Adaptive Temporal-Segment Inference and Statistical Test-Time Adaptation for UAV RF Recognition
Open Access
Abstract
Unmanned aerial vehicle (UAV) control signals are often bursty or utilize frequency hopping, so the evidence available in a spectrogram varies over time. We study confidence-adaptive multi-segment early exit (CAMSE) and separately evaluate online statistical adaptation of batch normalization (OSA-BN). CAMSE sequentially processes temporal segments with a shared ResNet18 and stops when the top-two probability margin from averaged logits reaches a stage-specific threshold. Temporal-segment augmentation supports segment-wise inference. An eight-class RFUAV evaluation separates 82 source IQ files into training, tuning, and test partitions. At signal-to-noise ratios (SNRs) from −30 to −22 dB, CAMSE achieves 48.53% accuracy with 2.47 segments per sample, compared with 49.07% for fixed-five fusion, reducing backbone evaluations by 50.51%. Regular-SNR accuracy is 99.52% with 1.06 segments. The whole-image Frozen-BN reference achieves 60.53% extreme-SNR accuracy. Uniform and decreasing thresholds offer different accuracy–computation operating points. In the separate whole-image experiment, OSA-BN raises extreme-SNR accuracy to 76.13% without labels, SNR estimates, or gradient updates. On eight native-noise IQ windows, CAMSE reduces single-thread CPU latency from 498.41 to 378.97 ms relative to fixed-five inference. These results support adaptive stopping within multi-segment processing and statistical adaptation for whole-image recognition.Keywords
This publication has 30 references indexed in Scilit:
- RF-Based UAV Detection and Identification Enhanced by Machine Learning ApproachIEEE Access, 2024
- RF Drone Detection System Based on a Distributed Sensor Grid With Remote Hardware-Accelerated Signal ProcessingIEEE Access, 2023
- Using Early Exits for Fast Inference in Automatic Modulation Classification2023
- Signal Preprocessing Technique With Noise-Tolerant for RF-Based UAV Signal ClassificationIEEE Access, 2022
- RF-UAVNet: High-Performance Convolutional Network for RF-Based Drone Surveillance SystemsIEEE Access, 2022
- Wavelet transform analytics for RF-based UAV detection and identification system using machine learningPervasive and Mobile Computing, 2022
- Drone classification from RF fingerprints using deep residual nets2021
- RF-based drone detection and identification using deep learning approaches: An initiative towards a large open source drone databaseFuture Generation Computer Systems, 2019
- DroneRF dataset: A dataset of drones for RF-based detection, classification and identificationData in Brief, 2019
- Deep Residual Learning for Image Recognition2016