International Journal of Communication Systems最新文献

{"title":"Tail-Latency-Aware Reinforcement Learning for Dynamic Resource Allocation in 5G Network Slicing","authors":"Mahalakshmi S,&nbsp;Markkandan S","doi":"10.1002/dac.70605","DOIUrl":"https://doi.org/10.1002/dac.70605","url":null,"abstract":"<div>\u0000 \u0000 <p>Network slicing is a fundamental technology in 5G and beyond networks, enabling multiple virtual networks to coexist over a shared physical infrastructure while supporting heterogeneous services with diverse quality-of-service (QoS) requirements. In this context, radio access network (RAN) slicing plays a critical role in allocating radio resource units to different service slices. A fundamental challenge in RAN slicing is the dynamic allocation of radio resources under fluctuating traffic demand and user mobility, where rare but severe tail-latency events corresponding to extreme delays experienced by a small fraction of packets have a dominant impact on performance, particularly for latency-critical ultrareliable low-latency communication (URLLC) services. Although reinforcement learning has been extensively studied for RAN slicing, most existing RAN-side approaches focus on optimizing average performance metrics and permit unconstrained exploration, which can result in instability and service-level agreement (SLA) violations in safety-critical scenarios. This paper proposes a tail-latency-aware proximal policy optimization (PPO) framework for dynamic multislice RAN resource allocation. The proposed approach integrates offline behavior cloning using ns-3-generated new radio (NR) traces with online policy refinement to enable continuous adaptation. The framework incorporates a slice-aware state representation capturing traffic and mobility dynamics, an explicit tail-latency penalty targeting the 95th-percentile URLLC delay, a URLLC-aware adaptive exploration mechanism, and an SLA-driven safety layer with emergency resource reallocation. System-level evaluations across three representative scenarios demonstrate that the proposed approach consistently outperforms baseline methods in overall SLA satisfaction and tail-latency control, achieving above 92% overall SLA compliance and maintaining balanced compliance across all service slice types, particularly during sudden traffic spikes.</p>\u0000 </div>","PeriodicalId":13946,"journal":{"name":"International Journal of Communication Systems","volume":"39 15","pages":""},"PeriodicalIF":1.8,"publicationDate":"2026-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148942816","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}

{"title":"Efficient Resource Management in 6G for Sustainable Spectrum Allocation Using Dual-Channel Temporal Convolutional Frequency-Separated Attention Network with Generation Rights Trading Blockchain","authors":"Manimaran Arjunan,&nbsp;Vivek Jain,&nbsp;Kalyan Kasturi,&nbsp;C. Kanmani Pappa","doi":"10.1002/dac.70603","DOIUrl":"https://doi.org/10.1002/dac.70603","url":null,"abstract":"<div>\u0000 \u0000 <p>The need for effective spectrum allocation to guarantee highly reliable, minimal-latency, and sustainable connections has increased due to the exponential expansion of wireless communications and the introduction of 6G technologies. In order to cope with these challenges, the proposed research is Efficient Resource Management in 6G to Sustainable Spectrum Allocation using a Dual-Channel Temporal Convolutional Frequency-Separated Attention Network with Generation Rights Trading Blockchain (ERMSA-6G). This objective is achieved by means of a layered network model that combines spectrum sensing, dynamic allocation and security. The Communication Layer is based on a Generation Rights Trading Blockchain (GRT-<span>BC</span>) with a smart contract algorithm to allocate resources transparently, and the Security Layer uses an Ultra-Lightweight Encryption Algorithm (ULwEA). This is improved by the use of the Dual-Channel Temporal Convolutional Network (DCTCN) of short- and long-term demand trends, and Frequency-Separated Attention Network (FSAN) of fine-tuning attention modeling, collectively to create the Dual-Channel Temporal Convolutional Frequency-Separated