In contrast to most of the existing equalization methods, blind equalization (BE) can eliminate the effect of multipath fading without any known sequences. As a result, BE is a promising technique for wireless intelligence and non-cooperative communication. However, the conventional BE methods require long sequences or large-scale training to recover the received signals. In this paper, a deep learning-based neighborhood-assisted symbol-based decision (DL-NA-SBD) method is proposed to tackle this problem. Specifically, we replace the commonly used linear approaches with neural network to optimize the traditional SBD function and the mean square error (MSE) loss function in two stages to generate the equalizer coefficients. To avoid collecting large numbers of signals, we train the network using the online training strategy. Simulation results demonstrate that the proposed method achieves better inter-symbol interference (ISI) elimination and bit error rate (BER) performance compared with the conventional methods while requiring only a short-length signal sequence.

Abstract The hybrid visible light communication (VLC)/radio frequency (RF) communications are investigated with the aid of reconfigurable intelligent surfaces (RISs) in dynamic wireless networks, where the RIS access selection processes of VLC/RF users are updated depending on the channel quality dynamically. Specifically, a dynamic optimization problem due to the mobility of users and time‐varying selection strategy is formulated. Under the constraints of the average minimum rate for VLC/RF users and the maximum transmit power constraints for VLC/RF access points (APs), the target is to minimize the average long‐term power consumption, by jointly considering the active beamforming at APs and the passive beamforming at RISs. Based on the Lyapunov optimization framework and the drift‐plus‐penalty (DPP) algorithm, the original optimization problem is transformed into corresponding short‐term problems at each frame. Furthermore, the closed form solutions with active‐passive beamforming are derived using the fractional programming method based on the Lagrangian dual theory. Finally, numerical results demonstrate the convergence and effectiveness of the proposed optimization algorithm.

As electromagnetic environments are more and more complex, wireless interference identification (WII) is becoming vital for non-cooperative communication systems in both civilian and military scenarios. With the enormous success of deep learning (DL), methods that optimize convolutional neural networks (CNNs) for WII have been proposed. However, due to the intrinsic characteristics of CNNs, the existing networks are difficult to capture long-range feature dependencies, causing the low recognition accuracy and the high computational complexity. Motivated by the success of transformers in natural language processing (NLP) domain, we propose an augmented convolutional neural network with transformer (ACNNT), which combines both the advantages of CNNs and transformers to simultaneously strengthen locality and establish long-range dependencies. Specifically, the ACNNT has multiple stages, and every stage consists of convolutional layers and transformer module to model local and long-range dependencies of context, respectively. At the end of the network, a classification token is used for classification. A channel attention (CA) module is proposed to further improve the expressive ability of the transformers. Extensive experiments demonstrate that the proposed method leads to performance improvement as compared to conventional DL based methods.

Wireless interference identification (WII) is a promising technology for non-cooperative communication systems in both civilian and military scenarios. With the rapid development of artificial intelligence, deep learning (DL) based WII methods have been proposed. However, the existing networks based on DL do not have the adaptive ability, and this situation may cause a waste of computing resources. In this paper, we propose a novel Multi-Depth Adaptive Network (MDANet), and it can adaptively determine the forward propagation depth according to the difficulty of input samples in inference. Specifically, we firstly divide a given convolutional neural network (CNN) into several blocks, and each block has its own output of classification by attaching a fully connected layer. The mechanism of confidence is introduced to enable the network to dynamically select depth of forward propagation and allocate appropriate computational resources depending on the complexity of samples during test time. In addition, we improve the recognition ability of early blocks through three proposed approaches. Experiments demonstrate that the MDANet can reduce the calculation cost and prediction time significantly without the performance loss.

