployed in an IoT context are initially clustered using Fuzzy Logic–Based Enhanced Gray Wolf Optimization (FL_eGWFO) techniques. In the second phase, packets from the IoT sensor nodes are received by a CH, forwarding them to the base station. The intercluster uses Levy Flight Based Improved Bald Eagle Search Optimization (Lf_IBESO) algorithms to find the best route from sources to the destination during routing. The goal function for choosing CH considers Euclidean distances, error rate, energy consumption, and packet delivery ratio (PDR). Factors such as the remaining energy and the separation between the base station (BS) and CH are assessed to determine the best route. The proposed model attained the end-to-end delay of 0.0796 ms, energy consumption of 4.294 j, network overhead of 1.71%, PDR of 0.98412%, and throughput of 158.6 kbps, respectively. The proposed model attained the best results by comparing with existing models.</p>\u0000 </div>","PeriodicalId":13946,"journal":{"name":"International Journal of Communication Systems","volume":"38 16","pages":""},"PeriodicalIF":1.8,"publicationDate":"2025-10-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145271763","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Miniaturization of a Multiband Pyramidal Antenna Using AMC Reflector for Satellite Applications 基于AMC反射镜的卫星多波段锥体天线小型化研究

IF 1.8 4区计算机科学

International Journal of Communication Systems Pub Date : 2025-10-04 DOI: 10.1002/dac.70281

Safia Chenaoui, Lila Mouffok, Sami Hebib, Pierre Lemaître Auger, Dahmane Allane, Smail Tedjini

{"title":"Miniaturization of a Multiband Pyramidal Antenna Using AMC Reflector for Satellite Applications","authors":"Safia Chenaoui, Lila Mouffok, Sami Hebib, Pierre Lemaître Auger, Dahmane Allane, Smail Tedjini","doi":"10.1002/dac.70281","DOIUrl":"https://doi.org/10.1002/dac.70281","url":null,"abstract":"<div>\u0000 \u0000 <p>In this paper, a modified trap-loaded pyramidal antenna backed by a triband artificial magnetic conductor (AMC) reflector of size 0.42 <i>λ</i><sub><i>L</i></sub> × 0.42 <i>λ</i><sub><i>L</i></sub> × 0.15 <i>λ</i><sub><i>L</i></sub> (where <i>λ</i><sub><i>L</i></sub> is the guided wavelength at the lowest frequency) is designed for satellite applications (GPS/Galileo/MicroSat). The triband AMC reflector, consisting of 3 × 3 unit cells, is proposed to miniaturize and further reduce the backward radiation of a conventional multiband pyramidal antenna, originally backed by a bulky metallic cutoff open-ended waveguide. Indeed, a significant reduction in the overall antenna size by 37%, 37%, and 67% along the <i>x</i>-, <i>y</i>-, and <i>z</i>-axes, respectively, has been achieved. A prototype of the proposed design has been manufactured, characterized, and compared with similar works reported in the literature. The antenna radiates circularly polarized electromagnetic fields with quasi-hemispherical radiation patterns at multiple operating frequencies, achieved through quadratic phase excitations of its four feeding ports. The suggested design exhibits measured peak right-handed circular polarization (RHCP) directivity levels of 5.12, 6.60, and 7 dB, along with significantly reduced backward radiation levels (LHCP directivity) of −8.06, −14, and −12.60 dB at the three measured operating frequencies: 1.20, 1.58, and 2.29 GHz, respectively. The proposed triband AMC-based pyramidal antenna is compact, lightweight, and easy to integrate, making it well-suited for satellite applications.</p>\u0000 </div>","PeriodicalId":13946,"journal":{"name":"International Journal of Communication Systems","volume":"38 16","pages":""},"PeriodicalIF":1.8,"publicationDate":"2025-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145224029","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A Proof of Resource Blockchain-Based Constitutive Recurrent Neural Network Model for Quality-Centric Resource Management in Wireless Sensor Networks 基于资源区块链的无线传感器网络质量中心资源管理本构递归神经网络模型证明

IF 1.8 4区计算机科学

International Journal of Communication Systems Pub Date : 2025-10-03 DOI: 10.1002/dac.70256

