In this work, we propose a novel energy-efficient spiking neural network (SNN)-based receiver for 5G-NR OFDM system, called neuromorphic receiver (NeuromorphicRx), replacing the channel estimation, equalization and symbol demapping blocks. We leverage domain knowledge to design the input with spiking encoding and propose a deep convolutional SNN with spike-element-wise residual connections. We integrate an SNN with artificial neural network (ANN) hybrid architecture to obtain soft outputs and employ surrogate gradient descent for training. We focus on generalization across diverse scenarios and robustness through quantized aware training. We focus on interpretability of NeuromorphicRx for 5G-NR signals and perform detailed ablation study for 5G-NR signals. Our extensive numerical simulations show that NeuromorphicRx is capable of achieving significant block error rate performance gain compared to 5G-NR receivers and similar performance compared to its ANN-based counterparts with 7.6× less energy consumption.

Designing an efficient receiver for multiple users transmitting orthogonal frequency-division multiplexing signals to the base station remain a challenging interference-limited problem in 5G-new radio (5G-NR) system. This can lead to stagnation of decoding performance at higher signal-to-noise-and-interference regimes. Further, the problem is exacerbated in future critical internet-of-thing (IoT) devices operating on smaller block size due to latency constraints and IoT users moving at varying speeds introducing Doppler shift and delay spread. In this work, we propose a novel deep learning (DL)-based U-net- and Resnet-inspired receiver for multi-user uplink transmission for a 5G-NR system that replaces only the signal demapping block of the receiver chain. Compared to traditional U-net frameworks, we propose a DL receiver with upsampling in the encoder that takes complex equalized symbols as input and downsampling in the decoder to output bit-wise log-likelihood ratios for multiple users. Further, residual skip connections are introduced in the decoder to facilitate stronger connections to the upsampling blocks. Finally, the DL receiver is optimized by maximizing the optimal bit-metric decoding rate. Comparative simulations show that our proposed DL receiver outperforms traditional 5G-NR receivers by considerable margins.

Hearing loss is among the most serious public health problems, affecting as much as 20% of the worldwide population. Even cutting-edge multi-channel audio-only speech enhancement (SE) algorithms used in modern hearing aids face significant hurdles since they typically magnify noises while failing to boost speech understanding in crowded social environments. Recently, for the first time we proposed a novel integration of 5G cloud-radio access network, internet of things (IoT), and strong privacy algorithms to develop 5G IoT enabled hearing aid (HA) [1]. In this demonstration, we show the first-ever transceiver (PHY layer) model for cloud-based audio-visual (AV) SE, which meets the requirements for high data rate and low latency of forthcoming multi-modal HAs (such as Google glasses with integrated HAs). Even in highly noisy conditions like cafés, clubs, conferences, meetings, etc., the transceiver [2] transmits raw AV information from a hearing aid system to a cloud-based platform and obtains a clear signal. In Fig. 1, we illustrate an example of our cloud-based AV SE hearing aid demonstration. Herein, the left-side computer and Universal Software Radio Peripheral (USRP) x310 function as IoT systems (hearing aids), the right-side USRP serves as an access point or base station, and the right-side computer serves as a cloud-server for operating NN-based SE models. Please take note that the channel between the HA device and the cloud is defined as an uplink channel, whereas the channel between the access point (cloud) and the HA device is defined as a downlink channel. Given the time-varying sensitivity of the data received at HA devices, the uplink channel can therefore handle a variety of data rates. As a result, a customized long-term evolution (LTE)-based frame structure is developed for uplink transmission of data. It provides error-correction codes in the 1.4 MHz and 3 MHz bandwidths with a variety of modulations and code rates. Furthermore, the cloud access point simply supports a limited transmission rate because it only transmits audio data to the HA equipment. In order to support real-time AV SE, a modified frame structure for LTE with 1.4 MHz of bandwidth is developed. The AV SE algorithm receives cropped lip images of the target speaker and a noisy speech spectrogram, and it produces an ideal binary mask that lessens the noise-dominant regions while improving the speech-dominant areas. We use the depth-wise separable convolutions, reduced STFT window size of 32 ms, smaller STFT window shift of 8 ms, and 64 convolutions in the audio feature extraction layers of our Cochlea-Net [3] multi-modal AV SE neural network architecture to reduce processing latency. Furthermore, the visual feature extraction framework is employed. Our proposed architecture can handle streaming data frame-by-frame. Thus, the users will experience for the first time the real-world development of a physical layer transceiver that can perform AV SE in real-time under strict latency and data rate requirements. For this demonstration, we will bring two computers and two USRP x310 devices.