Attention Network (DCTCN-FSAN). Hyperparameters are further tuned using Cleaner Fish Optimization (CfO), and verified results are stored on GRT-<span>BC</span>. Experimental results demonstrate that ERMSA-6G achieves a 99.18% spectrum efficiency, 99.44% blockchain security, a 29.8-dB signal-to-interference-plus-noise ratio (SINR) margin, and an 85-ms consensus delay, while reducing transaction and servicing latency to 2060 ms. Its statistical tests prove that it is significantly better than the current techniques. To sum up, ERMSA-6G provides a secure, transparent, and sustainable framework of 6G spectrum allocation, which is more effective than the state-of-the-art techniques and guarantees scalability, reliability, and efficiency in future wireless networks.</p>\u0000 </div>","PeriodicalId":13946,"journal":{"name":"International Journal of Communication Systems","volume":"39 15","pages":""},"PeriodicalIF":1.8,"publicationDate":"2026-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148942354","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}

{"title":"Energy Aware Archery Northern Goshawk Optimization-Based Cluster Head Selection and Gt-LSTM for Weather Forecasting in WSN-IoT Network","authors":"S. Mathavi,&nbsp;N. Uma Maheshwari","doi":"10.1002/dac.70596","DOIUrl":"https://doi.org/10.1002/dac.70596","url":null,"abstract":"<div>\u0000 \u0000 <p>The distributed and resource-constrained nature of wireless sensor network–internet of things (WSN-IoT) nodes poses significant challenges for weather forecasting. Existing methods often struggle to balance prediction accuracy, energy efficiency, and network scalability. An efficient approach is presented in this research to resolve these issues through weather forecasting and cluster head (CH) selection. The selection of CHs is carried out using the Energy-Aware Archery Northern Goshawk Optimization (ANGO), a nature-inspired technique that replicates the predatory behavior of the Northern Goshawk. ANGO efficiently handles mobile nodes, maintains energy balance, and improves network longevity. A hybrid Gt-LSTM model, incorporating gated recurrent unit (GRU) and long short-term memory (LSTM) architectures, is employed at the WSN-IoT server for weather forecasting, allowing the extraction of both short-term fluctuations and long-term weather trends. Using ANGO for CH selection achieves a remaining energy of 58.855 J, maintains 89% of alive nodes, reaches a throughput of 47.869 Mbps, and results in an overall energy consumption of 55.569 J. Additionally, the Gt-LSTM technique for weather forecasting achieves a mean square error (MSE), root mean square error (RMSE), mean absolute error (MAPE), and accuracy of 0.219, 0.468, 0.328, 92.812%, respectively.</p>\u0000 </div>","PeriodicalId":13946,"journal":{"name":"International Journal of Communication Systems","volume":"39 15","pages":""},"PeriodicalIF":1.8,"publicationDate":"2026-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148942533","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}

{"title":"A Mechanism for Analyzing the Energy Consumption and Environmental Impact of LoRa Sensors Over Time","authors":"Vandirleya Barbosa,&nbsp;Melissa Alves,&nbsp;Iago Almeida,&nbsp;Iure Fé,&nbsp;Jean Araujo,&nbsp;Francisco Airton Silva","doi":"10.1002/dac.70602","DOIUrl":"https://doi.org/10.1002/dac.70602","url":null,"abstract":"&lt;p&gt;Long Range (LoRa) sensors are widely adopted in Internet of Things (IoT) applications due to their combination of long-range communication and low energy consumption. However, the continuous, large-scale operation of these devices raises concerns about cumulative energy consumption and environmental impacts over time. Evaluations based solely on prototypes and field tests tend to be costly, time-consuming, and poorly reproducible, hindering the systematic comparison of multiple operational scenarios. To address these challenges, this work proposes a mechanism for analyzing the energy consumption and environmental impact of LoRa sensors over time, focusing exclusively on the sensor node. The goal is to support sustainable planning of large-scale LoRa deployments by enabling the temporal evaluation of