CLChenyao Liu

Chenyao Liu

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Chenyao Liu has a total of 11 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • S 2 IE: Semantic and Side Information-Embedded PAPR Reduction for OFDM-Based Semantic Communications

    by Chenyao Liu, Weiyu Zhao, Yimeng Zhang, Liyang Lu, Wenjun Xu, Nan Ma, Ping Zhang

    Semantic communication (SemCom) based on orthogonal frequency division multiplexing (OFDM) is recognized as an essential topic for next-generation wireless networks, where peak-to-average power ratio (PAPR) reduction becomes a key issue. However, existing PAPR reduction methods fail to match SemCom and hence deteriorate the system performance, due to the ubiquitous semantic correlation from source. To address this challenge, a semantic and side information (SI)-embedded PAPR reduction framework (S$^{2}$IE) is proposed, which integrates a PAPR-aware power allocation module (PAPR-PAM) and a PAPR dual mapping module (PAPR-DMM) to achieve joint PAPR reduction. Semantic importance and SI, including the inverse discrete Fourier transform (IDFT) matrix, signal-to-noise ratio (SNR), and channel gain, are leveraged to guide the construction of an efficient reduction strategy. Specifically, the PAPR-PAM adopts a PAPR-constrained power allocation strategy, which further considers the target PAPR beyond semantic importance and channel conditions, thereby restraining PAPR surges. Meanwhile, the PAPR-DMM is developed to reduce PAPR while maintaining reconstruction quality, which reshapes OFDM symbols into a low-PAPR distribution with reversible nonlinear mapping. Simulations demonstrate that under the same PAPR, S$^{2}$IE achieves up to a 3.18 dB gain in peak signal-to-noise ratio (PSNR) and a 55.95% reduction in learned perceptual image patch similarity (LPIPS).

  • 2-DAM-SC: 2-D-Adaptive Modulation for Semantic Communications Under Shadowed Fading Channels

    by Chenyao Liu, Yimeng Zhang, Wenjun Xu, Liyang Lu, Jiaqi Wang, Dusit Niyato, Ping Zhang

    Semantic communication has emerged as a promising paradigm for next-generation wireless networks. In this context, high-efficiency modulation plays a crucial role in enhancing the resilience of semantic systems. However, non-ideal factors such as channel fading and estimation errors remain major impediments to practical deployment. To address these challenges, a two-dimensional adaptive modulation framework for semantic communications (2DAM-SC) is proposed, which adapts dynamically to signal-to-noise ratio (SNR) and channel estimation error. Firstly, an adaptive modulation scheme based on two-dimensional (2D) constellation sets is developed to improve robustness against quantization noise and channel variation. Secondly, a semantic codec based on channel state information (CSI) is designed to enhance semantic representation under imperfect channel estimation. Thirdly, a novel loss function is introduced to jointly optimize constellation mapping and image distortion. Simulation experiments are conducted under non-ideal channel conditions with shadowed fading and imperfect channel estimation, demonstrating that the proposed scheme achieves up to a 2.08 dB gain in peak signal-to-noise ratio (PSNR).

  • Top Cited Papers

    Semantic Communication for the Internet of Vehicles: A Multiuser Cooperative Approach

    by Wenjun Xu, Yimeng Zhang, Fengyu Wang, Zhijin Qin, Chenyao Liu, Ping Zhang

    The Internet of Vehicles (IoV) is expected to become the central infrastructure to provide advanced services to connected vehicles and users for higher transportation efficiency and security. A variety of emerging applications/services bring explosively growing demands for mobile data traffic between connected vehicles and roadside units (RSUs), imposing the significant challenge of spectrum scarcity in the IoV. In this article, we propose a cooperative semantic-aware architecture to convey essential semantics from collaborated users to servers for lessening data traffic. In contrast to current solutions that are mainly based on piling up highly complex signal processing techniques and multiple access capabilities in terms of syntactic communications, this article puts forth the idea of semantic-aware content delivery in the IoV. Specifically, the successful transmission of essential semantics of the source data is pursued rather than the accurate reception of symbols regardless of their meaning, as in conventional syntactic communications. To assess the benefits of the proposed architecture, we provide a case study of an image retrieval task for vehicles in intelligent transportation systems (ITSs). Simulation results demonstrate that the proposed architecture outperforms existing solutions, with fewer radio resources, especially in a low-signal-to-noise-ratio (SNR) regime, which can shed light on the potential of the proposed architecture in extending applications in extreme environments.