IET Communications最新文献

Integrated sensing and communication (ISAC) demonstrates significant advantages in spectrum and resource utilization compared to traditional communication and sensing coexistence systems. To further alleviate the scarcity of spectrum resources, non-orthogonal multiple access (NOMA), as a potential technology for 6G, is introduced into the ISAC system. Additionally, a transmit antenna selection scheme based on sensing priority and communication user fairness is proposed to further save hardware resources. As a further contribution, the multipath components induced by target reflection are captured and recombined to form constructive signal superposition, thereby further enhancing communication performance. The communication performance of the system proposed is investigated by deriving the exact and asymptotic outage probabilities (OPs), diversity gain, and ergodic communication rate (ECR) of users. Meanwhile, the sensing performance is analyzed in terms of probability of detection (PoD) and sensing rate (SR). Simulation results indicate that: (1) The proposed NOMA ISAC system outperforms the traditional OMA scheme in terms of both OP and PoD; (2) The full-duplex (FD) scheme sacrifices part of the outage performance in exchange for additional gains in ECR and SR.

Link prediction is a topic within the realm of graph theory. However, the majority of existing link prediction models are tailored for static graphs, disregarding the temporal evolution of graphs and the significance of global features during this process. Addressing the high dynamics and time-varying feature of unmanned aerial vehicle (UAV) network, traditional static graph methods encounter issues with the loss of network feature extraction information. By slicing the motion process of UAV nodes to form dynamic sequence graphs and designing sub-modules of structural attention and temporal attention, we characterize the spatial relationships within subgraphs of dynamic sequence graphs and the temporal relationships between subgraphs. We propose a dynamic link prediction method using dynamic graph neural networks, which possesses exchangeability and interpretability, capturing the temporal dimension features of the entire evolution process of the cluster dynamic network and characterizing the spatial relationships between nodes. A dataset of time-varying topologies for cluster networks is constructed, enabling link prediction under complex dynamic networks with time-varying conditions. Experimental results demonstrate that this method can accurately predict link relationships between nodes in time-varying complex UAV network topologies. Compared with traditional dynamic graph network models such as node2vec and GraphSAGE, this model achieves a link prediction accuracy of 88.79% on the RPGM dataset, surpassing node2vec's 70.24% and GraphSAGE's 62.81%.

RETRACTION: S. Sangeetha, T. A. A. Victoire, C. Kumar, and S. Barua, “Segment Routing for WSN Using Hybrid Optimisation With Energy Efficient Game Theory Based Clustering Technique,” IET Communications 19, no. 1 (2025): e70088, https://doi.org/10.1049/cmu2.70088.

The above article, published online on 15^th September 2025, in Wiley Online Library (wileyonlinelibrary.com) has been retracted by agreement between the journal's Editor-in-Chief, Jian Ren; the Institution of Engineering and Technology; and John Wiley and Sons Ltd.

Since publication, it has come to our attention that there is substantial text overlap with a previously published article [1].

The authors were asked to clarify the overlap and the similarity of the article title. They have responded but have not addressed the concerns adequately. Accordingly, the article is retracted. The authors have been informed of the decision, and C. Kumar disagrees with the retraction. The other authors have not responded.

Reference

1. S. Sangeetha, T. A. A. Victoire,M. Premkumar, and R. Sowmya, “Segment Routing for WSN Using Hybrid Optimization With Energy-Efficient Game Theory-Based Clustering Technique,” Automatika 66, no. 1 (2024): 24–42, https://doi.org/10.1080/00051144.2024.2431750.

In the originally published article [1], an error occurred in Table 1. Due to an oversight, for most of the rows (all except the third row, ‘intra-cabin and intra-flight deck’), the data values for the columns ‘C_0(dB)’, ‘a_0(dist. exp.),’ and ‘b_0(freq. exp.)’ were incorrectly shifted. The value for ‘C_0(dB)’ was mistakenly placed in the last column (b_0(freq. exp.)), and the values for ‘a_0(dist. exp.)’ and ‘b_0(freq. exp.)’ were shifted one column to the left (into the C_0(dB) and a_0(dist. exp.) columns, respectively).

The corrected Table 1 should read as follows:

We apologize for this error.

To address mutual interference caused by frequency conflicts among equipment in multi-platform formations, a novel time-frequency-polarisation multi-domain electromagnetic resource allocation (EMRA) method is proposed in this paper. Unlike traditional allocation methods, which are limited to the single frequency domain, a significant advancement is achieved by expanding EMRA to three domains: time, frequency and polarisation, enabling comprehensive coordination of electromagnetic resources. The equipment's operating time is divided into time units, an objective function and constraints reflecting interference levels at various time points are created, and the optimal allocation scheme is searched for using a multi-domain particle swarm optimisation (PSO) algorithm, which effectively leverages the expanded domains. Simulations on ship and ship-aircraft formations show that complete interference elimination is achieved with ≤12% time overhead and ≤7% memory increase. For ship formations, the multi-domain algorithm runs in 214 s (2625.2 MB) compared to 192 s (2514.2 MB) for frequency-domain PSO, converging to zero interference in 4 iterations, far outperforming the 21 iterations required by time-frequency PSO and the stagnant interference (>200) of frequency-domain PSO after 7 iterations; for ship-aircraft formations, it runs in 294 s (2834.4 MB) versus 267 s (2713.6 MB) for frequency-domain PSO, with similarly superior convergence. Theoretical and practical solutions for formation electromagnetic interference are provided by this work, with the efficacy of the multi-domain approach validated.