battery discharge, transmitted packets, and CO&lt;span&gt;&lt;/span&gt;&lt;math&gt;\u0000 &lt;semantics&gt;\u0000 &lt;mrow&gt;\u0000 &lt;msub&gt;\u0000 &lt;mrow&gt;&lt;/mrow&gt;\u0000 &lt;mrow&gt;\u0000 &lt;mn&gt;2&lt;/mn&gt;\u0000 &lt;/mrow&gt;\u0000 &lt;/msub&gt;\u0000 &lt;/mrow&gt;\u0000 &lt;annotation&gt;$$ {}_2 $$&lt;/annotation&gt;\u0000 &lt;/semantics&gt;&lt;/math&gt; emissions under different message generation rates and physical transmission parameters. The mechanism is developed using Stochastic Petri Nets (SPN), which model the alternation between the operating states of a LoRa sensor. Environmental impact is quantified by converting accumulated energy consumption into CO&lt;span&gt;&lt;/span&gt;&lt;math&gt;\u0000 &lt;semantics&gt;\u0000 &lt;mrow&gt;\u0000 &lt;msub&gt;\u0000 &lt;mrow&gt;&lt;/mrow&gt;\u0000 &lt;mrow&gt;\u0000 &lt;mn&gt;2&lt;/mn&gt;\u0000 &lt;/mrow&gt;\u0000 &lt;/msub&gt;\u0000 &lt;/mrow&gt;\u0000 &lt;annotation&gt;$$ {}_2 $$&lt;/annotation&gt;\u0000 &lt;/semantics&gt;&lt;/math&gt; emissions using a global average carbon emission factor. The SPN model is cross-validated against a discrete-event simulation implemented in NS-3. The cross-validation indicated close agreement between the SPN model and NS-3, with mean absolute percentage errors below 0.3% across all evaluated metrics. The packet generation rate is shown to govern both sensor lifetime and the temporal distribution of CO&lt;span&gt;&lt;/span&gt;&lt;math&gt;\u0000 &lt;semantics&gt;\u0000 &lt;mrow&gt;\u0000 &lt;msub&gt;\u0000 &lt;mrow&gt;&lt;/mrow&gt;\u0000 &lt;mrow&gt;\u0000 &lt;mn&gt;2&lt;/mn&gt;\u0000 &lt;/mrow&gt;\u0000 &lt;/msub&gt;\u0000 &lt;/mrow&gt;\u0000 &lt;annotation&gt;$$ {}_2 $$&lt;/annotation&gt;\u0000 &lt;/semantics&gt;&lt;/math&gt; emissions, with the per-packet carbon footprint increasing under low-traffic scenarios due to the higher share of idle consumption. The Spreading Factor (SF) exhibits a monotonic effect on energy consumption, per-packet CO&lt;span&gt;&lt;/span&gt;&lt;math&gt;\u0000 &lt;semantics&gt;\u0000 ","PeriodicalId":13946,"journal":{"name":"International Journal of Communication Systems","volume":"39 15","pages":""},"PeriodicalIF":1.8,"publicationDate":"2026-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/dac.70602","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148848956","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Circularly Polarized High Gain Antenna Design Using Slot-Notch Mechanism for Millimeter Wave 5G Applications","authors":"Mamoni Saha,&nbsp;Taimoor Khan,&nbsp;Daasari Surender,&nbsp;Fazal Ahmed Talukdar,&nbsp;Sembiam R. Rengarajan","doi":"10.1002/dac.70600","DOIUrl":"https://doi.org/10.1002/dac.70600","url":null,"abstract":"<div>\u0000 \u0000 <p>This study presents the development of a compact, broadband microstrip patch antenna operating at 32.6 GHz, tailored for fifth-generation (5G) millimeter-wave (mm-wave) communication systems. Designed on low-loss Rogers RO4003 (<i>ε</i>_r= 3.38, 0.8 mm), the structure ensures minimal dielectric loss and stable broadband performance. The radiating patch includes a central rectangular slot for bandwidth enhancement, upper-corner open-ended notches for current control and surface-mode suppression, and lower-edge rectangular stubs to improve impedance matching and polarization performance. The proposed design exhibits a resonant frequency centered at 32.6 GHz and delivers a measured impedance bandwidth of 1.5 GHz (31.7–33.2 GHz). At resonance, the antenna exhibits −24.8 dB reflection, indicating excellent matching. In terms of characteristics, the antenna achieves a peak gain of 7.2 dB at 32.6 GHz, making it suitable for directional transmission in compact communication modules. The proposed antenna supports circular polarization, reducing polarization mismatch and multipath fading. It achieves a 0.5 GHz 3-dB axial-ratio bandwidth (32.4–32.9 GHz), ensuring stable circular-polarization performance over a significant portion of the operating band. A prototype of the antenna was fabricated and tested, with the experimental results showing excellent agreement with simulated data, thereby confirming the design's viability for real-world mm-wave 5G applications.</p>\u0000 </div>","PeriodicalId":13946,"journal":{"name":"International Journal of Communication Systems","volume":"39 15","pages":""},"PeriodicalIF":1.8,"publicationDate":"2026-08-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148807772","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}

