Science topic

Brain Computer Interfaces - Science topic

Community for researchers who work with or are interested in BCIs and their applications.
Questions related to Brain Computer Interfaces
  • asked a question related to Brain Computer Interfaces
Question
4 answers
The software could aid visualization and data capture from the EEG sensing device transferring data through Bluetooth connection.
Relevant answer
Answer
Hi,
There are several ways to do this.
1. EEGLAB with MATLAB
2. LabVIEW
Use Instrument I/O > Instr Asst > NI DAQmx
Best regards
Elias
  • asked a question related to Brain Computer Interfaces
Question
2 answers
The BCI system does not have a particular application, it's just based on working with cognitive tasks. But there's doubt in what tasks to use and why
Relevant answer
Answer
Besides on the comments that are going to be posted, I would consider that feedback and response times are important metrics in the implementation of an effective BCI. You do not want to have something that reacts almost real-time with the use of a system that can only provide slow action, remember that the brain activity in EEG is measuring the activation of a certain group of neurons, located at a specific location based on specific stimuli and it takes an important amount of time to achieve that with untrained subjects.
In such sense, the feedback method has to be selected carefully based on the previous literature reviews. The response has to be corrected from any errors based also in the measuring methods. EEG is most common for low-cost research but I highly doubt you will end up doing MEG, Spikes or ECoG without the participation of a big laboratory.
Hope this information could be useful...
  • asked a question related to Brain Computer Interfaces
Question
4 answers
I got curious about the zero-padding of EEG signals, if I have two events that mark an area of interest, and I cut these specific areas of interest, they differ in their length by a few samples.
So, if I wanted to make all the epochs the same length, can I pad them with zeros or will that affect the overall results?
To be more specific, if the sampling rate is 500Hz and the area of interest is supposed to be 2 seconds long, so I expect to have 1000 samples, but I end up with 970 or 1100 samples, what would be the best approach to make them all the same length?
Thank you in advance.
Relevant answer
Answer
Padding means the addition of bits. Hence, padding may affect the classification.
  • asked a question related to Brain Computer Interfaces
Question
4 answers
Currently, I am a Ph.D. candidate pursuing the development of innovative projects related to Biomedical Engineering and Mechatronics fields. In the last 7 years, I was deeply involved in the theoretical and experimental research of the Brain-Computer Interface to achieve the implementation of simple to use, appealing, and cost-efficient real-life applications by using portable headsets that should be valuable for people with neuromotor disabilities. Until now, taking into account different limitations, I focused on detecting voluntary eye-blinking as controlling signals in Brain-Computer Interface applications.
Relevant answer
Answer
J. Rafiee, thanks a lot for the information. I will give it another try and if it is necessary, I will describe my technical issues to those web communities.
  • asked a question related to Brain Computer Interfaces
Question
5 answers
I am studying Information Engineering in an applied sciences university in Hamburg, Germany. I am starting my bachelor thesis next semester but I'm lost and I can't decide for an interesting topic to me which is suitable for a bachelor project.
In general I am interested in Biomedical engineering, especially in Brain Computer Interface after I did some reading on the topic. Do you have any simple projects ideas related to this field?
Many thanks to you.
Relevant answer
Answer
You may be attracted by the idea of development a simple Brain-Computer Interface application for controlling a real-life device, even a smartphone, or a simulation involving a mechatronic system, such as a multifunctional robot aimed for helping people with disabilities.
  • asked a question related to Brain Computer Interfaces
Question
4 answers
Hello,
I am currently working on a project with a colleague that uses EEG data to classify emotions using the circumplex model (i.e. valence/arousal). We plan to use the DEAP dataset for emotion calibration. However, one difference my colleague and I had was whether:
  • Pre-recorded EEG data from the DEAP dataset can be directly used to train a classifier? OR
  • Is it necessary to record participant's live EEG data, while being instructed to view items from the DEAP database to effectively categorize emotions with a classifier?
One issue I had is that pre-recorded EEG data from the DEAP database would not be as accurate for classification as having a group of participants view items from the DEAP database, while EEG activity is being recorded. However, my colleague suggests that recording raw EEG data from participants will be too time-consuming, and less effective. Does anyone familiar with EEG and emotion classification have any insights? Any suggestions are appreciated.
DEAP dataset
Relevant answer
Answer
Eric Andrews Thank you for your informative response. Initially, we are attempting to reproduce an emotion classifier, moreso replicating existing models. Eventually, we intend to use the emotion classifier to generalize to new participants with a generative music algorithm.
Hence, the emotion classifier may not need to be trained on new participants if the bootstrapping approach you mentioned works. However, eventually, we intend to recruit participants that can feed through the model, and then be sent to a generative algorithm. A good summary of this attached (Ehrlich, 2019):
The only difference would be our design does not use an LDA model for emotion classification, as I believe Ehrlich's design does. We also need access to DEAP pre-processed data. We only have it within one of our classifier datasets. Do you have any idea how the preprocessed MATLAB data can be accessed?