Full duplex (FD) relaying can provide double spectral efficiency. Despite advanced self-interference cancellation techniques, residual self-interference (RSI) limits the performance significantly. We present an autoencoder (AE)-based block coded modulation (BCM) and differential BCM (d-BCM) for an FD amplify-and-forward (FD-AF) relay network that can tackle the deteriorating impacts of RSI. Existing works treat AE frameworks as black-box with minimal/no focus on training convergence, limiting AE’s practical deployment. Focussing on training convergence, firstly, we show that training of AE converges above minimum signal-to-noise-ratio (SNR) and below maximum RSI level, and CSI helps in faster convergence. Secondly, we establish a relationship between training hyper-parameters and AE-based BCM/d-BCM design, by showing that, for any given hyper-parameters, training of the AE has converged to its maximum potential of decoding if AE’s encoder has designed$2^{k}$codewords, with an emphasis on the minimum required training samples. To open the black-box AE, we reveal five observations in the AE-based designed codewords concerning Euclidean distance, packing density, hamming distance, and kurtosis, that resemble the desired observations of theoretical random coded modulations. By extensive simulations, we show that the proposed AE outperforms the conventional methods considerably for varying SNR, RSI, transmission rate, channel estimation errors, and small/practical block lengths.

In this paper, we design a first of its kind transceiver (PHY layer) prototype for cloud-based audio-visual (AV) speech enhancement (SE) complying with high data rate and low latency requirements of future multimodal hearing assistive technology. The innovative design needs to meet multiple challenging constraints including up/down link communications, delay of transmission and signal processing, and real-time AV SE models processing. The transceiver includes device detection, frame detection, frequency offset estimation, and channel estimation capabilities. We develop both uplink (hearing aid to the cloud) and downlink (cloud to hearing aid) frame structures based on the data rate and latency requirements. Due to the varying nature of uplink information (audio and lip-reading), the uplink channel supports multiple data rate frame structure, while the downlink channel has a fixed data rate frame structure. In addition, we evaluate the latency of different PHY layer blocks of the transceiver for developed frame structures using LabVIEW NXG. This can be used with software defined radio (such as Universal Software Radio Peripheral) for real-time demonstration scenarios.

In this work, we study an end-to-end deep learning (DL)based constellation design for decode-and-forward (DF) relay network. Firstly, we study both the one-way (OW) and two-way (TW) relaying by interpreting DF relay networks as stacked autoencoders, under Rayleigh fading channels, leading to a performance improvement of 0.5 dB for TWDF networks. Secondly by introducing redundant bits in transmission and reception, we design end-to-end DL-based framework similar to the differential coded modulation for OWDF and coded modulation for TWDF relay networks, under block fading Rayleigh channels and achieve performance gain of 2 dB and 1 dB over conventional method, without using the channel state information knowledge in OWDF networks.

In this work, we exploit the potential benefits of multi-arm bandit scheme in cooperative multiple-input multiple output (MIMO) wireless networks. In particular, we consider an online-policy for amplify-and-forward MIMO relay selection (RS), where relays are provided with uncertain channel state information (CSI). We design the RS policy as a sequential experience-driven learning algorithm with a contextual bandit (CB) approach, where the algorithm learns to select an optimal relay node using the imperfect CSI provided as a context vector and the past experience of rewards procured with current policy, with the aim of maximizing the cumulative mean reward over time. Further, with extensive simulation result, we demonstrate that proposed CB based RS policy achieves superior performance gains compared to conventional Gram-Schmidt method.

In this work, we study an end-to-end deep learning (DL) based constellation design for the amplify-and-forward (AF) relaying network. Firstly, we study the one-way (OW) and two-way (TW) AF relay networks as an autoencoder by utilizing a single channel to transmit the desired bits, whilst operating under Rayleigh fading channels. As a result of optimal constellation design via end-to-end DL-based framework, we achieve a performance gain of 4 dB and 1.2 dB at 10 dB average signal-to-noise ratio (SNR) over conventional OWAF and TWAF relay networks, respectively. Secondly, by adding redundant bits at the transmitter, we jointly design an end-to-end DL-based coding and modulation scheme for block fading Rayleigh channels. This leads to DL-based coding and modulation, and DL-based differential coding and modulation, similar to the coded modulation and differential coded modulation in conventional networks, depending upon the presence of channel state information knowledge at the receivers. Thus, we propose an end-to-end DL-based data-driven frameworks for differential coded modulation in OWAF and coded modulation in TWAF relay networks. Lastly, we show that at 20 dB average SNR, our proposed methods (DL based differential coded modulated OWAF and DL-based coded modulated TWAF) achieve a gain of 4 dB and 4.8 dB, over conventional OWAF and TWAF relay networks employing Hamming codes with same rates.

