Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in [1].

Open-world Radio Frequency Fingerprint Identification via Augmented Semi-supervised Learning

Authors: Zehua Han, Jing Xiao, Qirui Zhao, Zhexuan Cui, Yufeng Wang, Duona Zhang, Wenrui Ding

AAAI 2025 | Venue PDF | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experimental results on three temporal signal datasets demonstrate that our method effectively recognizes both the known and unknown classes, outperforming several state-of-the-art methods by a large margin.
Researcher Affiliation Academia 1 Beihang University 2 Northeastern University 3 North China University of Technology EMAIL, EMAIL
Pseudocode No The paper describes methods and processes in narrative text and mathematical formulations but does not include any clearly labeled pseudocode or algorithm blocks.
Open Source Code Yes Code https://github.com/Shua S2020/Open RFI
Open Datasets Yes Additionally, to verify the generalization of our open-world method, we also test Open RFI s performance on the UCIHAR dataset, which contains 6 classes of human activity recognition data, and the SHAR dataset, which contains 17 classes of human activity recognition data.
Dataset Splits Yes When using the self-supervised learning framework Sim CLR (Chen et al. 2020) to pre-train a model on a dataset, we split all data into training, validation, and test sets in a 6:2:2 ratio.
Hardware Specification No The paper does not provide specific hardware details such as GPU/CPU models, memory amounts, or detailed computer specifications used for running its experiments.
Software Dependencies No The paper refers to frameworks and models like Sim CLR, Open NCD, Informer, and Transformer but does not specify programming languages, libraries, or other software dependencies with version numbers.
Experiment Setup Yes In the Open RFI setting, the number of prototypes is generally much larger than the number of actual classes. Here, we set the number of prototypes to be ten times the number of known classes. The dimension of the instance features obtained from the pre-trained model is set to 32. The temperature parameter τs is set to 0.05. The batch size is set to 128, and the learning rate for the Adam optimizer is 0.002.