An intelligent reflective surface (IRS)-assisted cognitive radio (CR) multiple-input multiple-output (MIMO) communication system is considered. Incorporating cognitive radio and IRS capabilities into such a system yields significant improvements in system performance, including energy efficiency (EE) and receiver quality of service (QoS). For enhancing the attainable rate of secondary users (SU) without exceeding the interference temperature limit (IT) on the primary users (PU), a non-convex optimization problem is formulated, which is usually solved by means of alternative optimization (AO) methods such as block coordinate descent (BCD) algorithms. In this paper, we focus on deep reinforcement learning (DRL) approaches, specifically, the soft actor-critic (SAC) algorithm, to solve this optimization problem. For comparison, all simulation figures will be composed of a BCD benchmark beside the SAC curves. In addition, a 16-element MIMO antenna array for the secondary transmitter (ST) base station is proposed, designed, fabricated, and tested, yielding a 90% radiation efficiency with perfect impedance matching and acceptable return losses.

The combination of cognitive radio (CR), full-duplex (FD) transmission, energy scavenging (ES), and non-orthogonal multiple access (NOMA) significantly improves spectral efficiency, spectrum utilization, and energy efficiency - key performance indicators in the development of future wireless communication infrastructures. However, the growing threat of eavesdropping necessitates robust physical-layer security mechanisms. The paper proposes NOMA CR networks with FD ES unlicensed transmitter (UT), referred to as NOEHwJ, to exploit primary interference as an energy source for UT's operation and a jamming source to secure UT's information. An in-depth evaluation of reliability and secrecy metrics for NOEHwJ is also presented. Through rigorous theoretical analysis and simulation, the study elucidates the impact of each enabling technology on secrecy capability. It is evident from the results that NOEHwJ delivers marked enhancements in security when compared to the benchmarked orthogonal multiple access (OMA) CR networks with FD ES UT (OEHwJ), thereby demonstrating the superior advantages of jointly employing CR, ES, NOMA, FD, and jamming techniques for the development of wireless communication architectures that are secure, energy-efficient, and adaptable to future demands.

The Mobile Reliable Opportunistic Routing (MROR) protocol improves data-forwarding reliability in Cognitive Radio Sensor Networks (CRSNs) through mobility-aware virtual contention groups and handover zoning. However, its heuristic decision logic is difficult to optimize under highly dynamic spectrum access and random node mobility. To address this limitation, we present DRL-MROR, a refined routing framework that incorporates deep reinforcement learning (DRL) to enable intelligent and adaptive forwarding decisions. In DRL-MROR, the secondary users (SUs) act as autonomous agents that observe local state information, including primary-user activity, link quality, residual energy, and neighbor-mobility patterns. Each agent learns a forwarding policy through a Deep Q-Network (DQN) optimized for long-term network utility in terms of throughput, delay, and energy efficiency. We formulate routing as a Markov Decision Process (MDP) and use experience replay with prioritized sampling to improve learning stability and convergence. The DQN used at each node is intentionally lightweight, requiring 5514 trainable parameters, about 21.5 kB of weight storage in 32-bit precision, and approximately 5.4k multiply-accumulate operations per inference, which supports practical deployment on edge-capable CRSN nodes. Extensive simulations show that DRL-MROR outperforms the original MROR protocol and representative AI-based routing baselines such as AIRoute under diverse operating conditions. The results indicate gains of up to 38% in throughput, 42% in goodput, a 29% reduction in energy consumed per packet, and an approximately 18% improvement in network lifetime, while maintaining high route stability and fairness. DRL-MROR also reduces control overhead by about 30% and average end-to-end delay by up to 32%, maintaining strong performance even under elevated PU activity and higher node mobility. These results show that augmenting opportunistic routing with lightweight DRL can substantially improve adaptability and efficiency in next-generation IoT-oriented CRSNs.

Unused channel sensing and allocation in Cognitive Radio Networks (CRN) are streamlined using guard intervals to enhance the Quality of Service (QoS) of secondary users (SUs). Identifying the guard interval succeeding unused channels is tedious due to multi-interference and asynchronous resource allocations. To address this problem, the article introduces a Multi-Objective Optimization Scheme (MOOS) using Partial-Order Transfer Learning (POTL). The objectives are defined as interference minimization, optimal power utilization, and maximum channel allocation. These objectives are satisfied by untying the allocated channels that are close and away from the guard interval. The guard interval without overlapping channels is identified to reduce the allocation failures by mitigating the asynchronous intervals. The partial order derivatives are responsible for verifying the asynchronous overlap between the guard and unused channel allocation intervals. From this estimation, the overlapping and non-overlapping intervals are distinguished to improve the allocation with optimal power utilization. The transfer learning opts for the selection of a precise unused channel that satisfies maximum QoS objectives during SU response intervals. The proposed optimization scheme improves the channel allocation rate by 10.13%, power utilization efficiency by 10.5%, and network throughput by 12.03% for the maximum number of secondary user variants considered.

