Behaviorally Diverse Data Augmentation for RFID-based Gesture Recognition

LIU Jianwei; CHEN Jiatong; YAO Xinwei; HAN Jinsong

doi:10.12263/DZXB.20251202

您当前的位置：

首页 >

文章列表页 >

Behaviorally Diverse Data Augmentation for RFID-based Gesture Recognition

更新时间：2026-04-23

- Behaviorally Diverse Data Augmentation for RFID-based Gesture Recognition
- ACTA ELECTRONICA SINICA Pages: 1-13(2026)
- 作者机构：
  
  1.浙江大学计算机科学与技术学院，浙江杭州 310027
  2.浙江工业大学先进技术研究院，浙江杭州 310014
  3.浙江工业大学计算机科学与技术学院，浙江杭州 310014
- 作者简介：
- 基金信息：
  
  National Natural Science Foundation of China(62372400);China Postdoctoral Science Foundation(2025M781520);Postdoctoral Fellowship Program of CPSF(GZC20241488);"Pioneer" and "Leading Goose" Research and Development Program of Zhejiang(2025C01054;2025C01212);Postdoctoral Research Excellence Funding Project of Zhejiang Province(ZJ2025024)
- DOI：10.12263/DZXB.20251202
  CLC： TP391;
- Received：02 January 2026，
  
  Accepted：31 January 2026，
  
  Online First：23 April 2026，
- 稿件说明：
移动端阅览
LIU Jianwei, CHEN Jiatong, YAO Xinwei, et al. Behaviorally Diverse Data Augmentation for RFID-based Gesture Recognition[J/OL]. ACTA ELECTRONICA SINICA, 2026, 1-13.
DOI：

LIU Jianwei, CHEN Jiatong, YAO Xinwei, et al. Behaviorally Diverse Data Augmentation for RFID-based Gesture Recognition[J/OL]. ACTA ELECTRONICA SINICA, 2026, 1-13. DOI： 10.12263/DZXB.20251202.

摘要

手势识别是人机交互中的关键支撑技术，已广泛应用于智能医疗、虚拟现实和智能家居等场景。相较于依赖视觉信息的方法，基于射频识别（Radio Frequency IDentification，RFID）的手势识别具有非接触、低成本和隐私友好等优势，展现出良好的应用前景。然而，现有RFID手势识别模型的性能高度依赖于训练数据的规模与多样性，而射频数据的采集成本较高、数据分布受限，从而制约了模型在未知样本上的泛化能力。为缓解上述问题，数据增强被视为提升识别性能的有效手段。然而，现有数据增强方法往往忽略了人类行为本身的固有差异性，导致合成样本在分布上的多样性不足。事实上，即便属于同一手势类别，不同样本之间仍普遍存在显著差异，其根本原因在于人类难以以完全一致的方式重复执行同一动作。在手势识别场景中，这种行为差异在直觉上主要源于手部相对于传感器的距离变化以及运动速度的差异。本文通过建立信号传播模型并结合先验实验，对这一直觉假设进行了系统验证。基于上述分析，本文提出一种面向行为多样性的RFID数据增强方法。该方法首先从射频信号传播机理出发，将手势的距离与速度信息显式编码为条件输入。随后，本文设计了一种新颖的条件扩散模型，在生成过程中沿距离和速度对应的条件方向进行受控偏移，从而合成在物理一致性约束下、分布范围更广的高质量样本。通过在手势识别模型的训练集中引入富含行为多样性的合成数据，可以有效提升模型对未知样本的泛化能力以及手势识别的准确率。本文在真实应用场景中搭建了RFID手势识别原型系统，并开展了系统性的物理实验。实验结果表明，在10类手势识别任务中，所提出的方法相较于基线模型的识别准确率提升超过20%，且显著优于现有的数据增强策略。此外，该方法的数据增强效果不会随着感知任务规模的扩大而明显衰减。在身份识别任务上的实验结果进一步表明，本文提出的方法同样适用于其他人机交互应用场景。