Non-orthogonal multiple access (NOMA) is one of the key technologies being evaluated for the fifth generation (5G) wireless communications. In this paper, a novel NOMA mechanism combining both the code-domain and power-domain techniques is proposed to potentially support a higher number of users. In particular, considering the code-domain NOMA method of sparse code multiple access (SCMA) as the baseline, new low data rate (LDR) users are added on top of it using power-domain NOMA. The optimization problem involving resource and power allocation in such a system is solved such that the overall achievable sum-rate is maximized. Simulation results indicate that the proposed mechanism not only supports higher number of users, but also demonstrates a higher achievable sum-rate than the original SCMA-based system.

The rapid growth of energy consumption due to the strong demands of wireless multimedia services, has become a major concern from the environmental perspective. In this paper, we investigate a novel energy-efficient resource allocation scheme for relay-assisted multiuser networks to maximize the energy efficiency (EE) of the network by jointly optimizing the subcarrier pairing permutation formed in one-to-many/many-to-one manner, subcarrier allocation, as well as the power allocation altogether. By analyzing the properties of the complex mixed-integer nonlinear programming problem, which is generally very difficult to solve in its original form, we transform the problem into an equivalent convex problem by relaxing the integer variables using the concept of subcarrier time sharing, and by applying a successive convex approximation approach. Based on the dual decomposition method, we derive an optimal solution to the joint optimization problem. The impact of different network parameters, namely number of subcarriers and number of users, on the attainable EE and spectral efficiency (SE) performance of the proposed design framework is also investigated. The numerical results are provided to validate the theoretical findings and to demonstrate the effectiveness of the proposed algorithm for achieving higher EE and SE than the existing schemes.

The rapid growth in energy consumption due to strong demands of wireless multimedia services, has become a major concern from an environmental perspective. In this paper, we investigate a novel energy-efficient resource allocation scheme for relay-assisted multiuser networks to maximize the energy efficiency (EE) of the network by jointly optimizing the subcarrier pairing permutation formed in one-to-many/many-to-one manner, subcarrier allocation, as well as the power allocation all together. By analyzing the properties of the complex mixed-integer nonlinear programming problem, which is generally very difficult to solve in its original form, we transform the problem into an equivalent convex problem by relaxing the integer variables using the concept of subcarrier time sharing, and by applying a successive convex approximation approach. Based on the dual decomposition method, we derive an optimal solution to the joint optimization problem. Numerical results are provided to validate the theoretical findings and to demonstrate the effectiveness of the proposed algorithms.

In this paper, we investigate resource allocation algorithm for multiuser full-duplex (FD) decode-and-forward (DF) relay network for improving the energy efficiency (EE). The problem of energy-efficient joint subcarrier and power allocation is formulated as a ratio of the spectral efficiency (SE) of the network to the total energy consumption in the network. The formulated problem is a non-convex fractional mixed binary-integer non-linear programming problem. Further, we resolve this problem by a series of convex transformations and introduce a network penalty factor, which works as EE parameter, to convert the fractional mixed-integer form into a parametric subtractive form, and then design an effective energy-efficient iterative resource allocation algorithm to find the optimal solution. In addition, we also propose a low-complexity suboptimal algorithm. The effectiveness of the proposed iterative and suboptimal algorithms are evinced by simulation results.

In this paper, we investigate an energy-efficient joint subcarrier and power allocation algorithm for improving the worst energy efficiency (worst-EE) in multiuser two-way amplify-and-forward (AF) relay networks, that not only balances the EE of the two-way links, but also ensures the desired quality-of-service (QoS) of each user. In order to maximize the worst-EE, an EE-balancing optimization problem is formulated as the ratio of the spectral efficiency (SE) over the total network power consumption subject to a total transmit power and users' QoS constraints. Since the formulated primal problem is a non-convex fractional mixed binary-integer program, i.e., NP-hard to solve, thus a concave lower bound on the objective function and a series of convex transformations are applied to transform the problem into a tractable convex form. An iterative algorithm is proposed to achieve the optimal solution of the dual problem. We further propose an efficient, low-complexity suboptimal resource allocation algorithm. Simulation results demonstrate the effectiveness of the proposed iterative and suboptimal algorithms.