In the vision of the next generation communications, the wireless devices may work on different transmission media, such as microwave and visible light. In this case, how to bridge these different devices remains an open challenge. Following the framework of [1], we consider a cross-media base station (BS) for supporting devices working on different media, as visible light and radio frequency (RF). Specifically, we conceive two criteria for power allocation toward enhanced performance, by maximizing the sum and minimum rates. Furthermore, we also analyze the impact of the position of BS to the system performance. Finally, the theoretical results are verified by simulations for supporting the effectiveness of the developed power allocation schemes in cross-media communications.

Single-carrier frequency-domain turbo equalization (SC-FDTE) has gained widespread adoption in the emerging broadband spatial modulation (SM) systems operating in frequency-selective channels, where the channel model considered is a quasi-static Rayleigh fading channel. In this paper, a new class of robust FDTE designs based on the minimum mean-square error (MMSE) criterion is conceived for broadband single-carrier SM (SC-SM) systems relying on realistic imperfect channel knowledge. First, a robust time-domain soft-decision feedback (TDSDF)-aided FDTE is proposed to cope with channel estimation errors at the receiver. Furthermore, its robust frequency-domain soft-decision feedback (FDSDF)-aided counterpart is derived to offer a low-complexity approximate solution. Finally, by exploiting the carefully selected reliable soft-decision output of the channel decoder as pilots, we refine the resultant decision-directed channel estimation. As a benefit, the performance of the two robust FDTEs can be further improved. Both our simulation results and our extrinsic information transfer (EXIT) chart analysis demonstrate that the proposed robust FDTEs achieve significant performance improvements over the conventional FDTEs.

Grant-free non-orthogonal multiple access (NOMA) has recently gained significant attention for reducing signaling overhead in machine-type communications (MTC). In this context, compressed sensing (CS) has been identified as a good candidate for joint activity and data detection due to the inherent sparsity nature of user activity. This paper augments activity and data detection for frame based multi-user uplink scenarios where users are (in)active for the duration of a frame, namely frame-wise joint sparsity model. Firstly, we formulate the block CS (BCS)-based sparse signal recovery framework, by fully extracting and exploiting the underlying frame-wise joint sparsity of the user activity. Then, to make explicit use of the block sparsity inherent in the equivalent block-sparse model and consider that the user sparsity level should be unknown for multiuser detection, two enhanced BCS- based greedy algorithms are developed, i.e., threshold aided block sparsity adaptive subspace pursuit (TA-BSASP) and cross validation aided block sparsity adaptive subspace pursuit (CVA- BSASP). Specifically, the proposed TA-BSASP algorithm can approach the oracle least squares (LS) performance, by reasonably setting the threshold based on the AWGN noise floor. And the proposed CVA-BSASP algorithm is a highly practical algorithm design that does not require any prior knowledge, by adopting the statistical and machine learning mechanism cross validation (CV) to determine the stopping condition of the algorithm. Superior performance of the proposed algorithms is demonstrated by numerical experiments.

Grant-free non-orthogonal multiple access has recently gained significant attention for reducing signaling overhead in machine-type communications. In this context, compressed sensing (CS) has been identified as a good candidate for joint activity and data detection due to the inherent sparsity nature of user activity. This paper augments activity and data detection for frame-based multi-user uplink scenarios where users are (in)-active for the duration of a frame, namely, the frame-wise joint sparsity model. First, we formulate the block CS (BCS)-based sparse signal recovery framework, by fully extracting and exploiting the underlying frame-wise joint sparsity of the user activity. Then, to make explicit use of the block sparsity inherent in the equivalent block-sparse model and considering the user sparsity level to be unknown for multiuser detection, two enhanced BCS-based greedy algorithms are developed, i.e., threshold aided block sparsity adaptive subspace pursuit (TA-BSASP) and cross-validation aided block sparsity adaptive subspace pursuit (CVA-BSASP). Specifically, the proposed TA-BSASP algorithm can approach the oracle least squares (LS) performance by reasonably setting the threshold based on the additive white Gaussian noise floor. Moreover, the proposed CVA-BSASP algorithm is a highly practical algorithm design that adopts the statistical and machine learning mechanism cross-validation to determine the stopping condition of the algorithm and this does not require prior knowledge. Furthermore, the convergence and the computational complexity of the proposed algorithms are derived and the superior performance of the proposed algorithms is demonstrated by numerical experiments.