The integration of Internet of Things (IoT) technologies into healthcare has transformed real-time monitoring and data communication. However, IoT-enabled Cognitive Radio Networks (CRNs) face persistent challenges such as high energy consumption, routing delays, and security risks. This paper proposes a novel Grey Wolf Optimization-based Multi-Adaptive Routing Protocol (GWO-MARP) that combines cluster-based routing with adaptive meta-heuristic intelligence. Unlike traditional cluster-based routing approaches that rely on static or energy-weighted selection, GWO-MARP dynamically determines cluster heads through a multi-objective fitness function that balances residual energy, lifetime, link quality, and security cost. The adaptive hunting behaviour of the GWO algorithm guides optimal path formation and ensures secure and energy-aware transmission, making the protocol distinct from existing methods. The proposed method is implemented and evaluated using MATLAB, and its performance is benchmarked against existing protocols including DA-EDC, MT-DQL, and SDL. Experimental results demonstrate significant improvements in throughput (44.30 kbps), end-to-end delay (1.175ms), packet delivery ratio (99.6%), and energy consumption (0.103J) for a network of 200 nodes. These outcomes validate the proposed protocol's capability to support robust, scalable, and energy-efficient data transmission in IoT-enabled healthcare networks.

Spectrum handoff upon collision detection is considered an insufficient mechanism in cognitive radio, motivating the development of spectrum occupancy prediction methods for radiocommunication systems. Prediction of transmission opportunities within the bandwidth of primary users represents a promising direction that requires novel approaches supported by advancements in Machine Learning (ML) and Deep Learning (DL). Beyond performance, DL model complexity and computational cost are key parameters, both during training and inference. While numerous modern architectures have been proposed for prediction tasks, a gap still exists between complex and efficient models. We propose a simple yet effective method using a Recurrent Neural Network (RNN), specifically Long Short-Term Memory (LSTM), where the input feature is directly represented as time differences between transmission events. Raw input signals are reduced and processed through a fast signal-processing path, allowing the LSTM to infer from an activity history buffer on demand. The model is implemented using the standard toolset with the Keras framework. The proposed approach is evaluated using synthetic data simulating ON–OFF activity patterns, under assumptions tailored to a representative channel scenario. Results demonstrate that the time-differential LSTM approach can effectively predict and identify transmission window opportunities. LSTM provides learned immunity to the random nature of primary user activity, offering a tradeoff between model complexity and prediction capability.

The rapid development of 5G wireless communication networks, driven by the increasing demands of mobile internet and the Internet of Things (IoT), necessitates innovative solutions to meet stringent performance requirements. Non-Orthogonal Multiple Access (NOMA) has emerged as a promising technology to address these challenges by enabling efficient use of spectral resources through the sharing of resource blocks by multiple users. This survey comprehensively analyses various user pairing and power allocation strategies in NOMA, highlighting their effects on system capacity, spectral efficiency, and user fairness. Additionally, the integration of NOMA with advanced 5G technologies such as MIMO, cognitive radio, and cooperative communication is explored, addressing key challenges and potential solutions. The survey identifies significant research gaps, including the need for scalable user pairing algorithms, advanced power allocation methods, effective interference management, and robust security mechanisms. This review aims to provide insights into optimizing NOMA performance and guiding future research to enhance 5G networks.

The rapid expansion of internet of things (IoT) networks has intensified spectrum scarcity due to the massive growth in wireless device connectivity. Cognitive radio sensor networks (CRSNs) offer a promising solution by enabling dynamic access to underutilized spectrum bands. However, existing spectrum sensing techniques in CRSNs often suffer from high energy consumption, low adaptability, and limited prediction accuracy posing challenges in energy-constrained environments. This paper proposes an energy-efficient spectrum sensing (EESS) framework using an adaptive hybrid learning model (AHLM) that integrates wavelet transform-based signal decomposition (WT-SD), deep reinforcement learning (DRL), entropy-based hierarchical clustering (EHC), and meta-learning-based transfer learning (ML-TLM). WT-SD extracts key spectral features, while DRL with policy-gradient optimization dynamically predicts spectrum availability. The EHC mechanism clusters sensor nodes to minimize redundant sensing, and ML-TLM enhances adaptability with minimal retraining. The proposed model achieves substantial improvements over traditional methods. Experimental results show a 36% reduction in sensing time, 60% lower energy consumption than energy detection (ED) methods, and an 18.3% increase in network lifetime. The model also achieves a probability of detection of 0.998 and accuracy of 98.1%. These results confirm that the proposed EESS-AHLM framework provides a scalable and intelligent solution for energy-aware spectrum sensing in next-generation cognitive radio (CR)-IoT environments.