Abstract

Gesture recognition is a fundamental enabling technology for humancomputer interaction and has been widely adopted in applications such as smart healthcare

virtual reality

and smart homes. Compared with vision-based approaches

radio frequency identification (RFID)-based gesture recognition offers several distinctive advantages

including contact-free operation

low deployment cost

and privacy preservation

making it a promising solution for practical deployments. However

the performance of existing RFID-based gesture recognition models heavily depends on the scale and diversity of training data. In practice

the acquisition of RF data is costly and the resulting data distributions are inherently limited

which significantly constrains the generalization capability of models to unseen samples. To address this challenge

data augmentation has been widely regarded as an effective means to enhance recognition performance. Nevertheless

most existing augmentation methods overlook the intrinsic variability of human behavior

leading to synthesized samples with insufficient distributional diversity. In fact

even within the same gesture category

substantial variations commonly exist across different instances

primarily because humans cannot reproduce the same action in a perfectly identical manner. In gesture recognition scenarios

such behavioral variability intuitively arises from changes in the hand’s distance relative to the sensor as well as variations in motion speed. This intuitive hypothesis is systematically validated in this work through the establishment of a signal propagation model combined with preliminary experimental analysis. Motivated by these observations

we propose a behavior diversity-aware RFID data augmentation framework. Specifically

grounded in the physical principles of RF signal propagation

the proposed method explicitly encodes gesture-related distance and speed as conditional inputs. A novel conditional diffusion model is then designed to perform controlled shifts along the distance- and speed-conditioned directions during the generation process

thereby synthesizing high-quality samples that are both physically consistent and distributed over a broader behavioral diversity space. By introducing synthetic data enriched with behavioral diversity into the training set of gesture recognition models

the generalization capability to unseen samples and the recognition accuracy can be significantly improved. We implement an RFID based gesture recognition prototype system in real world scenarios and conduct systematic physical experiments. Experimental results show that

in a ten-class gesture recognition task

the proposed method improves recognition accuracy by more than 20% compared with baseline models and significantly outperforms existing data augmentation strategies. In addition

the effectiveness of the proposed data augmentation approach does not degrade noticeably as the scale of the sensing task increases. Experimental results on identity recognition further demonstrate that the proposed method can be effectively applied to other human computer interaction applications.

关键词

Keywords

references

Xiao Rui , Liu Jianwei , Han Jinsong , et al . OneFi: One-shot recognition for unseen gesture via COTS WiFi [C ] // Proceedings of the 19th ACM Conference on Embedded Networked Sensor Systems . New York : ACM , 2021 : 206 - 219 .

谷军霞 , 丁晓青 , 王生进 . 基于人体行为3D模型的2D行为识别 [J ] . 自动化学报 , 2010 , 36 ( 1 ): 46 - 53 .

Gu Junxia , Ding Xiaoqing , Wang Shengjin . Human 3D model-based 2D action recognition [J ] . Acta Automatica Sinica , 2010 , 36 ( 1 ): 46 - 53 . (in Chinese)

曹媛媛 , 黄飞跃 , 陶霖密 , 等 . 自然环境下日常动作的在线识别 [J ] . 电子学报 , 2009 , 37 ( S1 ): 16 - 21 .

Cao Yuanyuan , Huang Feiyue , Tao Linmi , et al . On-line recognition of actions in daily living [J ] . Acta Electronica Sinica , 2009 , 37 ( S1 ): 16 - 21 . (in Chinese)

Zou Yongpan , Xiao Jiang , Han Jinsong , et al . GRfid: A device-free RFID-based gesture recognition system [J ] . IEEE Transactions on Mobile Computing , 2017 , 16 ( 2 ): 381 - 393 .

Liu Jianwei , Zou Xiang , Lin Feng , et al . Hand-key: Leveraging multiple hand biometrics for attack-resilient user authentication using COTS RFID [C ] // 2021 IEEE 41st International Conference on Distributed Computing Systems . Piscataway : IEEE , 2021 : 1042 - 1052 .

Liu Jianwei , Cui Kaiyan , Zou Xiang , et al . Reliable multi-factor user authentication with one single finger swipe [J ] . IEEE/ACM Transactions on Networking , 2023 , 31 ( 3 ): 1117 - 1131 .

Zhang Shigeng , Ma Zijing , Yang Chengwei , et al . Real-time and accurate gesture recognition with commercial RFID devices [J ] . IEEE Transactions on Mobile Computing , 2023 , 22 ( 12 ): 7327 - 7342 .

Wang Chuyu , Liu Jian , Chen Yingying , et al . Multi - touch in the air: Device-free finger tracking and gesture recognition via COTS RFID [C ] // IEEE INFOCOM 2018-IEEE Conference on Computer Communications . Piscataway : IEEE , 2018 : 1691 - 1699 .