The integration of artificial intelligence (AI) into 5G network slicing is essential for overcoming limitations in autonomous management and precise resource allocation in complex network environments. Traditional methods struggle with dynamic adaptability, often requiring manual intervention and lacking scalability. This research leverages AI models, specifically logistic regression and long short-term memory (LSTM) to automate and optimise real time slice allocation. During testing across various values of the regularisation parameter (alpha), the models achieved classification accuracy up to 95% at alpha = 0.1 and maintained over 65% at higher values, demonstrating robustness. We also implement dynamic programming of segment routing over IPv6 (SRv6) Identifiers, enabling accurate differentiation of up to 40,000 enhanced mobile broadband (eMBB) slices, as well as ultra-reliable low-latency communication (URLLC) and massive machine type communications (mMTC) types. An adaptive application programming interface (API) based framework further adjusts SRv6 traffic engineering (SRv6 TE) policies in real time, ensuring uninterrupted service. High receiver operating characteristic-area under the curve (ROC AUC) scores, reaching 0.99, validate the model's strong classification performance. This approach advances automated 5G slicing by enhancing responsiveness, scalability and service quality.

The universal filter multi carrier (UFMC) is one of the most popular applications for beyond the fifth generation (B5G) radio framework owing to its numerous recompenses such as high-speed access, low latency, and small filter size. However, a high peak-to-average power ratio (PAPR) is a severe concern when deploying UFMC for B5G systems. The amplitude fluctuation introduces a nonlinear distortion that degrades the power amplifier (PA) efficiency in the UFMC structure. In this study, a hybrid algorithm consisting of selective mapping (SLM), partial transmission (PTS), and a recurrent neural network (RNN), also known as SLM+PTS+RNN, was used. The proposed method uses different algorithms to optimize the PAPR performance of the framework. Constraints such as the PAPR, bit error rate (BER), and power spectral density (PSD) were estimated and analyzed. The outcome of the experimental results reveals that the proposed SLM+PTS+RNN outperforms the conventional SLM, PTS, A-Law, and Mu-Law by obtaining a power-saving performance of 30%–40% while preserving the BER and PSD performance of the framework.

Vehicular ad hoc networks (VANETs) have a dynamic topology. This nature makes them highly susceptible to security attacks. It also leads to ineffective data delivery. In solving this, we introduce PPCMV-BLOCK, a new framework, which combines information-centric networking (ICN) with Blockchain to create a secure and trusted content exchange framework. Our approach uses a content security policy (CSP) for encrypted transmission. It employs an authenticate vehicle data (AVD) algorithm for integrity. It also uses a support vector machine (SVM) model for malicious node detection. The SVM achieves 91.3% accuracy, 92.4% precision, and a 93.6% F-score. Comparisons with benchmarks show significant performance gains. Our method shows a 10% increase in bandwidth usage and a 13% increase in throughput. It also achieves 9% better network content usage and 14% faster content delivery. These improvements persist even under attack. These findings decisively confirm the high-performance and robustness of PPCMV-BLOCK on IoT-based VANETs.

Automatic modulation recognition enables rapid spectrum access and serves as a key technical component for achieving communication-aware integration. In recent years, deep learning methods have attracted considerable attention in this field. However, their performance relies heavily on the availability of large-scale datasets. Data augmentation has proven effective in mitigating data scarcity. To address this challenge, this paper proposes a data augmentation algorithm based on a conditional diffusion model to improve model training under limited data conditions. In the proposed framework, the noise observation model detects noise in the input signal at different time steps. The identified noise is then iteratively removed during the reverse process of the conditional diffusion model to generate the corresponding modulated signals. Generated signals with high confidence are incorporated into the training set to enhance data diversity. Experimental results demonstrate that the proposed algorithm significantly improves the classification network's performance and outperforms existing data augmentation approaches.

The Internet of Things (IoT) has revolutionised the maintenance of parking systems. By incorporating IoT technology, parking systems can assist drivers in quickly locating appropriate parking spaces, alleviating traffic congestion, and minimising emissions from vehicles meandering in search of parking. This paper proposes a machine learning multilayer model that efficiently handles data generated by the sensors; it works at two layers to accurately predict appropriate parking spaces according to the vehicle type. Based on the survey conducted by the researchers, we use different models at different layers. At the first layer, an ensemble technique predicts the available parking spot; in the second layer, a random forest technique detects the type of vehicle. The integration of these techniques makes the proposed multilayer model novel, time-efficient, and cost-effective. These techniques are selected because they can handle complex data patterns, use the model's different strengths, and achieve high accuracy in prediction and classification tasks. The proposed multilayer model is implemented on the sensor dataset extracted from the Harvard Dataverse. The model is implemented using Python in a Jupyter notebook, and the evaluation metrics include accuracy, recall, precision, F1 score, and ROC curve. The proposed multilayer model obtained an accuracy of 97.88%, a precision of 96.11%, a recall of 95.69%, an F1 score of 96.04%, and an AUC score of 0.89. The results prove that the proposed multilayer model achieves the highest accuracy among all existing models in predicting the parking space with appropriate vehicle detection for the most effective parking space allocation in real-time scenarios.