The rapid advancement of connected vehicle technologies has intensified the need for efficient spectrum utilization. Cognitive radio (CR) enables dynamic access to underutilized spectrum, with spectrum sensing playing a key role in detecting primary users (PU). This study introduces a novel spectrum sensing approach that integrates filter bank (FB) signal decomposition with convolutional neural networks (CNNs)—referred to as filter bank decomposition and convolutional neural network (FB-CNN)—to enhance detection performance compared to conventional methods. Unlike traditional techniques such as energy detection (ED), the proposed FB-CNN leverages the frequency components extracted by the FB as CNN inputs, enabling robust identification of PU signals across multiple modulation schemes, including BPSK, QAM, FSK, and GMSK. Simulation results demonstrate substantial gains, particularly in low-SNR scenarios: for example, at an SNR of 5 dB, FB-CNN achieves a detection probability of 89% for 2-FSK, compared to only 22% with ED—representing a fourfold improvement. These findings highlight the novelty and effectiveness of FB-CNN in significantly improving spectrum sensing reliability for connected vehicle networks operating in challenging signal environments.

Joint Beamforming and Active/Passive Reflecting Elements Allocation for Hybrid Intelligent Reflecting Surface-Assisted Energy Harvesting Cognitive Radio Sensor Networks

This paper proposes a new deep learning estimation algorithm of spectrum sensing and channel estimation in Cognitive Radio Sensor Networks (CRSNs) using Non-Orthogonal Multiple Access (NOMA). The given model will combine Long Short-Term Memory (LSTM) Networks with Bayesian Neural Networks (BNNs) to improve the work of the system in dynamic and unpredictable wireless conditions. The LSTM networks are used to predict with accuracy complex-valued Rayleigh Fading Channels and Bayesian is used to model the uncertainty with which such predictions are made. Also, a parallel Bayesian LSTM spectrum sensing model classifies activity of primary users (PU) to provide intelligent spectrum access and reduce interference. Prediction and spectrum sensing: Prediction and spectrum sensing is possible with the model in real-time and this is important in efficient spectrum management in CRSN where the Mean Absolute Error (MAE) of channel estimation is brought to under 0.02, implying high accuracy of channel condition prediction. Results of simulation demonstrate a significant enhancement when compared with traditional systems. The maximum accuracy of the spectrum sensing in the model is 98% at Signal to Noise Ratio of 10 dB and also a low Bit Error Rate (BER). LSTM combined with Bayesian inference structuring enables a combination of accurate channel estimation and trusted spectrum sensing, which are significant in terms of accuracy and the quantification of the uncertainties. These findings indicate the possibility of the proposed Bayesian-enhanced LSTM model to enhance the CRSN performance, especially in a low SNR and high-interference environment. This method is superior to the traditional models, which is a guarantee of the stable communication and spectrum utilization in the complicated wireless settings.

Cognitive Radio Networks (CRNs) form the basis of an interesting approach to ease the ongoing shortage of spectral resources. Through allowing Secondary Users (SUs) to opportunistically use underutilized frequency bands, including the integrity of Primary Users (PUs), CRNs represent a complex solution to the old spectrum quandary. This research paper outlines an independent, vibrant channel assignment model based on a 27-rule Mamdani fuzzy logic decision model. This framework cleverly coordinates channel selection after wise disposition of simulated network characteristics including Signal-to-Interference-plus-Noise Ratio (SINR), transmission power and the necessary channel capacity. In spectrum sensing, energy-detection approach is implemented to detect idle channels and assign a high-priority SUs to a stable interweave channel, and a low-priority SUs to a hybrid interweave-underlay approach reducing transmission power when the PU is active. The proposed system demonstrates adaptive responsiveness to varying conditions in the network by having a distributed decision making at the individual SU units. The empirical findings, in both simulation cases of various SU arrival conditions using MATLAB, indicate that the fuzzy-based allocation system can make significant improvements in throughput, reduce the service delay and drop rate, and increase the spectrum utilization compared to the traditional CRN paradigms. Cognitive intelligence combined with fuzzy decision-making, therefore, is envisaged to autonomies, scale, and provide effective spectrum management in heterogeneous Internet of Things (IoT) communications.