{"title":"A Low-Pilot-Overhead Two-Stage Channel Estimation Scheme for XL-RIS-Assisted Multi-User Terahertz Systems","authors":"Haiping Yang,&nbsp;Shitong Cheng,&nbsp;Ziyan Liu","doi":"10.1002/dac.70601","DOIUrl":"https://doi.org/10.1002/dac.70601","url":null,"abstract":"<div>\u0000 \u0000 <p>Accurate channel state information (CSI) is essential for exploiting terahertz communication and reconfigurable intelligent surfaces (RISs) in sixth-generation (6G) wireless systems. However, CSI acquisition in RIS-assisted terahertz systems requires prohibitive pilot overhead because the cascaded channel has high spatial degrees of freedom and the RIS contains a large number of passive reflecting elements. To address this challenge, we propose a low-pilot-overhead two-stage channel estimation scheme for RIS-assisted multi-user terahertz systems. In the first stage, a reliability-based rule selects a typical user, and a denoising network estimates its cascaded channel to extract the common BS-RIS channel information shared by different users. In the second stage, a single-link channel estimation algorithm estimates the channels of the remaining users by exploiting the correlation among users' cascaded channels. Specifically, only one RF link is activated to estimate the channel scaling factors between the typical user and the other users. A single-link denoising network is further designed to suppress scaling-factor errors and improve channel reconstruction accuracy. Simulation results show that the proposed scheme achieves higher channel estimation accuracy and spectral efficiency than benchmark methods while requiring fewer pilot symbols.</p>\u0000 </div>","PeriodicalId":13946,"journal":{"name":"International Journal of Communication Systems","volume":"39 15","pages":""},"PeriodicalIF":1.8,"publicationDate":"2026-08-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148807773","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}

{"title":"Four-Port Wideband Circularly Polarized MIMO Antenna Covering WLAN, WiMAX, and 5G NR n77/n78/n79 Bands","authors":"Sanjeev Kumar,&nbsp;Mahesh Kumar Singh,&nbsp;Sachin Kumar,&nbsp;Hala Mostafa","doi":"10.1002/dac.70604","DOIUrl":"https://doi.org/10.1002/dac.70604","url":null,"abstract":"<div>\u0000 \u0000 <p>This article describes a compact four-port multiple-input-multiple-output (MIMO) antenna that has a broad axial ratio bandwidth (ARBW) for use in WLAN/WiMAX/sub-6 GHz 5G bands: n77 (3.3–4.2 GHz), n78 (3.3–3.8 GHz), and n79 (4.7 GHz) (4.4–5 GHz). The radiating element of the MIMO antenna is a polygon, and a modified ground structure is used to achieve both size reduction and bandwidth enhancement. A folded microstrip line is incorporated at the center of the ground plane to achieve circular polarization. Furthermore, the circular polarization bandwidth is enhanced by using horizontal and vertical parasitic strips on the opposite side of the ground plane. The presented quad-port MIMO antenna utilizes interelement slots to reduce electromagnetic interference (mutual coupling) and improve directional gain. The antenna design is implemented on the 1.6 mm thick FR-4 dielectric substrate with a relative permittivity of 4.4, occupying a total area of 0.25<i>λ</i>₀ × 0.48<i>λ</i>₀. The projected design achieves a measured impedance bandwidth of 2.4–6.0 GHz. It demonstrates circular polarization characteristics with a measured 3-dB ARBW of 3.3–4.1 GHz. Exceptional diversity performance is confirmed by an isolation level exceeding 18 dB, an envelope correlation coefficient below 0.005, and a diversity gain greater than 9.95 dB. These metrics validate the antenna's suitability for sub-6 GHz 5G, WLAN, and dual-band ISM implementations.</p>\u0000 </div>","PeriodicalId":13946,"journal":{"name":"International Journal of Communication Systems","volume":"39 15","pages":""},"PeriodicalIF":1.8,"publicationDate":"2026-08-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148807774","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}