  • asked a question related to Brain Computer Interfaces
Question
5 answers
Hello,
I am currently working on a project with a colleague using a Brain-Computer Music Interface (BCMI) to generate music from EEG signals. Affective states will be recorded with EEG signals and sent to a generative music algorithm. A couple of questions I had about the design:
1). We plan to use Emotiv Epoc+ (14 channels), does anyone know any way to run raw EEG data on EEGLAB in real-time, or must EEG data be recorded with external data acquisition software, and analyzed separately?
2). To run the generative music algorithm, is it necessary to train a classifier to model emotion? Can a SVM or random-forest classifier be used to classify emotion from EEG signals, which can then be fed into the generative music algorithm? Or is this step unnecessary?
3). We plan to use the DEAP dataset for emotion calibration. However, one difference my colleague and I had was whether:
  • Pre-recorded EEG data from the DEAP dataset can be sent directly into the generative music algorithm? OR
  • Is it necessary for participant's EEG data to be recorded, while being instructed to view items from the DEAP database to gauge their affective brain states?
DEAP dataset
The generative algorithm is inspired by Ehrlich et al. (2019), and is designed to generate sounds reflective of the user's affective state.
Relevant answer
Answer
Hi I have been playing with BCI for music (using a Neurosky Mindwave headset until we can get the Emotiv one) and used BrainwaveOSC (it is open source on GitHub) to turn the EEG data into OSC. I found a MaxMSP patch to turn the OSC into MIDI, but not yet got it working. Would love to hear more about your work!
  • asked a question related to Brain Computer Interfaces
Question
3 answers
For Image classification tasks there are may existing techniques to overcome class imbalance problem. Can any one please suggest the best possible way to overcome Class Imbalance in Epoched EEG data?
Relevant answer
Answer
The first thing that comes to mind then would be playing with class weights. Simply assign a greater weight to the minority class so that the penalty of a misclassification is comparable to that of the majority one.
If you are using Keras it should be straightforward: store the class-weight mapping in a dictionary and feed to the model when calling .fit() with the class_weight argument.
In PyTorch you can do the same by passing the weights to the loss function via the weight argument.
If you haven't tried, give it a shot and good luck!
  • asked a question related to Brain Computer Interfaces
Question
5 answers
After designing an estimator aiming to predict attention state from EEG, it has been thought to implement it in a neurofeedback in virtual reality.
However, due to the covid related issues, it is very difficult to plan a big study with a large number of participants (as often the case in related research projects). I was wondering if it could be interesting to consider a study (or pre-study) with a small number of participants?
Relevant answer
Answer
Hi Victor!
I think the number of patients depends on what you want to demonstrate. If you are looking for a preliminary study, with few patients you can sense the magnitude of the effect of your intervention. After this preliminary study, you can calculate better the number of patients you need to robustly demonstrate an effect of neurofeedback.
Moreover, you must keep in mind the statistical analysis is different if you have few or more patients.
Best regards,
Jorge de Francisco
  • asked a question related to Brain Computer Interfaces
Question
3 answers
Hi,
I am working in brain computer Interface application. Is there any possibility to extract features through reinforcement learning. can you please guide me with some tutorials and materials.
Relevant answer
Answer
yes you can use reinforcement and other techniques in the extraction process and even you can doing a hybrid classification in the extraction feature process
  • asked a question related to Brain Computer Interfaces
Question
2 answers
Greetings RG community,
I have been working on a pipeline for the classification of EEG motor imagery signals. This is currently being done on the Giga Science MI dataset with 52 subjects, using all 64 EEG channels. The question can be isolated to my first preprocessing step involving ICA by way of Hyvarinen's fast fixed-point algorithm. If I develop spatial filters (vectors of the unmixing matrix) using only the intended training data, is it a violation of appropriate protocol if I then project all raw data (which includes testing data) on these vectors in an attempt at blind source separation? The nuanced thing that brings about concerns is that the raw data is provided in two matrices each containing LH+RS and RH+RS signals (LH = left hand; RH = right hand; and RS = resting state). If the spatial filters wL and wR were constructed using the LH and RH training data respectively, then the original raw data of the LH and RH matrices (including both training and testing data) were projected into these directions prior to the partitioning of trials, is this considered using knowledge of the classes thereby rendering the entire analysis ineffective? At first, I thought I was in the clear because class labels were not used as ICA is unsupervised, now I think it pertinent to ask someone that may have experience in this field.