ABSTRACT These days, wireless communication is facing the problems of short battery lifetime and lower capacity globally for Beyond 5G (B5G) communication. These problems can be addressed by proposing the advantages of nonorthogonal multiple access (NOMA)–based cooperative green cognitive radio networks (GCRNs) utilizing green secondary users (GSUs) as relays. For this, an auction market is designed with the composition of BS (auctioneer), GSUs (sellers), and PUs (buyers). The PUs must pay for the cooperative service provided by GSUs, while GSUs sell it for revenue. Moreover, PUs can adjust their bid according to their residual energy. Thus, less energy PUs have a higher chance of winning GSUs' service to prevent energy exhaustion. Meanwhile, GSUs reduce their ask price as per the amount of energy harvesting (EH). Hence, GSUs can serve more PUs if they harvest more energy from the received NOMA signal. Three auction rules impacting GSUs (as relay) selection are also being proposed. Finally, the simulation illustrates the diverse performance of three auction rules (with their merits and demerits) in selecting GSUs. Although all of them effectively enhance system capacity and extend the battery lifetime of PUs, with 0.01% battery energy consumption noticed in each second while transmitting 10 GB of data from the BS to the PUs.

ABSTRACT In recent years, Vehicular Ad Hoc Networks (VANETs) have emerged as crucial enablers of technology for intelligent vehicular transport systems. The VANETs, which primarily operate in the dedicated 5.9‐GHz band have suffered from severe congestion due to rapidly growing users and also due to interference from other wireless devices, thereby limiting its overall performance under both static and mobility conditions. To circumvent this challenge, Cognitive Radio (CR) technology is employed in VANETs by adopting the concept of opportunistic licensed spectrum access, leading to an improvement in sensing reliability under high‐mobility and fast fading conditions. This article proposes a Whale Optimization Algorithm (WOA)‐optimized Adaptive Switching Spectrum Sensing (ASSS) method subject to road segmentation, whose performance is compared with other baseline CSS ED‐based methods. The simulation results show that the proposed method with segmentation, under static and mobility conditions, has an enhanced detection probability with reduced computational complexity in terms of lower convergence time and higher RSU residual energy compared to the case of without segmentation and other baseline methods. Under the static case, in terms of detection probability, the proposed method shows a ~3% marginal improvement over CSS ED + WOA, ~11% improvement over CSS ED + Bayesian, and ~40% improvement over CSS ED w/o Bayesian methods. Similarly, under poor channel and dynamic vehicular mobility (0‐kmph) conditions, the proposed ASSS + WOA method undergoes a reduction in detection probability of only ~19.88% compared to the other baseline CSS ED method of WOA, Bayesian, and w/o Bayesian approaches, respectively.

The rapid growth of wireless communication systems and devices has increased global energy consumption in wireless communication networks. Therefore, wireless communication technologies are advancing towards the development of fifth-generation wireless communication systems and beyond, i.e., towards the development of sixth-generation wireless communication systems. It is important that the energy efficiency of wireless communication systems considered a significant parameter along with data rate, delay and reliability. Green wireless communication systems aim to reduce the power consumption of wireless communication systems minimize carbon emissions and make wireless communication systems environmentally sustainable. This paper presents a comprehensive review of sustainable wireless communication systems and energy-efficient protocols for green wireless communication systems. This study discusses various architectural strategies such as energy-efficient base stations, heterogeneous and ultra-dense networks, cloud radio access networks, adaptive networks, renewable energy and their role enables wireless networks to modify their behavior according to the nature of the data and availability of resources. Further, the paper discusses the role of sustainable wireless protocols in all layers of wireless communication, where techniques like power control, duty cycle, energy-efficient routing and transport protocols are playing a significant role in removing the unnecessary communication and utilizing resources efficiently. It also discusses enabling technologies that can be utilized in energy-efficient network operation including energy harvesting, cognitive radio, artificial intelligence, edge computing and network virtualization. Moreover, some of the major challenges in energy-efficient wireless communication including decisions, complexity, security, cost, and regulatory issues, are addressed. This study provides an sustainable wireless communication can be achieved based on recent developments and existing research gaps in wireless communication particularly in future 5G and 6G networks.

