gxhen / lora_rffi Goto Github PK

Dear author, thanks for your generous contribution. There is a s error in readme.md in Opensrt RFFI TIFS. While in the Load Datasets section, dev_range = np.arange(30,40, dtype = int) is wrong. Because you use the dataset_training_aug.h5 which only includes dev from 1-30, may be it should be corrected instead of confused others.

Hi, did the dataset go through the Normalisation operation?

We tried to replicate your results and use your code for our own implementation but there is a little misunderstanding on your the dataset.

1. On the git report readme there are 23 subdasets but only 19 in the dataset download link. The extracted zip file yield 19. Have we missed anything?

2. The training_aug.h5 has 1000 samples with labels as 0. Each h5 file in the readme should have N labels as specified in the data structure of the readme. I guess we have misunderstood you, could you clarify a little bit?

3. For the training in the code you passed the path to the training_aug.h5 file which has only one class. Except that we missed something it will be meaningless to train with just one label. Did you therefore generate your training dataset by merging the three sub datasets? (training_aug.h5, training_0hz.h5 and training_no_aug.h5)

I have read your latest paper about RFFI and I think your idea is great, but I can't figure out the meaning of the function of identity_loss.
The line 32 of this url https://github.com/gxhen/LoRa_RFFI/blob/main/Openset_RFFI_TIFS/deep_learning_models.py

When I introduced this dataset to my colleagues as utilising the preamble part from the device in LoRa , everyone was confused. Because the preamble part is not the same for different devices, we can directly use the preamble part for device identification, so why do we need to train the model to identificate.

hi , I want to know the difference between Closed_set_RFFI and Openset_RFFI_TIFS