RSRuiyuan Song

Ruiyuan Song

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Ruiyuan Song has a total of 21 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Authentication With Passports for Deep RF Sensing Model Protection

    by Ruiyuan Song, Zhi Lu, Liang Fang, Zhi Wu, Dongheng Zhang, Yang Hu, Yan Chen

    As RF sensing increasingly moves toward real-world deployments, critical concerns emerge around unauthorized model usage and access control. Existing protection approaches-such as watermarking-are typically reactive, task-specific, and ineffective at runtime. This paper presents AuthRF (Authentication with passports for RF sensing models), a novel signal-level passport mechanism that proactively enforces access control by mapping a user-specific passport to phase-compensation weights in the signal processing pipeline. Valid passports yield coherent phase alignment and high-fidelity representations, while invalid or forged ones induce phase distortion that significantly degrades model performance. This design effectively deters unauthorized access, supports scalable multi-user authentication, and enables personalized service provisioning through controlled passport variation. We evaluate AuthRF on six representative RF sensing tasks using both WiFi and radar signals. Experimental results demonstrate its robust protection capabilities and seamless integration with existing sensing pipelines, positioning AuthRF as a practical foundation for secure and commercial-grade RF sensing deployment.

  • UniTHP: Advancing Unified Representation Learning for Through-Wall Human-Centric Perception

    by Rui Zhang, Yadong Li, Ruiyuan Song, Hanqin Gong, Ruixu Geng, Binquan Wang, Dongheng Zhang, Yang Hu, Yan Chen

    Recent years have witnessed increasing interest in sensing humans through walls with radio frequency (RF) signals, which enables critical applications such as surveillance and rescue. However, existing RF-based through-wall sensing methods either fail to consider the amplitude-phase characteristics of RF signals or cannot handle various perception tasks through an end-to-end approach. To address these challenges, we propose UniTHP - an RF-tailored single-stage multi-task framework specifically designed for through-wall human-centric perception. In particular, since RF signals contain both amplitude and phase information, utilizing both is critical for effective sensing. Therefore, we introduce a scale-mix attention block that models RF signals in their complex form while effectively preserving their signal properties. Additionally, this block implements multi-scale attention by splitting multiple attention heads into several groups, and each group focusing on a specific granularity of attention for different tasks. Building upon the scale-mix attention block, we carefully design the scale-mix encoder and task-specific decoder to develop our UniTHP framework. To evaluate the performance of UniTHP, we collect the first large-scale through-wall human perception dataset containing 491,000 pairs of optical images and radar frames and will make it public to the research community. Extensive experimental results demonstrate that UniTHP achieves new state-of-the-art results throughout all three downstream tasks, including pose estimation, action recognition, and person re-identification.


  • RF$^{2}$ Transformer: Refocusing Transformer for RF Sensing

    by Ruiyuan Song, Zhi Lu, Liang Fang, Zhi Wu, Shuai Yang, Dongheng Zhang, Yang Hu, Hui Lin, Yan Chen

    The learning-based RF sensing methods typically involve signal processing to transform the RF signals into spectrograms, which are then input into neural networks. However, this approach is suboptimal due to the potential degradation caused by the inherent multi-path interference, resulting in blurred RF spectrograms. To tackle this challenge, we introduce a novel Refocusing Transformer backbone customized for RF sensing (RF$^{2}$ Transformer). Rather than attempting to precisely model interference using the traditional signal processing techniques, the RF$^{2}$ Transformer utilizes a self-compensation mechanism to treat the interference-induced phase shifts as learnable parameters. This mechanism learns and compensates for the phase shift caused by interference in the complex feature space to obtain refocused and high-quality feature maps of RF spectrograms, thereby improving the performance of downstream tasks. We show that the RF$^{2}$ Transformer is general for various RF sensing tasks by evaluating it on six typical RF sensing tasks using two general RF signals (WiFi and radar). Experimental results indicate that the RF$^{2}$ Transformer takes an important step toward learning-based solutions for RF sensing.

  • Unleashing the Potential of Multiple WiFi APs in Real-World Localization System

    by Shuai Yang, Guanzhong Wang, Tianyu Zhang, Xuecheng Xie, Pengfei Yin, Ruiyuan Song, Dongheng Zhang, Yan Chen