{"title":"A Novel Temporal Leakage Evaluation Framework for Vehicle-To-Infrastructure Network Traffic Prediction","authors":"Ishant Rustagi,&nbsp;Ajay Dureja,&nbsp;Rajiv Kumar Nehra","doi":"10.1002/dac.70599","DOIUrl":"https://doi.org/10.1002/dac.70599","url":null,"abstract":"&lt;div&gt;\u0000 \u0000 &lt;p&gt;Random train/test splitting is standard practice in V2I traffic prediction, yet it introduces a systematic flaw: When time-series data are highly autocorrelated, randomly assigned test samples share temporal neighbors with the training set, causing models to appear more accurate than they are in deployment. This paper quantifies that inflation. We derive a synthetic vehicle-to-infrastructure (V2I) traffic dataset from the PKDD-8 drone-trajectory corpus using a long-distance path loss model at 5.9 GHz and a speed-dependent SNR decay function, producing 1938 half-second bins across a 285-m expressway segment. Three architectures, LSTM (Long Short-Term Memory), BiLSTM-MHA (Bidirectional Long Short-Term Memory with Multi-Head Attention), and CNN-BiLSTM-MHA (Convolutional Neural Network–Bidirectional Long Short-Term Memory with Multi-Head Attention), are evaluated under two conditions: a conventional random split (EXP-1) and a strict chronological split (EXP-2). We introduce the leakage gap, &lt;span&gt;&lt;/span&gt;&lt;math&gt;\u0000 &lt;semantics&gt;\u0000 &lt;mrow&gt;\u0000 &lt;mo&gt;∆&lt;/mo&gt;\u0000 &lt;msup&gt;\u0000 &lt;mi&gt;R&lt;/mi&gt;\u0000 &lt;mn&gt;2&lt;/mn&gt;\u0000 &lt;/msup&gt;\u0000 &lt;/mrow&gt;\u0000 &lt;annotation&gt;$$ Delta {R}^2 $$&lt;/annotation&gt;\u0000 &lt;/semantics&gt;&lt;/math&gt; = &lt;span&gt;&lt;/span&gt;&lt;math&gt;\u0000 &lt;semantics&gt;\u0000 &lt;mrow&gt;\u0000 &lt;msup&gt;\u0000 &lt;mi&gt;R&lt;/mi&gt;\u0000 &lt;mn&gt;2&lt;/mn&gt;\u0000 &lt;/msup&gt;\u0000 &lt;/mrow&gt;\u0000 &lt;annotation&gt;$$ {R}^2 $$&lt;/annotation&gt;\u0000 &lt;/semantics&gt;&lt;/math&gt; (EXP-1) − &lt;span&gt;&lt;/span&gt;&lt;math&gt;\u0000 &lt;semantics&gt;\u0000 &lt;mrow&gt;\u0000 &lt;msup&gt;\u0000 &lt;mi&gt;R&lt;/mi&gt;\u0000 &lt;mn&gt;2&lt;/mn&gt;\u0000 &lt;/msup&gt;\u0000 &lt;/mrow&gt;\u0000 &lt;annotation&gt;$$ {R}^2 $$&lt;/annotation&gt;\u0000 &lt;/semantics&gt;&lt;/math&gt;(EXP-2), as a scalar diagnostic that can be computed from any pair of published &lt;span&gt;&lt;/span&gt;&lt;math&gt;\u0000 &lt;semantics&gt;\u0000 &lt;mrow&gt;\u0000 &lt;msup&gt;\u0000 &lt;mi&gt;R&lt;/mi&gt;\u0000 &lt;mn&gt;2&lt;/mn&gt;\u0000 &lt;/msup&gt;\u0000 &lt;/mrow&gt;\u0000 &lt;annotation&gt;$$ {R}^2 $$&lt;/annotation&gt;\u0000 &lt;/semantics&gt;&lt;/math&gt; values without rerunning experiments. Under strict chronological evaluation, the CNN-BiLSTM-MHA achieved the highest leakage-free accuracy (&lt;span&gt;&lt;/span&gt;&lt;math&gt;\u0000 &lt;semantics&gt;\u0000 &lt;mrow&gt;\u0000 &lt;msup&gt;\u0000 &lt;mi&gt;R&lt;/mi&gt;\u0000 &lt;mn&gt;2&lt;/mn&gt;\u0000 &lt;/msup&gt;\u0000 &lt;/mrow&gt;\u0000 &lt;annotation&gt;$$ {R}^2 $$&lt;/annotation&gt;\u0000 &lt;/semantics&gt;&lt;/math&gt; = 0.9558, five-seed mean) and the smallest leakage gap (&lt;span&gt;&lt;/span&gt;&lt;math&gt;\u0000 &lt;semantics&gt;\u0000 &lt;mrow&gt;\u0000 &lt;mi&gt;Δ&lt;/mi&gt;\u0000 &lt;msup&gt;\u0000 &lt;mi&gt;R&lt;/mi&gt;\u0000 &lt;mn&gt;2&lt;/mn&gt;\u0000 &lt;/msu","PeriodicalId":13946,"journal":{"name":"International Journal of Communication Systems","volume":"39 14","pages":""},"PeriodicalIF":1.8,"publicationDate":"2026-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148784988","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}

