Search found 112 matches

by fabien.lotte
Thu Jan 07, 2021 11:19 am
Forum: Discussion about BCI and related topics
Topic: Epoch duration
Replies: 4
Views: 6922

Re: Epoch duration

Dear Ettore, Sorry, I saw that we have not answered yet your questions, sorry for the delay. Regarding the overlap in epochs, indeed, that is the case, in a given epoch there might be presence of ERP to subsequent stimulus. However, that is taken into account when training the XDAWN spatial filter, ...
by fabien.lotte
Fri Dec 11, 2020 11:30 am
Forum: Discussion about BCI and related topics
Topic: P300 accumulator- number of stimulations
Replies: 2
Views: 6143

Re: P300 accumulator- number of stimulations

Dear Ettore, I was not involved in the coding of that specific scenario, so I am not sure I can help much, but I can still try :-). The P300 accumulator accumulates the classifier output for each flash of the P300-speller, for each row or column, in order to find out which row and which column is th...
by fabien.lotte
Wed May 20, 2020 4:03 pm
Forum: Scenarios and BCI design
Topic: is it possible to write a word, a sentence with a p300 scenario?
Replies: 4
Views: 8047

Re: is it possible to write a word, a sentence with a p300 scenario?

I answer your questions below: 1) I understood that for you is better to try now with XDAWN-P300 speller and not with the p300 speller; am I right? Yes indeed, the XDAWN-P300 uses a better signal processing algorithm, so it should be more reliable, more robust 2) I understood that the best Opnevibe ...
by fabien.lotte
Fri May 15, 2020 12:51 pm
Forum: Scenarios and BCI design
Topic: is it possible to write a word, a sentence with a p300 scenario?
Replies: 4
Views: 8047

Re: is it possible to write a word, a sentence with a p300 scenario?

Dear Ettore, Welcome here and thank you for your interest in OpenViBE! Regarding the P300-speller in OpenViBE, indeed, the provided scenario are for "copy-spelling mode" only, that is, the application tells the user what to do and then the user tries to spell the required letters using the BCI. If y...
by fabien.lotte
Thu Jan 07, 2016 5:03 pm
Forum: Discussion about OpenViBE
Topic: Doubt how to configure the Acquisition Server
Replies: 1
Views: 3260

Re: Doubt how to configure the Acquisition Server

In openvibe, the data are sent by chunks (blocks), i.e., samples are not sent one by one from the acquisition server to the designer, but by blocks of several samples (see http://openvibe.inria.fr/acquisition-server/). It is not related to the frequency. The duration (in seconds) of this block depen...
by fabien.lotte
Wed Jan 06, 2016 3:49 pm
Forum: Discussion about OpenViBE
Topic: CSP Spatial Filter Trainer
Replies: 3
Views: 5032

Re: CSP Spatial Filter Trainer

Hello, Sorry for the late reply. There are two things that seem a bit weird in the files you send, and may explain the error: - in the Lua script, there is a line "a = 2b = a+2", and b is undefined. I think b should be defined, and Lua probably does not allow two variable assignment in a row. First ...
by fabien.lotte
Wed Jan 06, 2016 3:40 pm
Forum: Discussion about OpenViBE
Topic: Converting OpenViBE files to Matlab
Replies: 1
Views: 3322

Re: Converting OpenViBE files to Matlab

that will be very useful, thanks a lot!
by fabien.lotte
Thu Dec 10, 2015 9:41 am
Forum: Discussion about OpenViBE
Topic: CSP Spatial Filter Trainer
Replies: 3
Views: 5032

Re: CSP Spatial Filter Trainer

Maybe you could post your scenario so we can know more about what can go wrong?
Also, what messages do you have in OpenViBE console?
by fabien.lotte
Thu Dec 10, 2015 9:40 am
Forum: Discussion about OpenViBE
Topic: Where I find the files OVTK_GDF
Replies: 2
Views: 4291

Re: Where I find the files OVTK_GDF

Hello,

actually these are not files but stimulation codes (i.e., label for events in openvibe). See http://openvibe.inria.fr/stimulation-codes/

Best,
Fabien
by fabien.lotte
Wed Oct 28, 2015 1:49 pm
Forum: Boxes
Topic: Log Classifier Accuracy Measure output
Replies: 1
Views: 3384

Re: Log Classifier Accuracy Measure output

Hi, There is no box yet that sends the classifier accuracy continuously but there should be one in one of the next releases (we are working on it). In the mean time, you can use the confusion matrix box (http://openvibe.inria.fr/documentation/unstable/Doc_BoxAlgorithm_ConfusionMatrix.html), that out...
by fabien.lotte
Mon Aug 24, 2015 12:27 pm
Forum: Scenarios and BCI design
Topic: Saving scenarios as a box
Replies: 1
Views: 2772

Re: Saving scenarios as a box

Unfortunately, this is not yet possible. This is on the list of future features we want to add to OpenViBE, but this is not possible now, sorry for that!
by fabien.lotte
Thu Jul 30, 2015 5:09 am
Forum: Scenarios and BCI design
Topic: How to calculated mental states?
Replies: 2
Views: 3544

Re: How to calculated mental states?

Dear Deepinraw, If I understood correctly, your problem is building and using a classifier to recognise a given mental state based on EEG signals, is that right? If that is so, for your scenario, the problem is that the classifier trainer and the classifier processor are used at the same time (in pa...
by fabien.lotte
Tue Jul 21, 2015 2:12 am
Forum: Boxes
Topic: Filter Bank CSP
Replies: 3
Views: 5032

Re: Filter Bank CSP

There is no box to define a filter bank directly, but you can simply use multiple "temporal filter" boxes, each one designing one of the filter in the bank.
by fabien.lotte
Tue Jul 21, 2015 1:35 am
Forum: Designer
Topic: Subtracting one signal from another
Replies: 10
Views: 11730

Re: Subtracting one signal from another

Hello, I didn't try to create and open your scenario, but to subtract two signals from each other can be done in two ways: - using a spatial filter box, in which case you will give a weight of 1 to channel F3, an weight of -1 to channel F4, and a weight of 0 to any other channel you may have. - or (...
by fabien.lotte
Tue Jul 21, 2015 1:32 am
Forum: Designer
Topic: classifire Accuracy in openVibE
Replies: 1
Views: 3169

Re: classifire Accuracy in openVibE

you used the classifier accuracy measure on the same data in which you trained your classifier is that right? If so, the fact you obtained decreased accuracy may come from the fact that you gave all your data (including the non-control state - i.e., the data between trial that do not correspond to o...