In this paper, we investigate utility-based joint subcarrier and power allocation algorithms for improving the energy efficiency (EE) in multi-user two-way regenerative relay networks. With the objective of determining the best subcarrier allocation for each user pair, subcarrier pairing permutation, and power allocation to all the nodes, a network price is introduced to the power consumption as a penalty for the achievable sum rate, followed by the examination of its impact on the tradeoff between the EE and spectral efficiency. The formulated optimization problem is a non-convex mixed-integer nonlinear programming problem, and thus a concave lower bound on the objective function and a series of convex transformations are applied to transform the problem into a convex one. Through dual decomposition, we propose a utility-based resource allocation algorithm for iteratively tightening the lower bound and finding the optimal solution of the primal problem. By exploring the structure of the obtained optimal solution, an optimal price that enables green resource allocation is found from the perspective of maximizing EE. Additionally, a suboptimal algorithm is investigated to strike a balance between computational complexity and optimality. Simulation results evince the effectiveness of the proposed algorithms.

In this paper, a novel resource allocation algorithm is investigated to maximize the energy efficiency (EE) in multiuser decode-and-forward (DF) relay interference networks. The EE optimization problem is formulated as the ratio of the spectrum efficiency (SE) over the entire power consumption of the network subject to total transmit power, subcarrier pairing, and allocation constraints. The formulated problem is a nonconvex fractional mixed binary integer programming problem, i.e., NP-hard to solve. Furthermore, we resolve the convexity of the problem by a series of convex transformations and propose an iterative EE maximization algorithm to jointly determine the optimal subcarrier pairing at the relay, subcarrier allocation to each user pair and power allocation to all source and the relay nodes. Additionally, we derive an asymptotically optimal solution by using the dual decomposition method. To gain more insights into the obtained solutions, we further analyze the resource allocation algorithm in a two-user case with interference-dominated and noise-dominated regimes. In addition, a suboptimal algorithm is investigated with reduced complexity at the cost of acceptable performance degradation. Simulation results are used to evaluate the performance of the proposed algorithms and demonstrate the impacts of various network parameters on the attainable EE and SE.

In this paper, we study the problem of energy-efficient resource allocation in multiuser two-way amplify-and-forward (AF) relay networks with the aim of maximizing the energy efficiency (EE), while ensuring the quality-of-service (QoS) requirements and balancing the EE of the user links. We formulate an EE-balancing optimization problem that maximizes the ratio of the spectral efficiency (SE) over the total power dissipation subject to QoS and a limited transmit power constraints. The problem which maximizes the EE by jointly optimizing the subcarrier pairing, power allocation, and subcarrier allocation, turns out to be a non-convex fractional mixed-integer nonlinear programming problem, which has an intractable complexity in general. We apply a concave lower bound on the achievable sum rate and a series of convex transformations to make the problem convex one and propose an iterative algorithm for iteratively tightening the lower bound and finding the optimal solution through dual decomposition approach. In addition, a low-complexity suboptimal algorithm is investigated. We then characterize the impact of various network parameters on the attainable EE and SE of the network employing both EE maximization and SE maximization algorithms when the network is designed from the EE perspective. Simulation results demonstrate the effectiveness of the proposed algorithms.

In this paper, energy-efficient resource allocation algorithms are investigated to improve the energy efficiency (EE) in two-way multi- carrier amplify-and-forward (AF) relay networks by ensuring the quality-of-service (QoS) and balancing the EE of the user links. We formulate an EE-balancing optimization problem that maximizes the ratio of the spectral efficiency (SE) and the total network power consumption by jointly designing the subcarrier pairing at the relay node and power allocation at all nodes under the total transmit power and QoS constraints, thereby leading to a mixed integer programming problem which turns out to be non-convex. Further, we resolve the problem by a series of convex transformations and propose an iterative EE algorithm to determine the solution through Lagrangian dual decomposition. Moreover, a suboptimal EE algorithm is also investigated with reduced complexity at the cost of acceptable performance degradation. Simulation results validate the performance gain of the proposed algorithms and show the performance tradeoff between EE and SE.

In this paper, we investigate an energy-efficient power allocation scheme in the cognitive radio (CR) networks that utilizes the energy harvested from ambient sources and spectrum sensing information. The optimization problem is formulated as a ratio of the spectral efficiency (SE) to the total energy consumption under the energy and battery causality constraints, which is solved by an iterative algorithm to obtain the optimal solutions. Moreover, the expressions for the optimal solutions are obtained through the dual-decomposition method. Finally, with the help of exhaustive simulation results we show that the proposed power allocation scheme immoderately improves the the average energy efficiency (EE) and SE performance of the network.