S. Muthukumarasamy, Tapas Bapu. B. R

{"title":"A Proof of Resource Blockchain-Based Constitutive Recurrent Neural Network Model for Quality-Centric Resource Management in Wireless Sensor Networks","authors":"S. Muthukumarasamy, Tapas Bapu. B. R","doi":"10.1002/dac.70256","DOIUrl":"https://doi.org/10.1002/dac.70256","url":null,"abstract":"<div>\u0000 \u0000 <p>Wireless sensor networks (WSNs) have gained significant attention in recent years owing to their important role in enhancing various daily life services, including military operations, healthcare, and social applications. Routing protocols often face challenges posed by malicious nodes that disrupt network performance. Therefore, a proof of resource blockchain-based constitutive recurrent neural network model for quality-centric resource management in wireless sensor networks (PRB-CRNN-QRWSN) is proposed in this paper. Here, the input data are collected from the WSN-DS dataset, ensuring a robust data foundation for analysis. The collected data are provided to an innovative framework that leverages a constitutive recurrent neural network (CRNN) to effectively detect malicious nodes in the network. Then the proof of resource (PoR) is used to securely register legitimate nodes. The proposed PRB-CRNN-QRWSN achieves better performance of 22.13%, 24.14%, and 21.07% lower delay and 22.13%, 24.14%, and 21.07% higher throughput when compared to the existing methods: blockchain-depend deep-learning-driven architecture for quality routing in WSN (BDL-AQR-WSN), blockchain-depend secure localization against malicious nodes in IoT-depend WSN utilizing federated learning (BSL-WSN-FL), and detection of denial-of-service attack in WSN: a lightweight machine learning approach (DDSA-WSN-LMLA), respectively.</p>\u0000 </div>","PeriodicalId":13946,"journal":{"name":"International Journal of Communication Systems","volume":"38 16","pages":""},"PeriodicalIF":1.8,"publicationDate":"2025-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145223970","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

DeepCuckoo: A Synergistic Approach Using Deep Learning and Bioinspired Cuckoo Search for Optimized Energy-Efficient Cluster Head Selection in 5G and Advanced Wireless Sensor Networks 深度杜鹃：在5G和先进无线传感器网络中使用深度学习和生物启发杜鹃搜索优化节能簇头选择的协同方法

IF 1.8 4区计算机科学

International Journal of Communication Systems Pub Date : 2025-10-03 DOI: 10.1002/dac.70242

Vijayakumar K, Thirumaraiselvan Packirisamy

{"title":"DeepCuckoo: A Synergistic Approach Using Deep Learning and Bioinspired Cuckoo Search for Optimized Energy-Efficient Cluster Head Selection in 5G and Advanced Wireless Sensor Networks","authors":"Vijayakumar K, Thirumaraiselvan Packirisamy","doi":"10.1002/dac.70242","DOIUrl":"https://doi.org/10.1002/dac.70242","url":null,"abstract":"<div>\u0000 \u0000 <p>The exponential growth of Internet of Things (IoT) devices has intensified the demand for efficient data transmission in wireless sensor networks (WSNs), particularly in 5G and beyond technology. This study introduces DeepCuckoo, a novel hybrid framework that synergizes deep learning with bioinspired optimization to enhance energy-efficient cluster head (CH) selection in WSNs. Leveraging deep belief networks (DBNs) for unsupervised clustering, the framework classifies sensor nodes based on energy levels and proximity. Concurrently, convolutional neural networks (CNNs) and recurrent neural networks (RNNs) dynamically evaluate residual energy, distance, and node capacity to optimize CH selection. Further refinement is achieved through the cuckoo search (CS) algorithm, which optimizes routing paths to minimize energy consumption and balance the network load. Simulation results demonstrate that DeepCuckoo achieves up to 55% energy savings, significantly outperforming existing methods such as EPOA-CHS and E-CERP. The framework also extends the network lifetime by 36% and reduces the latency by 50%, ensuring reliable data transmission in dynamic environments. By integrating adaptive learning with bioinspired optimization, this study advances the scalability and resilience of WSNs, offering a robust solution for future IoT ecosystems.</p>\u0000 </div>","PeriodicalId":13946,"journal":{"name":"International Journal of Communication Systems","volume":"38 16","pages":""},"PeriodicalIF":1.8,"publicationDate":"2025-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145223968","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0