Gong Chen , Liang Bo , Gao Wei , et al . Data can speak for itself: Quality-guided utilization of wireless synthetic data [C ] // Proceedings of the 23rd Annual International Conference on Mobile Systems, Applications and Services . New York : ACM , 2025 : 209 - 222 .

Zhao Leqi , Xiao Rui , Liu Jianwei , et al . One is enough: Enabling one-shot device-free gesture recognition with COTS WiFi [C ] // IEEE INFOCOM 2024-IEEE Conference on Computer Communications . Piscataway : IEEE , 2024 : 1231 - 1240 .

Jiang Wei , Zhang Kai , Wang Nan , et al . MeshCut data augmentation for deep learning in computer vision [J ] . PLoS One , 2020 , 15 ( 12 ): e0243613 .

Zhang Xiaobin , Xu Hongzhe , Gao Wei , et al . FewSense: Enabling few-shot gesture recognition via COTS RFID [J ] . ACM Transactions on Sensor Networks , 2025 , 21 ( 5 ): 1 - 14 .

Yang Chao , Wang Ziqi , Mao Shiwen . RFPose-GAN: Data augmentation for RFID based 3D human pose tracking [C ] // 2022 IEEE 12th International Conference on RFID Technology and Applications . Piscataway : IEEE , 2022 : 138 - 141 .

Wang Ziqi , Mao Shiwen . AIGC for wireless sensing: Diffusion-empowered human activity sensing [J ] . IEEE Transactions on Cognitive Communications and Networking , 2025 , 11 ( 2 ): 657 - 671 .

Savin J , Gaudez C , Gilles M A , et al . Evidence of movement variability patterns during a repetitive pointing task until exhaustion [J ] . Applied Ergonomics , 2021 , 96 : 103464 .

Li Tianxing , Liu Qiang , Zhou Xia . Practical human sensing in the light [C ] // Proceedings of the 14th Annual International Conference on Mobile Systems, Applications, and Services . New York : ACM , 2016 : 71 - 84 .

Wang Minsi , Ni Bingbing , Yang Xiaokang . Recurrent modeling of interaction context for collective activity recognition [C ] // 2017 IEEE Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2017 : 7408 - 7416 .

Withana A , Peiris R , Samarasekara N , et al . zSense: Enabling shallow depth gesture recognition for greater input expressivity on smart wearables [C ] // Proceedings of the 33rd Annual ACM Conference on Human Factors in Computing Systems . New York : ACM , 2015 : 3661 - 3670 .

Zhao Tianming , Liu Jian , Wang Yan , et al . PPG-based finger-level gesture recognition leveraging wearables [C ] // IEEE INFOCOM 2018 - IEEE Conference on Computer Communications . Piscataway : IEEE , 2018 : 1457 - 1465 .

Kalgaonkar K , Raj B . One-handed gesture recognition using ultrasonic Doppler sonar [C ] // 2009 IEEE International Conference on Acoustics, Speech and Signal Processing . Piscataway : IEEE , 2009 : 1889 - 1892 .

Yatani K , Truong K N . BodyScope: A wearable acoustic sensor for activity recognition [C ] // Proceedings of the 2012 ACM Conference on Ubiquitous Computing . New York : ACM , 2012 : 341 - 350 .

Cao Dian , Wang Dong , Zhang Qian , et al . Towards domain-independent complex and fine-grained gesture recognition with RFID [J ] . Proceedings of the ACM on Human-Computer Interaction , 2020 , 4 : 1 - 22 .

Ma Zijing , Zhang Shigeng , Liu Jia , et al . RF-Siamese: Approaching accurate RFID gesture recognition with one sample [J ] . IEEE Transactions on Mobile Computing , 2024 , 23 ( 1 ): 797 - 811 .

Hou Weiying , Wu Chenshu . RFBoost: Understanding and boosting deep WiFi sensing via physical data augmentation [J ] . Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies , 2024 , 8 ( 2 ): 1 - 26 .

Mikołajczyk A , Grochowski M . Data augmentation for improving deep learning in image classification problem [C ] // 2018 International Interdisciplinary PhD Workshop . Piscataway : IEEE , 2018 : 117 - 122 .

Oneaţă D , Cucu H . Improving multimodal speech recognition by data augmentation and speech representations [C ] // 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops . Piscataway : IEEE , 2022 : 4578 - 4587 .