Non-orthogonal multiple access (NOMA) is an emerging research topic in the future fifth generation wireless communication networks, which is expected to support massive connectivity for massive machine-type communications (mMTC). Due to the sporadic communication nature of mMTC, the grant-free transmission methodology is highly expected in uplink NOMA systems, to drastically reduce the transmission latency and signaling overhead. Exploiting the inherent sparsity nature of user activity, compressive sensing (CS) techniques have been applied for efficient multi-user detection in the uplink grant-free NOMA. In this paper, we propose a prior-information-aided adaptive subspace pursuit (PIA-ASP) algorithm to improve the multi-user detection performance. In this algorithm, a parameter evaluating the quality of the prior-information support set is introduced, in order to exploit the intrinsically temporal correlation of active user support sets in several continuous time slots adaptively. Then, to mitigate the incorrect estimation effect of the prior support quality information, a robust PIA-ASP algorithm is further proposed, which adaptively exploits the prior support based on the corresponding support quality information in a conservative way. It is noted that both of the two proposed algorithms do not require the knowledge of the user sparsity level, while most of the state-of-the-art CS-based multi-user detection algorithms usually need. Moreover, for the two proposed algorithms, the upper bound of the signal detection error and the computational complexity is derived. Simulation results demonstrate that the two proposed algorithms are capable of achieving much better performance than that of the existing CS-based multi-user detection algorithms with a similar computational complexity.

Conventionally, fast frequency hopping (FFH) is regarded as a non‐coherent system, which has inevitable shortcomings in low spectral efficiency. To achieve a high spectral efficiency while maintaining a favourable bit error ratio (BER) performance in FFH systems, in this study, the authors extend their previously proposed subset‐based coherent FFH (S‐CFFH) scheme with the aid of spatial modulation (SM). Furthermore, they derive the closed‐form expressions of the pairwise error probability and asymptotically BER bound for the S‐CFFH/SM maximum‐likelihood receivers in the presence of multitone jamming and highly frequency‐selective Rayleigh fading channels, where the perfect and imperfect channel state information are both considered. The authors’ analysis and simulation results show that, the proposed S‐CFFH/SM scheme outperforms both the conventional non‐coherent FFH and the S‐CFFH schemes, in terms of spectral efficiency and BER, respectively.

Generalized spatial modulation (GSM) is a recently proposed appealing multi-input multi-output (MIMO) transmission technique, which is capable of striking a tradeoff between the achievable transmission rate and the cost of radio frequency (RF) chains. In this letter, a novel low-complexity near-optimal soft decision (SoD)-aided detector is proposed for GSM, which considerably reduces the search space by employing a block minimum mean-squared error (B-MMSE) algorithm. Our simulation results show that the proposed detector is capable of achieving a better tradeoff between bit-error-rate (BER) performance and computational complexity compared with the existing matched filter (MF)-based SoD algorithms.

The subset-based coherent fast frequency hopping (S-CFFH), was recently proposed to enable reliable channel estimation and coherent schemes for FFH over fading channels. In this paper, we analyze the maximum-likelihood (ML) receiver for the S-CFFH/binary phase shift keying (BPSK), with partial band noise jamming (PBNJ), frequency selective Rayleigh fading, and imperfect channel state information (CSI). The expressions of closed-form bit error ratio (BER) are presented, and the results are validated by simulations. It is shown that the proposed ML receiver significantly outperforms some conventional diversity combining receivers in terms of BER. The ML receiver also greatly reduces the jammer's efficiency.

