Affine frequency division multiplexing (AFDM) has emerged as a promising technology for high-mobility scenarios, offering reliable performance in doubly selective channels. However, the computational complexity of the maximum likelihood (ML) detection scheme renders it impractical for real-time AFDM applications. To address this, we propose a low-complexity AFDM symbol detection algorithm based on expectation propagation (EP) in this paper. The proposed EP-based detection scheme iteratively updates messages to approximate the ML result, reducing computational complexity from exponential to cubic order. By exploiting the sparse and quasi-banded structure of the channel in the discrete affine Fourier transform (DAFT) domain and employing matrix block decomposition, lower-upper factorization, and upper triangular matrix forward substitution, we further reduce the complexity of the EP algorithm to linear order. Additionally, we optimize the EP algorithm’s performance by incorporating deep learning-based moment matching, making the algorithm more adaptive with trainable parameters for both positive and negative components. Moreover, we propose a DAFT-domain iterative detection and decoding scheme, where external information from the decoder is fed back to the detector, resulting in improved system reliability. Simulation results show that the proposed scheme achieves near-ML performance while reducing complexity by dozens of orders of magnitude compared to the ML detector, striking a balance between performance enhancement and computational complexity.

In affine frequency division multiplexing (AFDM) systems, the severe peak-to-average power ratio (PAPR) signals exist in the time domain due to the coherent superposition of numerous modulated symbols. Eventually, high PAPR signals require sophisticated and expensive power amplifiers with a very large linear range. To this end, a neural network (NN) aided intelligent transceiver optimization framework is proposed for suppressing PAPR based on the spreading AFDM structure. Specifically, the transceiver jointly optimizes the constellation geometry and associated bit labeling, the precoding NN, as well as the NN based detector. Moreover, the precoding NN is learned from a precoding approach which minimizes the variance of the instantaneous power of output signals at the transmitter. The joint optimization framework aims to achieve maximum PAPR reduction under the constraints of unit energy and spectral emission mask. Besides, to mitigate the potential inter-carrier interference during the offline training, a long short term memory based detector is designed within the optimization framework. Simulation results demonstrate that the conceived NN based optimization method achieves a significant enhancement on PAPR reduction compared with conventional approaches, while slightly improving the bit error ratio performance.

Affine frequency division multiplexing (AFDM) achieves full diversity but faces multiple-access challenges due to signal dispersion. To address this issue, we propose a power domain non-orthogonal multiple access AFDM (PD-NOMA-AFDM) system, which enables parallel transmission of multi-user signals on the same resource block through power-domain multiplexing. Furthermore, we design a binary-loop maximal ratio combining-message passing (BLMM)-based successive interference cancellation (SIC) scheme. Specifically, the inner loop fully leverages the sparsity of the AFDM equivalent channel to effectively eliminate inter-symbol interference and achieve reliable initial symbol estimation; the outer loop iteratively updates extrinsic information to compensate for performance degradation caused by banded-matrix approximation. We prove the convergence of the inner loop to the MMSE fixed point and the local convergence of the outer loop. Subsequently, by combining Lipschitz continuity and perturbation theory, we demonstrate the convergence of the overall BLMM detector to a neighborhood of the exact fixed point. The pairwise error probability analysis is then used to characterize its diversity gain and performance gap to maximum likelihood (ML) detection. To further narrow this gap, a graph neural network (GNN) is incorporated into the BLMM multi-user detection framework. This approach dynamically captures the multi-user interference (MUI) characteristics through node message interactions, thereby improving the accuracy of the approximatea posterioriprobability distribution. Simulation results show that the proposed BLMM-GNN achieves near-ML performance with strong robustness.

Index modulation (IM) techniques have been widely studied over the past decade for their ability to enhance spectral and energy efficiency by exploiting additional degrees of freedom (DoF) in waveforms. In this paper, we propose a novel subcarrier filtering orthogonal frequency-division multiplexing (OFDM) scheme, named waveform index modulation (WIM), to boost the spectral efficiency (SE) of OFDM systems without compromising other performance metrics. In WIM-OFDM, information is conveyed not only by the modulated constellation symbols but also by altering the subcarrier filter shapes, thereby utilizing an additional DoF in the OFDM signaling process. An SE-enhanced version, referred to as generalized WIM-OFDM (GWIM-OFDM), is also designed to further boost the index transmission rate by maximizing the DoF for filter selection on each subcarrier. Additionally, the optimization of subcarrier filter shapes is formulated, and a special case of subcarrier filter pair can be optimized by utilizing the proposed non-convex to convex scaling method. At the receiver, a low-complexity interference cancellation algorithm is proposed to eliminate the introduced inter-carrier interference caused by the non-orthogonal subcarrier shapes. Finally, to validate the proposed scheme, closed-form expressions for the achievable rates and the upper bound on the average bit error rate are derived to prove the superiority of our WIM-OFDM and GWIM-OFDM schemes theoretically. Monte Carlo simulation results corroborate the benefits of the proposed scheme, that is, the GWIM-OFDM scheme exhibits 4.7 to 6.1 dB performance gain, considering both bit error rate and peak-to-average power ratio, compared with the traditional OFDM and other IM benchmarking schemes under the same spectrum mask at different transmission rate scenarios.

