SWStephen Wang

Stephen Wang

*This is an algorithmically generated author record based on publicly available information.

Stephen Wang has a total of 46 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • NeuromorphicRx: From Neural to Spiking Receiver

    by Ankit Gupta, Onur Dizdar, Yun Chen, Fehmi Emre Kadan, Ata Sattarzadeh, Stephen Wang

    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.


  • Two-Tier Frequency-Domain Equalization for Ultra-Wideband Integrated Sensing and Communication

    by Chao Xu, Jack Bedwell, Russel N. Torah, Stephen Wang, Shinya Sugiura, Robert G. Maunder, Lie-Liang Yang, Harald Haas, Lajos Hanzo

    Ultra-wideband (UWB) radio has license-free access to a substantial bandwidth of over 500 MHz, which makes it a promising candidate for integrated sensing and communication (ISAC), because the performance of both functionalities relies on the availability of sufficient bandwidth. However, due to its regulated power constraint and spectral mask, UWB sensing performance is susceptible to blockage, while the UWB data rate remains low. To enhance both functionalities, we propose a novel two-tier frequency-domain equalization (FDE) scheme for UWB ISAC, in which the first FDE removes the user-specific sequence from the received UWB header in support of sensing, while the second FDE equalizes the effect of channel impulse responses (CIRs) for data detection. The data-carrying amplitude/phase of UWB pulses, which are inherently repeated in the UWB header, naturally follow the circular convolution model without requiring a cyclic prefix (CP) for the proposed sensing operations. Furthermore, the CIRs estimated by the first FDE stage of bistatic sensing can be directly utilized by the second FDE stage of data detection. Compared to the conventional matched filtering (MF) aided UWB sensing, the proposed FDE approach improves the peak-to-sidelobe power ratio and facilitates multi-target sensing. Compared to conventional UWB MF template-based data detection, the proposed approach is capable of improving synchronization, channel estimation and equalization. Furthermore, the proposed two-tier FDE approach inspires a new pulse repetition tradeoff (PR-T) scheme, which reduces pulse repetition to achieve an improved data rate. Our simulation results demonstrate that the proposed UWB FDE sensing achieves centimeter-level accuracy even at a low Ricean K-factor of -4 dB. Additionally, the proposed FDE data detection designed for PR-T is capable of improving the UWB data rate from the single Megabits-per-second (Mbps) range to over 100 Mbps, at the cost of reduced pulse repetition gain.

  • Rate-Splitting Multiple Access for 6G: Prototypes, Experimental Results, and Link/ System Level Simulations

    by Sundar Aditya, Yong Jin Daniel Kim, David Vargas, David Redgate, Onur Dizdar, Neil Bhushan, Xinze Lyu, Sibo Zhang, Stephen Wang, Bruno Clerckx

    Rate-Splitting Multiple Access (RSMA) is a powerful and versatile physical layer multiple access technique that generalizes and has better interference management capabilities than 5G-based Space Division Multiple Access (SDMA). It is also a rapidly maturing technology, all of which makes it a natural successor to SDMA in 6G. In this article, we describe RSMA’s suitability for 6G by presenting: i) link and system level simulations of RSMA’s performance gains over SDMA in realistic environments, and (ii) pioneering experimental results that demonstrate RSMA’s gains over SDMA for key use cases like enhanced Mobile Broadband (eMBB), and Integrated Sensing and Communications (ISAC). We also comment on the status of standardization activities for RSMA.


  • Frequency Transfer Learning for AI-aided Beam Management in cmWave Spectrum

    by Yun Chen, Onur Dizdar, Ankit Gupta, Stephen Wang

    This paper focuses on the AI-aided beam management (AI-BM) scheme design for FR3 centimeter-Wave (cmWave) spectrum. A spindle-like decoder-encoder neural network is proposed to conduct spatial prediction with reduced measurements. To facilitate the AI-BM deployment for multi-frequency scenarios in 6G, an efficient frequency transfer learning solution is further proposed based on the antenna array theory. Moreover, a fully 3GPP compliant real-time proof-of-concept (PoC) platform is developed to evaluate the proposed scheme. By experimental results, we validate the advanced performance and robustness of the proposed AI-BM scheme.