A novel detect-and-forward (DeF) relaying aided cooperative SM scheme is proposed, which is capable of striking a flexible tradeoff in terms of the achievable bit error ratio (BER), complexity and unequal error protection (UEP). More specifically, SM is invoked at the source node (SN) and the information bit stream is divided into two different sets: the antenna index-bits (AI-bits) as well as the amplitude and phase modulation-bits (APM-bits). By exploiting the different importance of the AI-bits and the APM-bits in SM detection, we propose three low-complexity, yet powerful relay protocols, namely the partial, the hybrid and the hierarchical modulation (HM) based DeF relaying schemes. These schemes determine the most appropriate number of bits to be re-modulated by carefully considering their potential benefits and then assigning a specific modulation scheme for relaying the message. As a further benefit, the employment of multiple radio frequency (RF) chains and the requirement of tight inter-relay synchronization (IRS) can be avoided. Moreover, by exploiting the benefits of our low-complexity relaying protocols and our inter-element interference (IEI) model, a low-complexity maximum-likelihood (ML) detector is proposed for jointly detecting the signal received both via the source-destination (SD) and relay-destination (RD) links. Additionally, an upper bound of the BER is derived for our DeF-SM scheme. Our numerical results show that the bound is asymptotically tight in the high-SNR region and the proposed schemes provide beneficial system performance improvements compared to the conventional MIMO schemes in an identical cooperative scenario.

Differential Frequency Hopping (DFH) is a novel technique for the frequency-hopping system in HF (High Frequency) bands. The frequency transition function (FTF) and the signal detection methods are the key issues for DFH system. Symbol-by-symbol detection and sequence detection are adopted in DFH system. With these two detection methods, the symbol error rate (SER) performances of DFH system are analyzed over a Rayleigh-fading channel with multi-tone jamming (MTJ) and additive white Gaussian noise (AWGN). Simulations validate the analyses. The results of analyses and simulations prove that the DFH system with sequence detection can achieve better anti-jam (AJ) performance than that of conventional frequency-hopping (FH) system.

This paper presents a type of frequency-hopping system in HF (High Frequency) bands, which is called Differential Frequency Hopping (DFH) system. The frequency transition function (FTF) and the methods of signal detection are the key technologies for DFH system. The error-rate performances of DFH with Partial Band Jamming (PBJ) and additive white Gaussian noise (AWGN) over a Rayleigh-fading channel by using product-combining receiver (PCR) are studied analytically, the performances are validated by simulation results, performance comparisons among the various receivers show that the anti-jam (AJ) performance of DFH system with PCR outperforms that with linear-combining receiver (LCR).

Differential frequency hopping (DFH) is a novel technique for the frequency-hopping system in HF (high frequency) bands. The frequency transition function (FTF) and the signal detection methods are the key issues for DFH system. A novel non-coherent detection scheme is proposed in asynchronous multi-user environments and additive white Gaussian noise (AWGN) channels. The multi-user performance of DFH with this novel receiver is studied analytically and validated by simulation results. By comparing of synchronous multi-user system and asynchronous multi-user system with conventional non-coherent detection receiver, it is shown that the performance of asynchronous multi-user system outperform that of synchronous multi-user system, and the novel detection scheme can achieve better performance than the conventional non-coherent detection scheme in asynchronous multi-user environments

A type of frequency-hopping system in HF (high frequency) bands, differential frequency hopping (DFH) system, is presented in this paper. The frequency transition function (FTF) and the methods of signal detection are the key issues for DFH system. Symbol-by-symbol detection and sequence detection are adopted in DFH system. With these two detection methods, the symbol error rate (SER) performances of DFH system are analyzed over a Rayleigh-fading channel with partial band noise jamming (PBNJ) and additive white Gaussian noise (AWGN). Simulations validate the analyses. The results of analyses and simulations prove that the DFH system with sequence detection can achieve better anti-jam (AJ) performance than that of conventional frequency-hopping (FH) system.