Orthogonal time-frequency space modulation combined with multiple-input multiple-output transmission (MIMO-OTFS) has emerged as a strong waveform candidate for sixth-generation (6G) wireless networks because of its robustness against high mobility and doubly selective channels. However, reliable signal detection in large-scale MIMO-OTFS systems remains challenging owing to severe delay-Doppler coupling and channel state information (CSI), particularly under Rayleigh and Rician fading conditions. This paper proposes a residual-learning minimum mean square error neural detector (RL-MMSE-ND) to address these challenges under both perfect and imperfect CSI, including scenarios with up to a 20% channel estimation error. The proposed detector integrates a conventional minimum mean square error (MMSE) front-end with a lightweight residual-learning neural network that learns only the residual interference caused by CSI mismatch and delay-Doppler effects, thereby preserving MMSE stability while introducing minimal learning overhead. Extensive simulations were conducted for representative large-scale MIMO-OTFS configurations to evaluate the bit error rate (BER) versus signal-to-noise ratio (SNR), BER versus delay spread, power spectral density (PSD) characteristics, inference latency, and training convergence. Numerical results demonstrate that the proposed RL-MMSE-ND achieves 10-13 dB SNR gain at a BER of 10-3 compared to zero-forcing equalization and MMSE detectors, while requiring 3-6 dB lower SNR than the maximum likelihood, QR decomposition-based M-algorithm detection, and deep learning-based detectors under both Rayleigh and Rician fading. Moreover, the proposed method reduces inference latency by over 60% compared to long short-term memory and bidirectional long short-term memory detectors and achieves 5-8 dB lower out-of-band emissions while adding only linear computational overhead beyond MMSE detection. These results confirmed the novelty and practical significance of the proposed approach for robust, low-latency, and low-complexity MIMO-OTFS detection in future 6G wireless systems.

Abstract This paper investigates the reduction of Peak-to-Average Power Ratio (PAPR) in Optical Non-Orthogonal Multiple Access (O-NOMA) based Visible Light Communication (VLC) systems for beyond fifth generation (B5G) wireless applications. High PAPR is a major challenge in O-NOMA systems because it increases signal distortion and reduces the efficiency of optical transmitters. To address this issue, a deep learning assisted optimization technique based on Recurrent Neural Network–Partial Transmit Sequence (RNN-PTS) is proposed. The performance of the proposed approach is evaluated using Complementary Cumulative Distribution Function (CCDF) analysis for 256, 512, and 1,024 sub-carriers and compared with conventional techniques such as Clipping, Selective Mapping (SLM), Partial Transmit Sequence (PTS), Genetic Algorithm-PTS (GA-PTS), and Particle Swarm Optimization-PTS (PTS-PSO). Simulation results show that the proposed RNN-PTS method significantly reduces PAPR, achieving approximately 4.5 dB, 5.8 dB, and 6.0 dB at a CCDF of 10 −3 for 256, 512, and 1,024 sub-carriers, respectively. Furthermore, Bit Error Rate (BER) analysis demonstrates improved communication reliability with lower Signal-to-Noise Ratio (SNR) requirements. Power Spectral Density (PSD) analysis also confirms better spectral containment and reduced out-of-band radiation. Overall, the proposed RNN-PTS approach improves power efficiency, spectral efficiency, and transmission reliability in O-NOMA based VLC systems.

