27 February 2025 in IEEE Transactions on Microwave Theory and Techniques
Recent of radar-based human activity recognition (HAR) generally focus on activities radial to the radar. When it comes to omnidirectional ones, the susceptibility of the Doppler effect to aspect angle brings distortions between measured features and true ones. It will result in significant performance degradation. A novel omnidirectional HAR framework fusing spatial-temporal trajectory compensation (STTC) and multichannel long short-term memory (LSTM) based on a monostatic radar system is proposed to address this issue by normalizing omnidirectional features into radial ones. It can realize omnidirectional HAR by only using radial data in model training. First, a time sequence of feature points indicating measured distance, Doppler, and azimuth angle can be obtained from received signals and located in a range-angle-time (RAT) cube by the fast Fourier transform (FFT) and multisignal classification (MUSIC) algorithm. Next, a spatial–temporal trajectory estimation algorithm is designed to achieve an estimated movement trajectory in the cube. Then, a movement trajectory-based compensation method is proposed to suppress displacement and Doppler distortions according to the geometrical relationship between movement and radar main beam direction. Finally, multichannel LSTM models are designed to support the sequential feature points as input for classification. Contrast experiment results demonstrate its feasibility and superiority in classification accuracy and angle insensitivity compared to existing ones.
14 October 2021 in IEEE Transactions on Antennas and Propagation
A theoretical sea echo modeling of the floating-platform (FP) high-frequency hybrid sky-surface wave radar (HSSWR) is presented. The ionosphere is considered to be a no-tilt reflecting plane moving in the vertical direction. Subsequently, the first-order sea clutter cross section with consideration of the platform sway and yaw motion is derived. Simulations are conducted to explore the influences of the ionospheric movement and the platform oscillation motion on the sea clutter power spectrum. The simulation results indicate that the platform sway motion may induce additional peaks that distribute symmetrically concerning the Bragg peaks, while the platform yaw motion and the ionospheric movement may broaden and even split the sea clutter. Experiments are conducted with the newly developed HSSWR system, of which the receiving arrays are simultaneously deployed on a FP and the shoreside. Experimental measurements concerning the frequency shift, Doppler width, and the arrival angle of the E-layer/F-layer ionosphere-reflected direct wave are compared and analyzed. The study demonstrates the feasibility of the proposed modeling and provides valuable guidelines for the sea clutter characteristics analysis and the data quality assessments of the FP HSSWR.
27 February 2020 in IEEE Geoscience and Remote Sensing Letters
The detection performance of high-frequency surface wave radar (HFSWR) is highly susceptible to radio frequency interference (RFI). The fact that external RFIs will turn into a chirp signal and the fractional Fourier transform (FRFT) is a potent tool to analyze the chirp signal, motivates us to use FRFT in interference mitigation. In this letter, two new RFI suppression schemes are proposed, of which one is based on hybrid used of FRFT and autoregressive (AR) linear prediction algorithm, another is based on joint FRFT and recursive least squares (RLS) adaptive filtering algorithm. The simulation result indicates that the proposed schemes can effectively mitigate external RFIs even when the interferences cover Bragg peaks. The experimental result shows that the proposed schemes can effectively suppress RFI without losing echoes, and the signal to noise-plus-interference ratio is improved by 6 dB on average after RFI suppression.
24 September 2024 in IEEE Sensors Journal
Sleep apnea event detection using the radar sensor is attractive due to its non-contact fashion. In the radar baseband signal processing chain, the demodulation is a critical step affecting the quality of phase information involving the breathing signal, ultimately impacting the accuracy of detecting apnea-hypopnea events. However, some factors, such as phase wrapping and direct current (DC), lead to the distortion of the phase information and can hardly be obliterated. In this paper, by directly combining the quadrature baseband signals, a quadrature-temporal point cloud is proposed to represent the quadrature baseband signals involving breathing activity while avoiding the influences in the demodulation. In order to process the quadrature-temporal point cloud, a modified PointNet model is applied to classify the apnea-hypopnea event from the actual patients’ nocturnal signals. A dataset from 31 obstructive sleep apnea-hypopnea syndrome (OSAHS) patients with simultaneously measured polysomnography (PSG) has been collected in a sleep center. Various experiments have been carried out to evaluate the performance. The overall accuracy and ablation experiments both show the superiority of the proposed method. Moreover, the proposed method achieves an average accuracy of 84% and 78% for subject-wise cross-validation and multi-class (apnea, hypopnea, and normal breathing) classification, respectively. All the experimental results demonstrate the effectiveness of the proposed method, showing potential applications for home sleep apnea testing (HSAT).
23 January 2026 in IEEE Internet of Things Journal
Recent radar data generation studies for human activity recognition (HAR) always focus on statistic-driven methods guided by statistical parameters, such as mean, variance, or latent network features. However, they lack physical interpretability and are unable to generate targeted data with a specified position or direction. To address this issue, a novel motion-driven radar data generation method is proposed for any-position any-direction (APAD) HAR using monostatic radar. First, a 5-D point cloud, including time, range, Doppler, pitch, and azimuth angle features, is achieved as a human activity model sample from a radial recording by fast Fourier transform (FFT), constant false alarm rate (CFAR) detector, and direction of arrival (DOA) angle estimation processing. In particular, a speed-aware density-based spatial clustering of application with noise (VA-DBSCAN) algorithm is designed for point reduction under the consideration of nonuniform point cloud distributions. Then, new human activity samples from any starting position with any moving direction can be generated by translating and rotating the above model sample. The generated Doppler and energy features are corrected according to the viewing position and direction. Finally, a radar-based PointNet long short-term memory (PointNet-LSTM) network is adopted for the APAD-HAR. In contrast experiments, only 48 recorded samples were utilized as a data source to generate a training group with 27 888 samples. Our proposed method demonstrated its feasibility and superiority with an average recognition accuracy rate of 92.11% by more than 25% improvement compared to other state-of-the-art methods.