Target Recognition for Ultra-Wideband Radio Fuzes Using 1D-CGAN-Augmented 1D-CNN
Abstract
1. Introduction
2. Methodology
2.1. UWB Fuze
2.2. Experimental Echo Signal Acquisition
2.3. GAN-Based Synthetic Echo Signal Generation
2.4. Quality of Synthetic Echo Signal
2.5. Signal Preprocessing
- Additive white Gaussian noise , )
- Single-tone interference at 1 GHz (amplitude = 0.2)
2.6. Target Recognition Algorithm
- (1)
- Unified test set (10 signal sequences): 470 samples for model validation;
- (2)
- Original training set (40 sequences): 1880 annotated samples;
- (3)
- 1D-CGAN-augmented set (140 sequences): 6580 annotated samples.
3. Results and Analysis
3.1. Comparison with Other Models
3.2. System-Level Performance Evaluation
- (1)
- Miss detection: All target-present segments in a complete signal are misclassified as ‘Label 0’.
- (2)
- False alarm: Any target-absent segment misclassified as ‘Label 1’ prior to the first true target segment.
- (3)
- Fuze detonation position: The system triggers the fuze immediately at the temporal position corresponding to the first segment classified as ‘Label 1’. The classification of all subsequent segments is irrelevant once the detonation signal is issued.
4. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Data Availability Statement
Conflicts of Interest
References
- Cui, Z.Z.; Song, S.H. Principle of Proximity Fuze; Beijing Institute of Technology Press: Beijing, China, 1998. [Google Scholar]
- Zhang, H. Development of ammunition for the demand and promotion of fuze technology. J. Ordnance Equip. Eng. 2018, 39, 1–5. [Google Scholar]
- Zhou, Y.; Cao, R.; Li, P. A target spatial location method for fuze detonation point based on deep learning and sensor fusion. Expert Syst. Appl. 2024, 238, 122176. [Google Scholar]
- Li, M.; Huang, Z.H. Research on Relation between Sampling Pulse Width and Output Signal Amplitude for Ultra-wideband Radio Fuze. Acta Armamentarii 2016, 37, 1989. [Google Scholar]
- Wu, K.W.; Yang, B.; Hao, S.J.; Liang, Y.B.; Huang, Z.H. Modulated radio frequency stealth waveforms for ultra-wideband radio fuzes. Entropy 2024, 26, 605. [Google Scholar] [CrossRef]
- Raza, A.; Wang, H. Effect of land clutter on burst height of radio proximity fuze. In Proceedings of the International Bhurban Conference on Applied Sciences and Technology, Islamabad, Pakistan, 13–17 January 2015; pp. 612–616. [Google Scholar] [CrossRef]
- Gao, J.; Wu, R.; Zhang, J. An adaptive multi-target jamming waveform design based on power minimization. Entropy 2020, 22, 508. [Google Scholar] [CrossRef]
- Gan, L.; Xiong, K.; Liao, M.; Yu, X.; Cui, G. Cognitive jammer time resource scheduling with imperfect information via fuzzy q-learning. IEEE Trans. Aerosp. Electron. Syst. 2025, 61, 7422–7434. [Google Scholar] [CrossRef]
- Sun, Y.; Gong, S.; Mao, Y.; Dong, Y.Y.; Dong, C.X. Online unsupervised generative learning framework based radar jamming waveform design. IET Radar Sonar Navig. 2023, 17, 1441–1455. [Google Scholar]
- Yan, X.P.; Wang, K.; Liu, Q.; Hao, X.H.; Yu, H.H. Jamming Signal Design of Pseudo-code Phase Modulation FuzeBased on Duffing Oscillator. Acta Armamentarii 2022, 43, 729–736. [Google Scholar]
- Dong, E.W.; Hao, X.H.; Yan, X.P.; Yu, H.H. Research on Interference Mechanism of Swept-frequency Jamming to UWB Radio Fuze. Acta Armamentarii 2023, 44, 1006–1014. [Google Scholar]
- Wang, X.; Zhang, S.N.; Zhu, L.Z. Research on anti-Narrowband AM jamming of Ultra-wideband impulse radio detection radar based on improved singular spectrum analysis. Measurement 2022, 188, 110386. [Google Scholar]