Orthogonal Time Sequence Multiplexing (OTSM) has emerged as a promising waveform candidate for sixth-generation (6G) wireless systems due to its robustness against high mobility, Doppler dispersion, and time-varying channel conditions, while maintaining low receiver complexity. However, similar to other multicarrier-derived waveforms, OTSM suffers from a high peak-to-average power ratio (PAPR), which degrades power amplifier efficiency and system reliability. This letter proposes a novel Learning-Assisted Probabilistic Precoding (LA-PP) framework to address the PAPR issue in OTSM systems. The proposed LA-PP exploits learned OTSM-specific peak-sensitive signal statistics to guide probabilistic precoding, distinguishing it from conventional PAPR reduction techniques such as selective mapping (SLM), partial transmit sequences (PTS), and optimization-based approaches. Consequently, LA-PP avoids exhaustive search procedures and the need for side information. An OTSM-aware peak cost function is formulated to capture the sequency-domain phase alignment effects responsible for peak formation. Simulation results demonstrate that LA-PP achieves significant PAPR reduction across various subcarrier configurations, providing up to an 8 dB reduction compared to baseline OTSM. In addition, LA-PP improves bit error rate (BER) performance over Rayleigh fading channels. The proposed scheme preserves the standard OTSM signal structure and introduces no additional online computational complexity, making it a practical and efficient solution for real-time, high-mobility 6G communication scenarios.

Reliable spectrum sensing is a key requirement for cognitive radio (CR) networks; however, its performance is significantly degraded by fading, noise uncertainty, and channel estimation errors. This paper proposes a hybrid gated recurrent unit–long short‐term memory–convolutional neural network (GRU–LSTM–CNN) framework for cooperative spectrum sensing (CSS) that integrates spatial–spectral feature extraction with long‐ and short‐term temporal learning to improve primary user detection. The proposed framework incorporates a reliability‐aware cooperative fusion mechanism in which secondary users (SUs) transmit soft sensing reports together with predictive uncertainty, enabling adaptive weighting based on signal quality and decision reliability. Extensive simulations under additive white Gaussian noise (AWGN), Rayleigh, and Rician fading channels demonstrate that the proposed method consistently outperforms conventional energy detection (ED), matched filter (MF), long short‐term memory (LSTM), convolutional neural network (CNN), and LSTM–CNN models. The proposed framework achieves a probability of detection (Pd) approaching 1 at a signal‐to‐noise ratio of −4 dB, provides improvement in bit error rate (BER) performance over conventional methods, significantly reduces the probability of false alarm (Pfa), achieves the lowest power spectral density (PSD), and maintains robust sensing performance under 15% and 25% channel estimation errors. These results demonstrate that the proposed GRU–LSTM–CNN framework delivers accurate, robust, and reliable CSS, making it a promising solution for next‐generation internet of things (IoT)‐enabled and sixth‐generation (6G) wireless communication systems.

In the rapidly evolving landscape of beyond 5G (B5G) networks, ensuring robust security is paramount due to the increased complexity and heterogeneity of network architectures. This article presents a comprehensive security analysis using a Bi-LSTM-based intelligent deep learning method to address the emerging security challenges in B5G networks. Leveraging the bidirectional long short-term memory (Bi-LSTM) architecture, our approach effectively captures temporal dependencies and context from sequential data, enhancing the detection and mitigation of sophisticated cyber threats. The proposed method integrates feature extraction and classification into a unified framework, facilitating real-time analysis of the throughput of the framework. By analyzing various parameters such as bit error rate (BER), peak power and power spectral density (PSD), the projected Bi-LSTM model demonstrates superior performance compared to traditional. The study further explores the limitation and adaptability of the Bi-LSTM approach across diverse network scenarios, including ultra-dense networks and massive IoT deployments. Our findings underscore the critical role of advanced deep learning models in fortifying B5G networks, highlighting their potential to evolve in tandem with future network advancements.

Optical orthogonal frequency division multiplexing (Optical OFDM) is a key modulation technique for high-speed optical communication systems; however, its performance is significantly degraded by chromatic dispersion and phase noise, which impair subcarrier orthogonality and introduce inter-symbol and inter-carrier interference. To overcome these limitations, this work proposes an enhanced signal detection scheme for optical OFDM based on a hybrid equalization framework integrated with quasi-reduced maximum likelihood detection (QRM-MLD). The proposed approach is evaluated against conventional detection methods, including zero-forcing equalization, minimum mean square error, maximum likelihood, and successive interference cancellation. MATLAB-based simulation results demonstrate that the hybrid QRM-MLD scheme achieves substantial performance gains under various channel impairment conditions. At a target bit error rate of 10 −3 , the proposed method requires up to 10 dB lower signal-to-noise ratio compared to uncompensated optical OFDM and offers approximately 2–7 dB improvement over conventional detection schemes. Capacity analysis further confirms its superiority, achieving a value of 290 at an SNR of 50 dB. Overall, the proposed hybrid detection strategy significantly improves detection accuracy, spectral efficiency, and robustness, making it a strong candidate for next-generation high-capacity optical OFDM communication systems.