    Wireless fidelity (WiFi) indoor localization plays an important role in many real-world applications and has gained widespread attentions from both academia and industry over the past decade. While existing works have already achieved remarkable performance under various practical scenarios, they solely utilize multiple WiFi access points (APs) to achieve a higher accuracy and do not deeply explore the intrinsic relationships among them. To further unleash the potential of multiple APs and reach the limits of WiFi indoor localization, in this article, we propose Qidi, a novel multi-APs collaboration-based localization system. To the best of our knowledge, we are the first to explicitly reveal three underlying relationships among multiple spatially distributed APs, i.e., consistency, continuity, and nonuniformity. By combining these three basic principles with the unique characteristics of specific tasks, a series of long-lasting practical challenges, such as automatic phase offset calibration, bilateral angle ambiguity, elevation angle estimation with uniform linear array (ULA) and nonline-of-sight (NLoS), can be efficiently resolved. Extensive experiments in various complex environments are provided to demonstrate that Qidi can achieve 2.4°, 3.2° median errors of joint azimuth and elevation angle estimation, and 0.4-m localization median error even in $20\times 20$ m exhibition hall. Moreover, a one-month longitudinal evaluation conducted on a real-world deployed WiFi integrated sensing and communication (ISAC) system further validates the effectiveness and robustness of the proposed localization system.

  • UMIMO: Universal Unsupervised Learning for Mmwave Radar Sensing With MIMO Array Synthesis

    by Haoyu Zhang, Dongheng Zhang, Ruiyuan Song, Zhi Wu, Jinbo Chen, Liang Fang, Zhi Lu, Yang Hu, Hui Lin, Yan Chen

    Millimeter-wave (mmWave) radar sensing powered by deep learning is now emerging in numerous applications, which are predominantly trained in a supervised manner. However, due to the non-interpretable nature of mmWave signals, labeling the radar data has always been a difficult task. While there have been investigations on unsupervised pre-training for mmWave radar sensing, these methods are tailored to specific signal representations. In this paper, we propose UMIMO, an unsupervised learning framework combining the hardware nature of MIMO radar and deep learning techniques to resolve the challenge raised by the insufficient labeled data. UMIMO leverages the antenna arrays synthesized from multiple transmitting and receiving antennas in mmWave radar to construct positive samples for contrastive learning. To achieve this, we propose the constraints on angular resolution and grating lobes to generate effective signal representations with different synthetic arrays. We conduct experiments using UMIMO on three tasks: contactless ECG monitoring, 3D human pose estimation, and human silhouette generation. All experimental results demonstrate that UMIMO can effectively improve the performance of learning-based mmWave radar sensing in an unsupervised manner.


  • Unleashing the Potential of Self-Supervised RF Learning With Group Shuffle

    by Ruiyuan Song, Zhi Lu, Dongheng Zhang, Liang Fang, Zhi Wu, Yang Hu, Qibin Sun, Yan Chen

    Self-supervised learning (SSL) is a powerful approach that learns general semantic representations from large-scale unlabeled data to make downstream tasks solve easier, offering significant potential in enhancing downstream performance and alleviating the appetite for large-scale annotated data. However, existing SSL techniques, predominantly designed for natural images, may be prone to shortcuts when applied to RF signals. This study presents surprising empirical findings showing that SSL can indeed learn meaningful RF representations by employing simple group shuffle (GS) and asymmetry augmentation techniques. The GS augmentation is inspired by blind calibration tasks in Time-Interleaved Analog-to-Digital Converters (TIADC). By treating the original RF signal as a composite output from sub-ADCs, GS augmentation enriches RF signals while preserving their global semantics. We also provide a theoretical validation of the GS augmentation’s singular value consistency. Notably, we observe that the shortcut is essentially a domain gap between the pre-trained and the downstream task models. This issue can be mitigated by an asymmetry augmentation technique, which maximizes the similarity between an original RF signal and its augmented version, rather than between two augmentations of the same RF signal. By integrating group shuffle and asymmetry augmentation (GSAA) into an existing contrastive learning framework, we develop an effective contrastive learning approach for RF signals. Our evaluations, spanning seven downstream RF sensing tasks across two general RF devices (WiFi and radar), strongly demonstrate that GSAA plays a significant role in advancing SSL-based solutions in RF sensing.


  • Open Access

    RF-Search: Searching Unconscious Victim in Smoke Scenes with RF-enabled Drone

    by Bin-Bin Zhang, Dongheng Zhang, Ruiyuan Song, Binquan Wang, Yang Hu, Yan Chen

    Toxic gases inhalation is the most common cause of death in fire scenes, which can make people unconscious and unable to save themselves. Hence, discovering the unconscious victims is crucial to improve their survival rate. In this paper, we propose RF-Search, a victim searching system with RF device mounted on the drone. The challenge mainly comes from the fact that drone motion would overwhelm the subtle vital signs utilized for victim identification. To resolve this problem, we have noted that the physical signature of drone motion has been encoded in stationary object reflections. Leveraging this unique physical signature, we propose to identify the unconscious victim through the spatio-temporal correlation between signals reflected from the victim and the surrounding stationary objects. To extract respiration information of the victim, we propose a motion segmentation module and a motion compensation module to suppress the signal variation caused by drone movement. Extensive experiments have demonstrated that our system could achieve an accuracy of 92.5% for victim identification.