{"title":"An Integrated Consumer–Enterprise Federated Intelligence Framework With Post-Quantum Security for Healthcare IoMT","authors":"D. Dhinakaran,&nbsp;Chin-Shiuh Shieh","doi":"10.1002/dac.70597","DOIUrl":"https://doi.org/10.1002/dac.70597","url":null,"abstract":"<div>\u0000 \u0000 <p>This paper addresses the growing challenge of implementing secure, reliable, and scalable federated intelligence on consumer Internet of medical things (IoMT) devices and healthcare enterprise systems. Current solutions generally trade off individual aspects, for example, learning accuracy, cryptographic strength, and blockchain auditability, and do not present an end-to-end framework that ensures privacy preservation, adversarial robustness, post-quantum security, and enterprise governance. We address these shortcomings by introducing CeN-CHAIN, a consumer–enterprise integrated framework that incorporates post-quantum key distribution, homomorphic encryption with minimal computational overhead, differential privacy, blockchain-ensured validation, and federated model lifecycle management into a single architectural model. CeN-CHAIN enables on-device learning at a secure level, incorporating auditing, aggregability, and model custodianship in a heterogeneous IoMT and enterprise setting. Extensive experimental assessment based on evaluated healthcare IoMT dataset shows that CeN-CHAIN attains 96.1% global accuracy, 0.958 F1-score, and convergence in 22 rounds, which simultaneously minimizes the attack success rate (ASR) below 5% and a privacy leakage rate (PLR) below 3%. Although the framework includes sophisticated security levels, it has an approachable overhead, and the blockchain anchoring latency is 22–43 ms, energy usage of 2.15–6.15 J/FL round, and CPU usage of less than 77% in IoMT devices. These findings substantiate the claim that CeN-CHAIN provides a balanced trade-off between learning performance and integrated security under the evaluated healthcare IoMT experimental configuration.</p>\u0000 </div>","PeriodicalId":13946,"journal":{"name":"International Journal of Communication Systems","volume":"39 14","pages":""},"PeriodicalIF":1.8,"publicationDate":"2026-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148784445","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}

{"title":"A Lightweight CoDeV–HyPerion-T Deep Learning Framework for Threat Detection in Underwater Wireless Sensor Networks (UWSNs)","authors":"N. Dhanalakshmi,&nbsp;N. Babu,&nbsp;M. Anto Bennet,&nbsp;S. Pournima","doi":"10.1002/dac.70595","DOIUrl":"https://doi.org/10.1002/dac.70595","url":null,"abstract":"<div>\u0000 \u0000 <p>The use of underwater wireless sensor networks (UWSNs) has become a major security concern due to their increased use in environmental monitoring, military surveillance, and offshore applications. The networks are highly susceptible to various cyber threats due to their dynamic topology, limited energy resources, and unreliable communication networks. The existing intrusion detection techniques tend to exhibit low detection rates, high false alarms, and high complexity, making them inapplicable to real-time and resource-constrained UWSN systems. Moreover, many conventional and deep learning-based models cannot effectively model feature interactions and emerging attack patterns in heterogeneous IoTs and underwater environments. To address these weaknesses, this paper presents a new hybrid intrusion detection model, which integrates CoDeV based feature extraction algorithm and the HyPerion-T model. To capture both the spatial and temporal characteristics of network traffic and leverage a transformer-based structure to enhance intrusion detection by exploiting adaptive attention, the article presented here was based on sophisticated feature description and dependency modeling. These combinations will ensure greater accuracy, strength, and efficiency in the calculations. The results of the proposed methodology are tested on the benchmark datasets, i.e., WSN-DS, IoT-23, and N-BaIoT. Among all models, CoDeV+HyPerion-T has reached the highest average accuracy (98.96%) with an accuracy of more than 98% and recall of more than 98% and also achieved the lowest average inference time (9.5 ms), demonstrating great real-time performance. The inference energy is also measured to be 3.42 mJ for per inference, achieving up to 50.1% energy reduction compared with basis approach models.</p>\u0000 </div>","PeriodicalId":13946,"journal":{"name":"International Journal of Communication Systems","volume":"39 14","pages":""},"PeriodicalIF":1.8,"publicationDate":"2026-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148784824","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}