Non-Orthogonal Multiple Access (NOMA) is a key enabling technology for beyond fifth-generation (B5G) and sixth-generation (6G) wireless communication systems due to its high spectral efficiency and massive connectivity capabilities. However, the superposition of multiple user signals results in a high Peak-to-Average Power Ratio (PAPR), which degrades power amplifier efficiency, increases spectral leakage, and adversely affects system performance. To address this challenge, this paper proposes a low-complexity hybrid framework that integrates Invasive Weed Optimization (IWO) with Selective Mapping (SLM) and Partial Transmit Sequence (PTS) techniques for effective PAPR reduction in NOMA systems operating over Rayleigh and Rician fading channels. The IWO algorithm is employed to optimize phase sequences and phase weighting factors, thereby avoiding exhaustive search while maintaining low computational complexity. MATLAB 2016 simulations are conducted using a two-user NOMA system with 256-QAM modulation, 256 subcarriers, and ideal Successive Interference Cancellation (SIC) detection. Performance is evaluated in terms of Complementary Cumulative Distribution Function (CCDF), Bit Error Rate (BER), Power Spectral Density (PSD), and computational complexity. At a CCDF of 10–4, the proposed PTS + IWO scheme achieves PAPR values as low as 3.2 dB in Rayleigh fading and 2.1 dB in Rician fading, compared with approximately 12.8–13.3 dB for conventional NOMA. Furthermore, the proposed approach provides SNR gains of up to 3.5 dB at a BER of 10–4 and significantly improves spectral containment with PSD levels reaching − 76 dB/Hz. The results demonstrate that the proposed IWO-assisted PTS framework offers an excellent trade-off between complexity, PAPR reduction, BER performance, and spectral efficiency, making it a promising solution for future high-efficiency NOMA communication systems.

Channel estimation errors significantly degrade signal detection performance in massive multiple-input multiple-output (massive MIMO) systems, limiting the effectiveness of conventional linear, near-optimal, and learning-based detectors under practical channel uncertainty. To address this challenge, this paper proposes a channel state information (CSI)-aware deep neural network-assisted detector (DNN-ML) that explicitly incorporates channel estimation error variance into the detection process. The proposed framework employs CSI feature extraction, dimensionality reduction, error-adaptive feature fusion, and reliability-aware decision refinement to jointly exploit the received signal, estimated CSI, and CSI uncertainty. The detector is evaluated for a 256×256 massive MIMO system employing 256-QAM modulation over Rayleigh fading channels with 10

Orthogonal Time Sequence Multiplexing (OTSM) is a promising waveform for beyond-5G and 6G systems due to its flexible time–sequence structure and robustness to doubly dispersive channels. However, like other multicarrier techniques, it suffers from a high peak-to-average power ratio (PAPR) that forces high-power amplifiers (HPAs) to operate with large input back-off and degrades bit error rate (BER) performance. This paper proposes a low-complexity hybrid PAPR mitigation framework that combines DFT-spreading with an energy–entropy-aware Chaos-SLM scheme using a minimal candidate size (U=2) and no per-frame side information. Simulations across 64-, 256-, and 512-subcarrier OTSM systems with a Rapp HPA show PAPR reductions of up to 9 dB over OFDM and 8 dB over baseline OTSM at the 10−3 CCDF level, accompanied by 10–13 dB SNR gains at a target BER of 10−3, lower error vector magnitude (EVM), and reduced out-of-band emissions. The reduced PAPR translates into a smaller HPA back-off requirement, which improves the achievable PA operating efficiency; direct measurement of hardware power consumption is left for future work.