  • AI-Aided Delay-Doppler Estimation for Bistatic OFDM ISAC Systems

    by Longfei Yin, Julia Equi, Fehmi Emre Kadan, Onur Dizdar, Ankit Gupta, Yun Chen, Gábor Fodor, Stephen Wang

    This letter introduces a novel artificial intelligence (AI)-aided delay-Doppler estimation method for bistatic integrated sensing and communications systems employing orthogonal frequency division multiplexing (OFDM) under dense clutter and inter-cell interference. An attention-based recurrent neural network is designed to extract features from individual OFDM symbols using Long Short-Term Memory layers followed by an attention layer to determine the relative importance, aiming to improve sensing accuracy and robustness. We demonstrate by numerical results that the proposed AI-aided approach can outperform conventional baseline methods and is robust against the degrading effects of heavy clutter and colored noise.


  • Hybrid Beamforming Assisted OTFS-Based CV-QKD Systems for Doubly Selective THz Channels

    by Xin Liu, Chao Xu, Stephen Wang, Soon Xin Ng, Lajos Hanzo

    Continuous-variable quantum key distribution (CV-QKD) maps information onto the quadrature components of electromagnetic waves, so that off-the-shelf wireless transceivers can be utilized. This motivates the move from optical to Terahertz (THz) bands. However, wireless THz channels suffer from severe path loss, while the mobility of wireless users imposes doubly selective fading. Against this background, we propose a new CV-QKD regime that relies on hybrid beamforming (HBF) assisted multiple-input multiple-output (MIMO) orthogonal frequency division multiplexing (OFDM) and orthogonal time frequency space (OTFS) system, where the channel’s transmissivity and robustness against double selectivity are overcome by HBF and OTFS, respectively. Secondly, in order to provide channel state information (CSI) for both the transmitter (CSI-T) and receiver (CSI-R), practical channel estimation methods are conceived. They operate in the time-frequency domain for OFDM and in the delay-Doppler domain for OTFS. Thirdly, soft-decision detection is devised for our MIMO OFDM/OTFS aided multi-dimensional reconciliation (MDR) scheme. Low-density parity-check (LDPC) coding is invoked for further improving secure CV-QKD transmission distance in the THz band. Our simulation results demonstrate that the proposed HBF MIMO OTFS-based CV-QKD system relying on realistic estimated CSI is capable of achieving an adequate secret key rate (SKR) and secure transmission distance in hostile doubly selective THz channels.


  • AI-Empowered Bi-Static Sensing for Rank-Limited Communications

    by Fehmi Emre Kadan, Ankit Gupta, Onur Dizdar, Ata Sattarzadeh, Yun Chen, Longfei Yin, Stephen Wang

    This letter proposes an AI-empowered localization method for passive objects using rank-limited communication signals in bi-static scenario. Specifically, we consider linearly precoded communication signals that are rank-limited by the total number of independent data streams, resulting in traditional subspace methods failing to find correct angular information. A deep neural network (DNN) based solution is proposed to accurately localize the targets under reflections from clutters and inter-cell interference. The proposed DNN model applies data fusion over multiple user equipments to overcome the limitations of using rank-limited signals. The numerical results show the efficiency of the developed technique over baselines.

  • Low-Complexity Precoder Design for MU-MIMO OTFS Networks

    by Ata Sattarzadeh, Onur Dizdar, Venkateswara Battula, Stephen Wang

    Delay-Doppler (DD) domain transmission schemes, such as Orthogonal Time Frequency Space (OTFS), have attracted significant attention due to their unique properties, particularly their robustness in doubly-dispersive channels. One challenging problem in OTFS framework is the precoding for Multi-User MIMO (MU-MIMO) transmissions due to the increased computational complexity. In this work, we propose two methods to perform low-complexity precoding for OTFS in MU-MIMO systems in Delay-Doppler (DD) domain. The first method leverages the diagonalization properties of the Doubly Block Circulant (DBC) channel matrix under the assumption of ideal pulse shaping. The second method benefits from the equivalent Time-Frequency (TF) domain representation of the signal to perform precoding in DD domain without any ideal pulse shaping assumptions. We describe how both methods can be employed to perform Zero-Forcing (ZF) and Mininum Mean Square Error (MMSE) precoding in OTFS signals in a low-complexity manner. Numerical results show that our proposed methods minimize multi-user interference and achieve higher received SNR compared to benchmark schemes.