- This topic has 1 reply, 1 voice, and was last updated 6 hours, 15 minutes ago by .
Viewing 2 posts - 1 through 2 (of 2 total)
Viewing 2 posts - 1 through 2 (of 2 total)
- You must be logged in to reply to this topic.
No products in the cart.
Forum › Developers › Projects and Resources › Hosaka v2.0rc4 audiovisual stimulation software using Emotiv
Tagged: audiovisual, emotiv, LSL, Machine Learning, sleep
I have just released Hosaka v2.0rc4 for windows 11. Software optimizes audiovisual stimulation using EEG measurements. You can try to increase sleepiness or set any target state. Software uses LSL protocol which Emotiv supports (you can also test software with –device=random instead of –device=lsl).
Beta software is currently command-line only and one should read README for usage details. You need fast CPU (I use 16-thread AMD CPU) to optimize machine learning models (you need to watch stimulus 10 minutes to 2 hours before software learns something from stimulus (statistical models require lots of data)). Target errors typically cycle around zero because EEG is hard to change significantly but subjective tests seem to cause some sleepiness etc.
Software is freeware.
Downloads: https://www.whiteclinic.net/files/hosaka-2.0rc4-win64.zip
PS. If somebody want to donate me Emotiv Insight so I could better test the software I would be very happy.
Hosaka software example audio which tries to increase sleeping is here: https://soundcloud.com/tomas-ukkonen/sets/digital-sleeping-pill
Software seem to function a bit because it generates relaxing low frequency sounds and not aggressive high frequency sounds. Better results with EEG sync + visual stimulation.