- Chen, S.; Zhao, H.C.; Zhang, S.N.; Yang, Y.X. Study of ultra-wideband fuze signal processing method based on wavelet transform. IET Radar Sonar Navig. 2014, 8, 167–172. [Google Scholar] [CrossRef]
- Digulescu, A.; Despina-Stoian, C.; Popescu, F.; Stanescu, D.; Nastasiu, D.; Sburlan, D. UWB Sensing for UAV and Human Comparative Movement Characterization. Sensors 2023, 23, 1956. [Google Scholar] [CrossRef] [PubMed]
- Qian, P.F.; Qin, G.L.; Chen, Q.L.; Hao, X.H. A recognition method of radio fuze signal based on supervised contrastive learning. J. Beijing Univ. Aeronaut. Astronaut. 2025, 51, 953–961. [Google Scholar]
- Wu, J.; Zhang, X.Q. A Target Classification Optimization Recognition and Information Extracting Method of Laser Fuze Detection System Based on Fuzzy C-Means Incremental Update and Neural Network. IEEE Access 2023, 11, 131168–131177. [Google Scholar] [CrossRef]
- Khan, I.; Guerrieri, A.; Serra, E.; Spezzano, G. A hybrid deep learning model for UWB radar-based human activity recognition. Internet Things 2025, 29, 101458. [Google Scholar] [CrossRef]
- Nosrati, L.; Semnani, S.H.; Fazel, M.S.; Rakhshani, S.; Ghavami, M. Improving Indoor Localization Using Mobile UWB Sensor and Deep Reinforcement Learning. IEEE Sens. J. 2024, 24, 32546–32553. [Google Scholar] [CrossRef]
- Yang, B.; Li, J.; Shao, Z.P.; Zhang, H. Self-Supervised Deep Location and Ranging Error Correction for UWB Localization. IEEE Sens. J. 2023, 23, 1. [Google Scholar] [CrossRef]
- Brishtel, I.; Krauss, S.; Chamseddine, M.; Rambach, J.R.; Stricker, D. Driving Activity Recognition Using UWB Radar and Deep Neural Networks. Sensors 2023, 23, 818. [Google Scholar] [CrossRef]
- Wang, A.; Xue, D.; Wu, H.; Iwahori, Y. Lidar data classification based on improved conditional generative adversarial networks. IEEE Access 2020, 8, 209674–209686. [Google Scholar] [CrossRef]
- Han, L.; Feng, C.; Hu, X. Space targets with micro-motion classification using complex-valued gan and kinematically sifted methods. Remote Sens. 2023, 15, 5085. [Google Scholar] [CrossRef]
- Liu, F.; Li, Y.; Zheng, Y. Time Series Data Generation Method with High Reliability Based on ACGAN. Entropy 2025, 27, 111. [Google Scholar] [CrossRef] [PubMed]
- Li, S.Y.; Li, Q.C.; Li, M.F.; Lv, Y.C. Improved deep learning intrusion detection model based on GAN data enhancement. J. Intell. Fuzzy Syst. 2024, 49, 125–139. [Google Scholar] [CrossRef]
Model | Flops |
---|---|
1D-ResNet | 9,654,508 |
1D-CNN | 1,375,036 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2025 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Wu, K.; Hao, S.; Liang, Y.; Yang, B.; Huang, Z. Target Recognition for Ultra-Wideband Radio Fuzes Using 1D-CGAN-Augmented 1D-CNN. Entropy 2025, 27, 980. https://doi.org/10.3390/e27090980
Wu K, Hao S, Liang Y, Yang B, Huang Z. Target Recognition for Ultra-Wideband Radio Fuzes Using 1D-CGAN-Augmented 1D-CNN. Entropy. 2025; 27(9):980. https://doi.org/10.3390/e27090980
Chicago/Turabian StyleWu, Kaiwei, Shijun Hao, Yanbin Liang, Bing Yang, and Zhonghua Huang. 2025. "Target Recognition for Ultra-Wideband Radio Fuzes Using 1D-CGAN-Augmented 1D-CNN" Entropy 27, no. 9: 980. https://doi.org/10.3390/e27090980
APA StyleWu, K., Hao, S., Liang, Y., Yang, B., & Huang, Z. (2025). Target Recognition for Ultra-Wideband Radio Fuzes Using 1D-CGAN-Augmented 1D-CNN. Entropy, 27(9), 980. https://doi.org/10.3390/e27090980