Open
Conversation
Contributor
Author
|
Looks like classifier works best with sklearn 0.17 (ubuntu 15.10 has older, can be upgraded by pip). But needs adjusting probability level of decision. Tester works quite well. You can use this script to prepare some EEG recording for playback though synthetic_generator. (Launch in commandline with adress to recording ex: python prepare_signal.py ./dataset/test.obci filename without .raw or .xml Accepted tag format:
should appear. You should provide path to them in the scenario settings of the synthetic stimulator. |
starting to transfer to new architecture Offline calibration works! Looks like works online
typos
reworked sound on pyo
| try: | ||
| import pyo | ||
| except ImportError: | ||
| print ('ERROR no sound library.\n\t\t Installl pyo!\n\t\tsudo apt-get install python-pyo') |
Contributor
There was a problem hiding this comment.
sys.exit is probably missing here?
…w can ignore some ids
…ion, logic peers, mx rules
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Only discussion for now, don't merge...
Added P300 classifier, added tester peer for p300 classifiers - it sends synthetic signals with p300 (gaussians) burried in noise, simulating N-fields of p300 gui. While sending targets it sends nontarget tags too, simulating highlights of other fields, while focus of the "person" is on target field. Then it saves statistics such as - selected field (focus), how many targets were sent for selection of that field and response from classifier
For now there is no jitter, it can be added quite easily, and I thinking about adding possibility to send real epochs instead of simulated gaussians, and noise in between.
Mine classifier with some quite high noise makes no mistakes while needing 2-4 averages, that's strange.
You can test it yourself, if you use attached data for training. (P300 offline calibration scenario)
And then run P300 online synthetic test for testing and saving statistics. Like those:
synthetic_results_dec_stop2.txt
test1.obci.raw.zip
WIP any coments are welcome.