Yang Ling , Zhang Zhilong , Song Yang , et al . Diffusion models: A comprehensive survey of methods and applications [J ] . ACM Computing Surveys , 2024 , 56 ( 4 ): 1 - 39 .

He Yuan , Sun Yimiao , Guo Xiuzhen . RF computing: A new realm of IoT research [J ] . Journal of Computer Science and Technology , 2025 , 40 ( 4 ): 941 - 956 .

陆琪鹏 , 刘亚丽 , 刘长庚 , 等 . 基于区块链的RFID供应链产品所有权转移方案 [J ] . 电子学报 , 2025 , 53 ( 2 ): 451 - 459 .

Lu Qipeng , Liu Yali , Liu Changgeng , et al . Product ownership transfer scheme of RFID-enabled supply chain based on blockchain [J ] . Acta Electronica Sinica , 2025 , 53 ( 2 ): 451 - 459 . (in Chinese)

Finkenzeller K . RFID Handbook: Fundamentals and Applications in Contactless Smart Cards, Radio Frequency Identification and near-Field Communication [M ] . Hoboken : Wiley , 2010 .

Xu Huanyuan , Zhang Yajun , Yang Zhixiong , et al . RF-CSign: A Chinese sign language recognition system based on large kernel convolution and normalization-based attention [J ] . IEEE Access , 2023 , 11 : 133767 - 133780 .

Rappaport T S . Wireless Communications--Principles and Practice, (The Book End) [J ] . Microwave Journal , 2002 , 45 ( 12 ): 128 - 129 .

McInnes L , Healy J , Melville J . UMAP: Uniform manifold approximation and projection for dimension reduction [PP/OL ] . V3.arXiv ( 2020-09-18 )[ 2026-01-02 ] . https://doi.org/10.48550/arXiv.1802.03426 https://doi.org/10.48550/arXiv.1802.03426 .

Ng A Y , Jordan M I . On discriminative vs . generative classifiers: A comparison of logistic regression and naive Bayes [C ] // Proceedings of the 15th International Conference on Neural Information Processing Systems: Natural and Synthetic . New York : ACM , 2001 : 841 - 848 .

Arachchige C N P G , Prendergast L A . Confidence intervals for median absolute deviations [J ] . Communications in Statistics-Simulation and Computation , 2026 , 55 ( 1 ): 13 - 22 .

Henderi H . Comparison of Min-Max normalization and Z-Score Normalization in the K-nearest neighbor (kNN) Algorithm to Test the Accuracy of Types of Breast Cancer [J ] . IJIIS: International Journal of Informatics and Information Systems , 2021 , 4 ( 1 ): 13 - 20 .

Ronneberger O , Fischer P , Brox T . U-Net: Convolutional networks for biomedical image segmentation [M ] // Medical Image Computing and Computer-Assisted Intervention MICCAI 2015 . ChamSpringer International Publishing , 2015 : 234 - 241 .

Wang Zhou , Bovik A C , Sheikh H R , et al . Image quality assessment: From error visibility to structural similarity [J ] . IEEE Transactions on Image Processing , 2004 , 13 ( 4 ): 600 - 612 .

Liu Jianwei , Yuan Jiantao , Yu Guanding , et al . Efficient one-shot gesture recognition for WiFi ISAC via aug-meta learning [J ] . IEEE Journal on Selected Areas in Communications , 2025 , 43 ( 11 ): 3766 - 3781 .

Chi Guoxuan , Yang Zheng , Wu Chenshu , et al . RF-diffusion: Radio signal generation via time-frequency diffusion [C ] // Proceedings of the 30th Annual International Conference on Mobile Computing and Networking . New York : ACM , 2024 : 77 - 92 .

Li Zewen , Liu Fan , Yang Wenjie , et al . A survey of convolutional neural networks: Analysis, applications, and prospects [J ] . IEEE Transactions on Neural Networks and Learning Systems , 2022 , 33 ( 12 ): 6999 - 7019 .

卿宇寒 , 高陈强 , 谭卓林 , 等 . 基于时空自适应融合的双模行为识别 [J ] . 电子学报 , 2025 , 53 ( 7 ): 2389 - 2400 .

Yuhan Qing , Gao Chenqiang , Tan Zhuolin , et al . Bimodal action recognition based on spatiotemporal adaptive fusion [J ] . Acta Electronica Sinica , 2025 , 53 ( 7 ): 2389 - 2400 . (in Chinese)

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

No data

Related Author

No data

Related Institution

No data

⁰