Low Earth-orbit (LEO) satellite communications have attracted increasing attention as an effective complement to terrestrial networks for global coverage. However, inherent challenges, such as severe Doppler shifts, significantly degrade the estimation accuracy of instantaneous channel state information (CSI) and accordingly the beamforming performance. To address these issues, this paper proposes an end-to-end sensing-aided deep learning network (SANet) for beamforming in LEO satellite communications. The SANet enhances the sum-rate performance by extracting moving information from radar echo signals. Specifically, the sensing-aided hypernetwork employs an integrated sensing and communications (ISAC) framework to extract the relative velocity between the LEO satellite and ground users from radar echoes. This velocity information is then used to adjust the weights of the beamforming recurrent neural network (RNN), effectively mitigating the Doppler effects. Numerical results demonstrate the proposed SANet significantly outperforms the state-of-the-art beamforming approaches, achieving an approximate 25% improvement in sum-rate over the conventional approaches under identical parameter settings.

Modern network systems have grown considerably in scale and complexity. Deep learning technology has thus become indispensable for unlocking the full potential. Therefore, the demand for high-precision fine-grained data has grown significantly. In this paper, we introduce the critical yet unexplored problem of super-resolution for network traffic data, aiming to reconstruct fine-grained data (i.e., data sampled at high frequencies) from coarse-grained data (i.e., data sampled at low frequencies). Inspired by image super-resolution techniques, we first transform network traffic data into images to expose their inherent periodic patterns. Moreover, we successfully migrate vision backbone network to the temporal super-resolution task. Based on this foundational network, we design a novel cross-attention super-resolution generative adversarial network (SRGAN) model that integrates our cross-attention mechanism to jointly capture local-global temporal correlations. Experimental results on real-world network traffic datasets demonstrate that our model effectively performs super-resolution on traffic network data, outperforming several state-of-the-art models.

In this paper, we propose a novel waveform index modulation orthogonal frequency-division multiplexing (WIM-OFDM) scheme to increase spectral efficiency for multicarrier systems. More specifically, the proposed WIM-OFDM scheme conveys not only the classic constellation symbols but also extra index bits by changing the subcarrier filtering shape for each symbol. As a key point, the optimization of the subcarrier filter shapes is formulated and a preliminary subcarrier filter pair is given to verify the performance of the proposed scheme. Our simulation results demonstrate that the proposed WIM-OFDM scheme exhibits superior performance in both peak-to-average power ratio and bit error ratio compared to conventional OFDM-IM and its dual-mode counterparts without increasing the out-of-band emission.

Satellite Internet of things (S-IoT) aims to provide globally covered network services. In this paper, we conceive an uplink grant-free random access scheme for S-IoT network, where ground devices transmit data packets to the low Earth orbit (LEO) satellite, reducing signaling cost and making efficient use of spectrum resources by employing the non-orthogonal multiple access scheme. The impact of high operational speed of the LEO satellite is also taken into account. We further propose an iterative Gaussian approximated message passing-aided sparse Bayesian learning (GAMP-SBL) algorithm to address the joint channel estimation (CE), active user identification (UID) and data detection (DD) problem, where the three steps interacts with each other during the iterative process. Simulation results have demonstrated that our proposed joint receiver design outperforms the existing AMP-based schemes in terms of bit error rate (BER), convergence speed, as well as false alarm rate (FAR).

In future applications of Internet of Everything (IoE), we need to timely and reliably collect multi-modal sensing data in order to monitor dynamic environment. To this end, we study a timely wireless powered crowdsensing system by enabling cooperative sensing among multiple sensors to increase reliability, by exploiting radio frequency (RF) based wireless power transfer (WPT) to address energy shortage of miniature sensors, and by minimising the average age of information (AoI) to guarantee the timeliness of the sensing data. We jointly optimise the inter-group sensors scheduling and the intra-group sensors scheduling for minimising the weighted AoI among multiple group of sensors. Since the optimisation problem is NP-hard, we propose a joint scheduling algorithm to obtain the optimal scheduling policy. Simulation results demonstrate the superiority of our scheme over the existing state of the art.

