Eichhof

I've tried the BAD model with a proba threshold of 0.5 but it is classifying way too many chatbot responses as inappropriate. Can I use the BAD model to classify...

Actually, I have just seen that in eda_process() you pass the raw (unfiltered and unsmoothed) signal to cvxEDA. Am I right?

Thanks for your answer. So you mean cvxEDA or your library implements some form of trend correction?

I have taken the usual features according to literature. HRV featues work much better than EDA featues (perhaps due to the sensor, I don't know). I also has to throw...

Hi Dominique Thank you very much for your fast answer, it is great. In detail, I'm using the following features: EDA: Latency, rise time, recovery time, number of peaks, mean/max/min/std...

Do you have any thoughts on this?

Hi Dominique Thanks, that matkes sense. But when I look at the mean of the phasic component rather than the max amplitude then it makes again sense to baseline correct,...

Thank you for your answer. Do you have some of the papers at hand which you mentioned?

Any help on this?

Thank you very much. In administrator mode I could now build the wheel. I then installed the wheel using pip. The problem now is that when calling `deepspeed.init_inference(...)`, I'm getting...