RadioML 2016.10a
A public wireless signal dataset widely used in automatic modulation classification research, containing I/Q samples of multiple modulation types at various signal-to-noise ratios.
Timeline (last 90 days)
FuseAMC is a lightweight decision fusion model that achieves performance surpassing each of its baselines on the RadioML 2016.10a dataset, and the entire pipeline requires only a single CPU core to train and run.
On the RadioML 2016.10a dataset, using 5 random seeds and a held-out test set of 44k frames, FuseAMC achieves 55.8% overall accuracy.
The RadioML 2016.10a dataset is released by DeepSig and contains 11 modulation types (such as BPSK, QPSK, 8PSK, 16QAM, 64QAM, GFSK, etc.), with SNR ranging from -20dB to +18dB, and each frame consists of 128 complex samples (I/Q two channels).
The RadioML 2016.10a dataset consists of synthetic simulated signals and does not cover multipath, frequency offset, and hardware impairments of real channels, so the absolute accuracy values obtained on this dataset should not be directly extrapolated to actual deployment scenarios.
All Facts (4)
FuseAMC is a lightweight decision fusion model that achieves performance surpassing each of its baselines on the RadioML 2016.10a dataset, and the entire pipeline requires only a single CPU core to train and run.
50%UnverifiedOn the RadioML 2016.10a dataset, using 5 random seeds and a held-out test set of 44k frames, FuseAMC achieves 55.8% overall accuracy.
50%UnverifiedThe RadioML 2016.10a dataset is released by DeepSig and contains 11 modulation types (such as BPSK, QPSK, 8PSK, 16QAM, 64QAM, GFSK, etc.), with SNR ranging from -20dB to +18dB, and each frame consists of 128 complex samples (I/Q two channels).
50%UnverifiedThe RadioML 2016.10a dataset consists of synthetic simulated signals and does not cover multipath, frequency offset, and hardware impairments of real channels, so the absolute accuracy values obtained on this dataset should not be directly extrapolated to actual deployment scenarios.
50%