The modern-day wireless systems and devices require a single antenna system capable of supporting both sub-6 GHz and wide-band microwave frequency bands. These systems require stable performance throughout the operational band to enable seamless multi-standard operation. To meet the arising demands of modern-day wireless systems this work proposes the design and analysis of a compact size wideband antenna covering the frequency band ranges 2.59–20 GHz. The antenna is designed using FR4 with an overall size of 30 × 30 mm2 which corresponds to 0.25 λc × 0.25 λc, where λc is the wavelength at the lower cutoff frequency. The proposed antenna is extracted from a conventional semi-circular shaped broadband antenna after consecutive stages, and the final optimized design offers a stable gain of 2.4–5.2 dBi with high radiation efficiency across the operational bandwidth. Furthermore, to meet the requirements of modern-day applications along with increasing the channel capacity the proposed design is converted into 2-port multiple input multiple output (MIMO) antenna by placing the elements orthogonal to each other. The antenna covers similar bands compared to unit elements along with low coupling of less than − 18 dB throughout the targeted band without the requirement of any additional coupling structure. Unlike many reported wideband MIMO antennas that require complex decoupling structures or larger footprints, the proposed antenna simultaneously achieves compact size, wideband operation (2.59–20 GHz), and high isolation through a simple orthogonal arrangement of radiating elements. The MIMO antenna offers excellent performance in terms of the MIMO performance parameters by having low envelope correlation coefficient (ECC) and high diversity gain (DG). Furthermore, both unit elements and MIMO antenna are compared with recently reported antenna which highlights the novelty of the proposed antenna system: a compact wideband antenna and its MIMO configuration—with the MIMO gain improved to 3.5–6 dBi—well suited for sub-6 GHz and wideband wireless applications.

This paper proposes an Intelligent Minimum Mean Square Error–Deep Neural Network (IMMSE–DNN) hybrid signal detector for optical Multiple-Input Multiple-Output (MIMO) systems employing high-order modulation schemes. The aim is to ensure reliable detection for 64-Quadrature Amplitude Modulation (64-QAM), 256-QAM, 512-QAM, and 1024-QAM, where conventional detectors experience severe degradation due to noise enhancement, interstream interference, and nonlinear impairments. The proposed framework integrates a linear Minimum Mean Square Error (MMSE) front-end for effective interference suppression with a Deep Neural Network (DNN)-based nonlinear refinement stage to mitigate residual distortions. Simulation results obtained using MATLAB demonstrate that the proposed IMMSE–DNN consistently outperforms conventional MIMO, Zero-Forcing Equalizer (ZFE), MMSE, Maximum Likelihood Detection (MLD), autoencoder, and standalone DNN-based detectors. At a Bit Error Rate (BER) of 10 −3 , the proposed detector achieves SNR gains of approximately 4–5 dB for 64-QAM, 5–6 dB for 256-QAM, 6–7 dB for 512-QAM, and up to 8 dB for 1024-QAM compared to MMSE detection. Additionally, training accuracy analysis shows that the IMMSE–DNN converges rapidly, achieving nearly 90 % accuracy within 20 epochs, highlighting its robustness and suitability for next-generation high-capacity optical MIMO networks.

Massive multiple inputs and multiple outputs (M-MIMO) is one of the vital technologies for systems beyond fifth-generation (B5G). The signal detection 256 × 256 M-MIMO is complex and expensive due to the utilization of several antennas' arrays. In this letter, we give a Graph Neural Network (GNN) detection to investigate the bit error rate (BER), power spectral density (PSD), and complexity performance of the M-MIMO system under perfect channel state information (CSI) and imperfect CSI. The simulation results reveal that the proposed GNN achieved a 63