ABSTRACT Cognitive radio for vehicular ad hoc networks (CR-VANET) plays a key role in managing the spectrum dynamically and provides data communication in smart transportation. However, the security aspect is threatened by Sybil attacks where the adversary creates multiple fake identities in the network to hinder performance, damage topology, and mount denial of service attacks. To address these challenges, we present Vision-Augmented Split-Attention Neural Architectures for Sybil Resilience via Chaos-Driven Secure Elliptic Key Synthesis to Assured Data Exchange in CR-VANETs (Fuzz-CViAt_DuBe), a new approach. The proposed comprises of (i) Cluster Head selection with the Sooty Tern Maximizer for efficient communication; (ii) Sybil attack detection using Convolutional Neural Networks Augmented by Vision Transformers with split attention enhanced by the Dung Beetle Adaptive Optimizer; and (iii) Cryptographic security with the Fuzz-Resilient Chaotic Elliptic Curve Cryptographic Infrastructure. In simulations it is seen that there is a very much enhancement in the network performance. The proposed system increases the packet delivery ratio by 97.4%, improves throughput by 95.8%, and reduces latency by 88.3%. Additionally, the security rate is enhanced by 98.5%, while encryption time for 100KB of data is reduced to 15.2 s, demonstrating its superior performance over existing models. These findings highlight the benefits of the Fuzz-CViAt_DuBe framework in protecting CR-VANETs against Sybil attacks and enabling safe communication, providing solid grounds for improved future intelligent transportation systems.

Global Navigation Satellite Systems (GNSS) are highly affected in equatorial regions, especially due to the formation of Equatorial Plasma Bubbles (EPBs), which cause disturbances in the ionosphere resulting in different forms of signal degradation. Despite Colombia's privileged geographic position, its limited monitoring infrastructure hinders the detection and mitigation of these effects. This study proposes the development of a Low-Cost Scintillation Laboratory (LCSL) using a cognitive radio-based approach for real-time scintillation monitoring, aimed at improving GNSS reliability. The system was designed following a Systems Engineering methodology, defining functional architectures and constraints. A communication system model was developed to account for EPBs' effects on GNSS signals, while cognitive radio algorithms within a Software-Defined Radio (SDR) framework enabled real-time detection, monitoring, and alert generation. To implement this approach, monitoring stations were deployed in Bogotá, Cartagena, and Santa Marta utilized low-cost GNSS receivers integrated with Machine Learning (ML) algorithms for the automatic classification of scintillation events. Additionally, the system's accuracy was validated by comparing experimental data with historical records from the Geophysical Institute of Peru (IGP). The results demonstrated that the integration of cognitive radio and ML-based detection enhanced precision and adaptability compared to traditional methods. The network of monitoring stations effectively validated the system's performance, providing valuable insights into equatorial ionospheric dynamics. This study contributes to the advancement of monitoring methodologies and highlights the importance of accessible infrastructure for mitigating EPB effects on GNSS, ultimately fostering more resilient navigation and communication systems.

Retraction Note: Secure Distance Based Improved Leach Routing to Prevent Puea in Cognitive Radio Network

Cognitive Radio Networks (CRNs) are essential for improving spectrum efficiency in 5G and beyond; however, their open and adaptive nature makes them highly vulnerable to jamming attacks. The purpose of this work is to develop an anti-jamming framework that jointly addresses jammer detection and frequency selection under adversarial conditions. The novelty of this work lies in jointly addressing strategic anti-jamming decision-making and data-driven jammer detection within a single unified framework. Motivated by the limitations of standalone game-theoretic, evolutionary, and deep learning approaches in dynamic adversarial environments, we propose a hybrid anti-jamming framework that integrates game theory, deep learning, and particle swarm optimization (PSO). Game theory is employed to model the strategic interaction between secondary users and jammers, enabling utility-aware frequency hopping (FH) decisions, while a PSO-driven deep neural network (DNN), termed DeepSwarm, is designed for accurate and robust jammer detection. The strength lies in leveraging PSO to enhance the convergence speed and robustness of the DNN in dynamic jamming environments. Simulation results demonstrate that DeepSwarm achieves 98.10% accuracy, 98.30% recall, 98.10% precision, and a 98.05% F1-score, outperforming SVM, linear regression, and stacking baselines. Furthermore, FH guided by the proposed detection framework improves channel utilization and increases normalized throughput by up to 32% compared to static selection under varying jamming probabilities. These findings confirm the scalability and effectiveness of the proposed framework for securing CRNs in adversarial environments.

Probabilistic History-based distributed sensing protocol in cognitive radio networks