GTFA-Net: A Generative Network for High-Resolution Time–Frequency Analysis in Dual-Frequency Continuous-Wave Radar Tracking
- 14 May 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 26 (12) , 18896-18904
Abstract
Dual-frequency continuous wave (DFCW) radar is a promising technology for indoor target tracking, yet its performance is constrained by the low time-frequency resolution (TFR) and frequency ambiguity of traditional time-frequency analysis (TFA) methods, such as the short-time Fourier transform. To overcome these challenges, this paper proposes a novel semi-supervised network named GTFA-Net, which integrates a non-local mechanism for enhanced TFR. The proposed GTFA-Net integrates a Various Noise Maker (VNM), a Multi-Scale Short-Time Module (MDSTM), and an Energy Concentration Module (ECM) with a non-local mechanism. The proposed VNM enhances the robustness of the network by adding different types of noise to the input signal, while the MDSTM improves the richness of time-frequency information by introducing multiple short-time filtering windows. The ECM, incorporating an enhanced non-local attention mechanism, effectively extracts global time-frequency features. Experimental results demonstrate that GTFA-Net significantly outperforms traditional TFA methods in terms of noise immunity, energy concentration, and instantaneous frequency extraction accuracy, making it a promising solution for high-precision indoor target tracking.Keywords
Funding Information
- Special Foundation for Hunan Innovation Province Construction (2020RC3004)
- Hunan Provincial Postdoctoral Science Foundation (2026JJ50222)
This publication has 42 references indexed in Scilit:
- RSSI-based location fingerprint method for RFID indoor positioning: a reviewNondestructive Testing and Evaluation, 2023
- Synchrosqueezing transform meets -stable distribution: An adaptive fractional lower-order SST for instantaneous frequency estimation and non-stationary signal recoverySignal Processing, 2022
- Gaussian-modulated linear group delay model: Application to second-order time-reassigned synchrosqueezing transformSignal Processing, 2020
- Locally Optimized Adaptive Directional Time–Frequency DistributionsCircuits, Systems, and Signal Processing, 2018
- Sparsity-Aware Adaptive Directional Time-Frequency Distribution for Source LocalizationCircuits, Systems, and Signal Processing, 2018
- Instantaneous frequency estimation based on synchrosqueezing wavelet transformSignal Processing, 2017
- Multi‐component instantaneous frequency estimation using locally adaptive directional time frequency distributionsInternational Journal of Adaptive Control and Signal Processing, 2015
- Principles of time–frequency feature extraction for change detection in non-stationary signals: Applications to newborn EEG abnormality detectionPattern Recognition, 2015
- Modulation Theory2006
- Signal-dependent time-frequency analysis using a radially Gaussian kernelSignal Processing, 1993