Vehicle-to-everything (V2X) and vehicular Internet of Things (IoT) services in sixth-generation (6G) networks must operate within New Radio V2X (NR-V2X) coherence-time budgets of 1–3 ms at sustained vehicular speeds, while remaining compatible with the limited power-amplifier headroom of in-vehicle and roadside-unit terminals. Orthogonal Time Sequency Multiplexing (OTSM) — a Walsh–Hadamard-based two-dimensional waveform — delivers OTFS-class robustness against high Doppler at lower receiver complexity, making it a strong candidate for V2X / vehicular IoT in 6G. Like every multicarrier waveform, OTSM exhibits high peak-to-average power ratio (PAPR), requiring per-frame PAPR-reduction algorithms. Existing metaheuristicassisted Partial Transmit Sequence (PTS) methods — including the Whale Optimization Algorithm (WOA), Genetic Algorithm, and Particle Swarm Optimization — find the binary-PTS optimum but do not fit the NR-V2X coherence budget: a per-frame WOA-PTS pass takes ≈ 985 ms on a representative platform, exceeding the 1 ms coherence by three orders of magnitude. We propose Optimal-PTS-RNN, a Gated Recurrent Unit (GRU) surrogate trained against an exhaustive binary-PTS oracle constructed off-line over the (Walsh–Hadamard-justified) phase set B = ±1 with pseudo-random subblock partitioning at V = 4. The GRU replaces per-frame phase search with a single forward pass at ≈ 230 μs, fitting the NR-V2X coherence budget with ≈ 4× headroom. The proposed method approximates the exhaustive-binary-PTS optimum on 64-subcarrier OTSM under high-mobility Rayleigh fading within a mean amortisation gap Δamort ≈ 0.61 dB—the measured CCDF = 10−3 tail of its predictions shows the realised tail IBO saving (≈ 0.1–0.25 dB relative to unrotated operation) is presently bounded by surrogate fidelity rather than by the framework — while being the only one of the six evaluated methods (SLM, conventional PTS, GA-PTS, PSO-PTS, WOA-PTS, Optimal-PTS-RNN) to fit the NR-V2X coherence-time budget. Methods with strictly better PAPR — SLM and quaternary PTS — exceed the coherence budget by 13× and 61× respectively and are not deployable in V2X. The Δamort is documented quantitatively across M ∈ {64, 128, 256, 512} and reflects the trade-off between surrogate fidelity and inference latency under the baseline GRU input representation; two improved surrogate variants introduced in this revision — a feature-augmented GRU (GRU-F) and a full-resolution 1-D CNN encoder — do not close this gap (Δamort 0.56–0.70 dB across five training seeds), an informative negative result that bounds the fidelity achievable with the evaluated encoder families and sharpens the open surrogate-design problem. All code, trained weights, and simulation seeds are publicly released.

Non-Orthogonal Multiple Access (NOMA) is considered a promising multiple access technique for beyond-5G wireless communication systems due to its ability to improve spectral efficiency and support massive connectivity. However, the multi-carrier nature of NOMA signals results in a high Peak-to-Average Power Ratio (PAPR), which degrades power amplifier efficiency and overall system performance. In this paper, a hybrid PAPR reduction framework integrating Invasive Weed Optimization (IWO) with Selective Mapping (SLM) and Partial Transmit Sequence (PTS) is proposed. The IWO algorithm optimizes phase rotation factors and candidate sequences, reducing the search complexity associated with conventional methods. The proposed schemes are evaluated through MATLAB simulations for a downlink NOMA system with 256 subcarriers, 256-QAM modulation, and two users under Rayleigh and Rician fading channels. Performance is analyzed using CCDF, BER, and PSD metrics. At a CCDF of 10^-4 , the proposed PTS + IWO scheme achieves a PAPR reduction of approximately 6–9 dB, outperforming conventional PTS and SLM techniques. In addition, the BER performance improves by about 1–3 dB SNR gain, while the power spectral density is reduced to approximately − 700 to − 810 W/MHz, indicating improved spectral containment. These results demonstrate that the proposed hybrid approach effectively reduces PAPR while maintaining signal integrity and spectral efficiency in NOMA systems.