In continuum-armed bandit problems where the underlying function resides in a reproducing kernel Hilbert space (RKHS), namely, the kernelised bandit problems, an important open problem remains of how well learning algorithms can adapt if the regularity of the associated kernel function is unknown. In this work, we study adaptivity to the regularity of translation-invariant kernels, which is characterized by the decay rate of the Fourier transformation of the kernel, in the bandit setting. We derive an adaptivity lower bound, proving that it is impossible to simultaneously achieve optimal cumulative regret in a pair of RKHSs with different regularities. To verify the tightness of this lower bound, we show that an existing bandit model selection algorithm applied with minimax non-adaptive kernelised bandit algorithms matches the lower bound in dependence of T, the total number of steps, except for log factors. By filling in the regret bounds for adaptivity between RKHSs, we connect the statistical difficulty for adaptivity in continuum-armed bandits in three fundamental types of function spaces: RKHS, Sobolev space, and Holder space.

In order to unlock the full advantages of massive multiple-input multiple-output (MIMO) in the downlink, the base station (BS) must leverage information about the downlink fading channels. However, in frequency division duplex (FDD) systems, full channel reciprocity does not hold, and acquiring information about the downlink channels generally requires downlink pilot transmission followed by uplink feedback. Prior work proposed to design pilot transmission, feedback, and channel state information (CSI) estimation, or directly downlink beamforming, via deep learning in an end-to-end manner. While previous work only used downlink pilots in a single slot, in this work, we introduce an enhanced end-to-end design that leverages partial uplink-downlink reciprocity and temporal correlation of the fading processes by utilizing jointly downlink and uplink pilots across multiple time slots. The proposed method is based on a novel deep learning architecture – HyperRNN – that combines hypernetworks and recurrent neural networks (RNNs) to optimize the transfer of long-term invariant channel features from uplink to downlink. Simulation results demonstrate that the HyperRNN achieves a lower normalized mean square error (NMSE) performance in terms of channel estimation, and that it attains a larger achievable sum-rate when applied to multi-user beamforming, as compared to the state of the art.

We consider bandit optimization of a smooth reward function, where the goal is cumulative regret minimization. This problem has been studied for $\alpha$-Holder continuous (including Lipschitz) functions with $0<\alpha\leq 1$. Our main result is in generalization of the reward function to Holder space with exponent $\alpha>1$ to bridge the gap between Lipschitz bandits and infinitely-differentiable models such as linear bandits. For Holder continuous functions, approaches based on random sampling in bins of a discretized domain suffices as optimal. In contrast, we propose a class of two-layer algorithms that deploy misspecified linear/polynomial bandit algorithms in bins. We demonstrate that the proposed algorithm can exploit higher-order smoothness of the function by deriving a regret upper bound of $\tilde{O}(T^\frac{d+\alpha}{d+2\alpha})$ for when $\alpha>1$, which matches existing lower bound. We also study adaptation to unknown function smoothness over a continuous scale of Holder spaces indexed by $\alpha$, with a bandit model selection approach applied with our proposed two-layer algorithms. We show that it achieves regret rate that matches the existing lower bound for adaptation within the $\alpha\leq 1$ subset.

MOTIVATION: DNA methylation is a key epigenetic factor regulating gene expression. While promoter methylation has been well studied, recent publications have revealed that functionally important methylation also occurs in intergenic and distal regions, and varies across genes and tissue types. Given the growing importance of inter-platform integrative genomic analyses, there is an urgent need to develop methods to discover and characterize gene-level relationships between methylation and expression. RESULTS: We introduce a novel sequential penalized regression approach to identify methylation-expression quantitative trait loci (methyl-eQTLs), a term that we have coined to represent, for each gene and tissue type, a sparse set of CpG loci best explaining gene expression and accompanying weights indicating direction and strength of association. Using TCGA and MD Anderson colorectal cohorts to build and validate our models, we demonstrate our strategy better explains expression variability than current commonly used gene-level methylation summaries. The methyl-eQTLs identified by our approach can be used to construct gene-level methylation summaries that are maximally correlated with gene expression for use in integrative models, and produce a tissue-specific summary of which genes appear to be strongly regulated by methylation. Our results introduce an important resource to the biomedical community for integrative genomics analyses involving DNA methylation. AVAILABILITY AND IMPLEMENTATION: We produce an R Shiny app (https://rstudio-prd-c1.pmacs.upenn.edu/methyl-eQTL/) that interactively presents methyl-eQTL results for colorectal, breast and pancreatic cancer. The source R code for this work is provided in the Supplementary Material. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

