Microwave HeartPrint: Noncontact Continuous Authentication Based on Multiview Dual-Domain Feature of Heart Micromotion Using UWB Bio-Radar
- 19 September 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 12 (23) , 51155-51167
Abstract
With the development of Internet-of-Things (IoT) technology, user identity recognition technology has become an important line of defense to ensure application access and privacy security. Ultrawideband (UWB) bio-radar, with its high range resolution and noncontact penetration detection advantages, can accurately capture the individual-specific and dynamic continuous surface micromotion characteristics caused by cardiac structural movement through transmitted microwaves, namely, Microwave HeartPrint, provides a new technological path for noncontact identity recognition. However, current radar-based noncontact cardiac motion recognition mostly treats the micromovement of the chest wall as a single scattering point target and primarily relies on single-domain data, thereby limiting the effectiveness of the recognition mechanism. To address the aforementioned issue, this article first uses UWB bio-radar to continuously monitor the multipoint micromotions in the range dimension of the cardiac body surface area along the radial direction, and then achieves the selection of effective range unit echoes from the perspective of multiple range tomographic planes. Second, based on the echo heartbeat segmentation and combined with short-time Fourier transform (STFT) time–frequency transform, the Microwave HeartPrint dual-domain data corresponding to the effective range units are obtained. Finally, a multiview dual-domain feature fusion recognition network is proposed, where the multiview single-domain feature fusion module (MV-SFFM) is designed to effectively fuse the differential and complementary micromotion features of effective range units on the cardiac surface. In addition, the cross-attention dual-domain feature fusion module (CA-DFFM) effectively fuses the time-domain and time–frequency-domain features to further improve the feature representation capability. Actual experiments show that the recognition accuracy of this method can reach more than 95%. Ablation experiments and visualization analysis strongly demonstrates the rationality and effectiveness of comprehensively using the micromotion information of multiple effective range units of the heart and dual-domain features.Keywords
Funding Information
- National Natural Science Foundation of China (62201578)
- Young Talent Fund of Association for Science and Technology in Shaanxi, China (20230144)
- Key Research and Development Plan of Shaanxi Province (2024SF-YBXM-658)
This publication has 28 references indexed in Scilit:
- WaveGRU-Net: Robust non-contact ECG reconstruction via MIMO millimeter-wave radar and multi-scale semantic analysisSignal Processing, 2025
- Individual Identification Using Radar-Measured Respiratory and Heartbeat FeaturesIEEE Access, 2024
- Simultaneous multi-person vital signs monitoring using multiple-input multiple-output FMCW millimeter wave radarAEU - International Journal of Electronics and Communications, 2024
- Can We Obtain Fine-grained Heartbeat Waveform via Contact-free RF-sensing?2022
- Multi-View CNN-LSTM Architecture for Radar-Based Human Activity RecognitionIEEE Access, 2022
- MU-ID: Multi-user Identification Through Gaits Using Millimeter Wave Radios2020
- Contactless person identification using cardiac radar signals2018
- Effective Iris Recognition SystemProcedia Technology, 2016
- Free Typed Text Using Keystroke Dynamics for Continuous AuthenticationLecture Notes in Computer Science, 2014
- Speech recognition with deep recurrent neural networks2013