Orthogonal time–space modulation (OTSM) is emerging as a promising two-dimensional signaling technique for massive multiple-input multiple-output (M-MIMO) communication; however, its performance is highly dependent on reliable signal detection under imperfect channel state information (CSI). Existing detectors, such as zero forcing (ZF), minimum mean-square error (MMSE), and maximum likelihood detection (MLD), as well as recent convolutional neural networks (CNNs), bidirectional long short-term memory (BiLSTM), and generative adversarial network (GAN) models, either suffer from significant bit error rate (BER) degradation or require high computational complexity in large antenna arrays. To address these limitations, in this study, we propose a recurrent neural network (RNN)-assisted QR decomposition-based reduced search maximum likelihood detector (QRM-MLD) for OTSM in 5G and beyond 6G systems. The algorithm combines lattice-based searching with adaptive sequence learning to improve robustness against Rayleigh fading and channel estimation errors. The numerical results for 64 × 64 and 256 × 256 M-MIMO configurations demonstrate a consistent 5–12 dB signal-to-noise ratio (SNR) gain at a BER of 10⁻3 over conventional linear and iterative detectors, even under 10

Power-domain non-orthogonal multiple access (NOMA) is a leading multiple-access candidate for Beyond-5G uplinks, but the power-domain superposition that gives NOMA its spectral-efficiency advantage also inflates the peak-to-average power ratio (PAPR) of the transmitted waveform, straining the linearity of low-cost power amplifiers. We adapt the Han–Kim quantum-inspired evolutionary algorithm to the partial transmit sequence (PTS) phase-search problem, replacing the exhaustive search with a probabilistic update driven by a quantum rotation gate. Under 256-QAM and a Rayleigh fading channel, the proposed QP-PTS attains a PAPR of approximately 5 dB at the 10⁻³ CCDF threshold—about 1 dB lower than PSO-PTS and about 2.5 dB lower than adaptive PTS—while reaching a 10⁻³ BER at approximately 7.5 dB SNR. The proposed scheme requires more fitness evaluations than exhaustive PTS for small subblock counts (M = 4), but its evaluation count is independent of M, so the complexity advantage emerges for the larger M typical of production OFDM systems. These results indicate a practical PAPR–complexity trade-off for NOMA transmitters when full PTS optimality cannot be afforded at production-scale M. The proposed Quantum-Probability-Assisted Partial Transmit Sequence (QP-PTS) framework provides an efficient low-complexity solution for PAPR reduction in NOMA systems. The proposed method improves PAPR, BER, and convergence performance through probabilistic phase optimization while reducing exhaustive search complexity. Therefore, the framework enhances transmission reliability and optimization efficiency for future Beyond-5G wireless communication applications.

Abstract This paper investigates peak-to-average power ratio (PAPR) reduction and its impact on bit error rate (BER) and spectral characteristics in optical orthogonal frequency division multiplexing (Optical-OFDM) systems using different numbers of sub-carriers. Conventional optical-OFDM suffers from high PAPR, leading to severe nonlinear distortion, BER degradation, and increased out-of-band radiation. To address these issues, classical PAPR reduction techniques such as selective mapping (SLM), partial transmit sequence (PTS), and C-PTS-PSO are analyzed and compared with a proposed PTS-PSO scheme. Simulation results demonstrate that the proposed method consistently achieves the lowest PAPR across 64, 256, and 512 sub-carrier configurations, with PAPR reductions of up to 8–9 dB at a CCDF of 10 −3 compared to conventional optical-OFDM. The reduced PAPR significantly improves BER performance, where the proposed scheme achieves SNR gains of approximately 6–7 dB at a BER of 10 −3 for 64 and 256 sub-carriers relative to conventional methods. Furthermore, power spectral density (PSD) analysis confirms substantial suppression of out-of-band emissions, achieving more than 50 dB reduction compared to conventional Optical-OFDM. These results highlight that the proposed PTS-PSO method effectively mitigates nonlinear effects, enhances spectral efficiency, and improves overall system reliability.