An edge-cancellation-aided iterative detection and decoding (EC-IDD) algorithm is proposed for polar-coded sparse code multiple access (SCMA), which jointly performs Gaussian-approximated message passing (GA-MP) detection of SCMA supported by the soft list decoding (SLD) of polar codes. A reduced-edge factor graph is formulated in each consecutive iteration with the aid of the cyclic redundancy check (CRC) and EC. Based on the simplified factor graph, the EC-IDD gradually reduces its complexity in each subsequent iteration, while improving the bit error rate (BER) performance, compared to the state-of-the-art joint detection and decoding (JDD) of polar-coded SCMA. Furthermore, an embedded decision-directed channel estimator (DD-CE) is proposed for our polar-coded SCMA system under realistic imperfect channel state information (CSI). Our simulation results demonstrate that the proposed EC-IDD achieves better BER performance than the state-of-the-art JDD under both perfect and imperfect CSI, despite achieving a complexity reduction of 92%. Finally, the BER of the proposed joint DD-CE and EC-IDD algorithm under imperfect CSI converges to that of EC-IDD operating under perfect CSI.

Space-time coded generalized spatial modulation-aided sparse code division multiple access (STC/GSM-SCDMA) is proposed, which exploits the two-dimensional transmit diversity potential of both the spatial and of the frequency domain. Hence, it constitutes a promising solution for the pervasive connectivity of devices in next-generation nonorthogonal multiple access (NOMA) systems. More explicitly, our STC/GSM scheme achieves diversity in the spatial-domain, while the sparse signal-spreading action of SCDMA results in frequency-domain (FD) diversity. A single-user bit error rate (BER) bound is derived as the benchmark of the BER performance of our STC/GSM-SCDMA system. Furthermore, a pair of novel detectors, namely a bespoke message passing aided (MPA) detector and a tailor-made approximate message passing (AMP) detector are conceived by designing a new factor graphs for our proposed STC/GSM-SCDMA system. The performance of these detectors is characterized in terms of their BER vs. complexity. Our simulation results show that the proposed AMP detector is capable of operating within 2 dB of the MPA detector's signal-to-noise ratio (SNR) requirement, while supporting a normalized user load of 150%, despite its appealing low complexity, which is about 1000 times lower than the MPA detector.

This paper proposes a novel spatial-modulated multicarrier sparse code-division multiple access (SM/MC-SCDMA) system for achieving massive connectivity in device-centric wireless communications. In our SM/MC-SCDMA system, the advantages of both MC signalling and SM are amalgamated to conceive a low-complexity transceiver. Sparse frequency-domain spreading is utilized to mitigate the peak-to-average power ratio (PAPR) of MC signalling, as well as to facilitate low-complexity detection using the message passing algorithm. We then analyze the single-user bit error rate performance of SM/MC-SCDMA systems communicating over frequency-selective fading channels. Furthermore, the performance of SM/MC-SCDMA systems is evaluated based on both Monte-Carlo simulations and analytical results. We demonstrate that our low-complexity SM/MC-SCDMA transceivers are capable of achieving near-maximum likelihood (ML) performance even when the normalized user-load is as high as two, hence constituting a variable solution to support massive connectivity in device-centric wireless systems.

In order to support high-user-load multiple-access (MA), we propose a non-orthogonal MA scheme based on a beneficial amalgam of spatial modulation (SM) and sparse code-division multiple-access (SCDMA), which is termed the SM-SCDMA. Hence, SM-SCDMA inherits both the merits of SM with single radio-frequency MIMO transceiver implementation and the advantages of SCDMA relying on low-complexity signal detection. In this paper, we evaluate the potential of SM-SCDMA as well as its low-complexity near-optimum signal detection. Given these objectives, we consider both the maximum likelihood detection and the message passing algorithm aided detection (MPAD) that is derived based on the maximum a posteriori principles. In order to evaluate the performance of large SM-SCDMA without relying on time-consuming simulations, we propose new approaches for analyzing the performance of SM-SCDMA systems. A range of formulas that are valid in the signal-to-noise ratio region of practical interest are derived. Finally, the performance of SM-SCDMA systems is investigated by addressing diverse design concerns. Our studies and performance results show that SM-SCDMA constitutes a promising MA scheme for the future ultra dense systems. Assisted by the MPAD, it is capable of supporting high-user-load MA transmission associated with a normalized user-load factor of two.