Related Experiment Video
Updated: Feb 28, 2026

Harmonic Radar Tags for Insect Tracking: Lightweight, Low-cost, and Accessible
Published on: May 13, 2025
Research on Multi-Feature Fusion and Lightweight Recognition for Radar Compound Jamming
Weiyu Zha1, Jianyin Cao1, Hao Wang1,2
1School of Electronic and Optical Engineering, Nanjing University of Science and Technology, Nanjing 210094, China.
This study introduces a lightweight network for recognizing radar compound jamming, achieving over 87% accuracy even in low signal conditions. The efficient model is ideal for electronic counter-countermeasure applications.
Area of Science:
- Radar Systems Engineering
- Artificial Intelligence
- Signal Processing
Background:
- Complex electromagnetic environments pose challenges for radar systems due to sophisticated jamming techniques.
- Accurate recognition of compound jamming is crucial for effective electronic counter-countermeasure (ECCM) operations.
Purpose of the Study:
- To develop a lightweight, high-accuracy network for recognizing radar compound jamming under challenging conditions.
- To balance recognition performance with computational complexity for practical ECCM deployment.
Main Methods:
- Utilized three complementary time-frequency representations for multi-feature extraction of compound jamming.
- Employed a multi-branch architecture with attention mechanisms for parallel, multi-scale feature learning and enhancement.
- Integrated features using a weighted fusion strategy and incorporated the lightweight GSENet module.
Main Results:
- Achieved over 87% recognition accuracy for seven compound jamming types under low jamming-to-noise ratio (JNR) conditions.
- The proposed network has a low parameter count, below 0.14 million.
- Demonstrated an effective trade-off between recognition performance and model complexity.
Conclusions:
- The developed lightweight multi-feature fusion network is effective for radar compound jamming recognition.
- The network's efficiency and accuracy make it suitable for real-time ECCM applications.
- The approach offers a viable solution for enhancing radar resilience in complex electromagnetic environments.
Related Concept Videos
IR Frequency Region: Fingerprint Region
Force Classification
Contact and non-contact forces are two of the most widely used categories of forces. As the name suggests, contact forces require physical contact between two objects to act upon each other. Examples of contact forces include frictional,...
Double Resonance Techniques: Overview
Spin decoupling is usually achieved by...
Raman Spectroscopy Instrumentation: Overview
The monochromatic laser source, typically using visible or near-infrared radiation, generates a highly focused beam of light. This light interacts with the molecules of the sample, scattering some of the light. Liquid and gaseous samples are usually tested in ordinary glass capillaries, while solids can be analyzed as powders packed in capillaries or as potassium...
IR Absorption Frequency: Hybridization
Among the sp, sp2, and sp3 hybridized orbitals, sp orbitals have the maximum s character (50%). Consequently, the electrons are held more closely to the nucleus, resulting in stronger and shorter C–H bonds that...
IR Spectrum Peak Splitting: Symmetric vs Asymmetric Vibrations