My results were great under these conditions (perhaps this would be obvious). To check if I could replicate results a different way, I vertically concatenated the LH and RH training data (doubling the number of samples in comparison to the conditions described above) and developed a single matrix of spatial filters then projected all original data onto these but the results were poor, indicating a large drop in spatial resolution. Ideally, I would like to develop a single set of spatial filters that can be applied to all data indiscriminately, if anyone has any advice given the situation it would be greatly appreciated. Since this step is being done prior to the partitioning of MI trials, I have considered performing ICA on some vertically concatenated trials after partitioning and was wondering if this would yield good results as I have also read that the resting state signals contain important information for the minimization of mutual information (maximization of differential entropy), so I am uncertain with this approach. I am also in the process of replacing FastICA with SOBI, JADE, and infomax in an attempt to gain higher spatial resolution. Please excuse any off-putting terminology as I recently pivoted from functional protein dynamics recognition and prediction to BCI-EEG motor imagery classification. Feel free to share any thoughts, all advice is welcomed.
Thank you for your time,
Tyler J Grear
Relevant answer
Lutsenko E. V. Diagnostics and forecasting of professional and creative abilities by the method of ACK-analysis of electroencephalograms in the "Eidos" system / E. V. Lutsenko, A. N. Lebedev / / Polythematic network electronic scientific journal of the Kuban State Agrarian University (Scientific Journal of KubGAU) [Electronic resource]. - Krasnodar: KubGAU, 2003. – №01(001). P. 59-61 – - IDA [article ID]: 0010301009. - Access mode: http://ej.kubagro.ru/2003/01/pdf/09.pdf, 0.188 cu. p. l.
EEG forecast the success of psychomotor test while reducing the level of wakefulness: an analysis of the results of the study / T. N. Shchukin, V. B. Dorokhov, A. N. Lebedev, E. V. Lutsenko // Polythematic network electronic scientific journal of Kuban state agrarian University (Scientific journal of Kubsau) [Electronic resource]. - Krasnodar: KubGAU, 2004. – №04(006). P. 290-306. - IDA [article ID]: 0060404022 – - Access mode: http://ej.kubagro.ru/2004/04/pdf/22.pdf, 1,062 cu. p. l.
EEG forecast the success of psychomotor test while reducing the level of wakefulness: a description of the experiment / T. N. Shchukin, V. B. Dorokhov, A. N. Lebedev, E. V. Lutsenko // Polythematic network electronic scientific journal of Kuban state agrarian University (Scientific journal of Kubsau) [Electronic resource]. - Krasnodar: KubGAU, 2004. – №04(006). P. 277-289. - IDA [article ID]: 0060404021 – - Access mode: http://ej.kubagro.ru/2004/04/pdf/21.pdf, 0.812 cu. p. l.
EEG forecast the success of psychomotor test while reducing the level of wakefulness: statement of the problem / T. N. Shchukin, V. B. Dorokhov, A. N. Lebedev, E. V. Lutsenko // Polythematic network electronic scientific journal of Kuban state agrarian University (Scientific journal of Kubsau) [Electronic resource]. - Krasnodar: KubGAU, 2004. – №04(006). P. 268-276. - IDA [article ID]: 0060404020 – - Access mode: http://ej.kubagro.ru/2004/04/pdf/20.pdf, 0.562 cu. p. l.
  • asked a question related to Brain Computer Interfaces
Question
4 answers
I am working on my master thesis of ethics of BCI.
Anyone in this field that could help me with the topic is welcome.
I find the biggest change that has happened during this pandemic to me the intense merging of humans and computers.
Relevant answer
Answer
Hi Ivana,
Additionally, this year there has been a lot of work from IEEE trying to push for a standard which deals with many ethical aspects of the technology: https://standards.ieee.org/content/dam/ieee-standards/standards/web/documents/presentations/ieee-neurotech-for-bmi-standards-roadmap.pdf.
You should check the work of Ricardo Chavarriaga which has produced a lot of awesome research around these topics.
Hope that helps.
Rodrigo
  • asked a question related to Brain Computer Interfaces
Question
1 answer
I am currently trying to figure out how to extract raw data from the Emotiv Epoc+ device. Any help regarding that would be appreciated.
Relevant answer
Answer
Tricky question. Depends on your Epoc+ Version and dongle version. Now Emotiv requires the subscription. So, headset version =<1.1 still works with most of open-source workarounds.
  • asked a question related to Brain Computer Interfaces
Question
2 answers
I am a research scholar working in brain computer interface for DOC patients. I am looking for EEG data set specifically of the patients with consciousness disorder. Could you suggest any references?
Relevant answer
Answer
  • asked a question related to Brain Computer Interfaces
Question
2 answers
In much of the tDCS literature I have reviewed so far, the position of M1 for anodal tDCS is given as coincident with C3/C4. Likewise, the positon of primary somatosensory cortex S1 for cathodal tDCS is given as 2 cm posterior or occipital to C3/C4. But now I am reading "the course of the central sulcus (rolandic fissure) which separates the frontal lobe from the parietal lobe corresponds to thin lines touching CPz-C2-C4 and CPz-C1-C3, respectively, [& actually courses through the centers of C4 & C3, respectively.] The two gyri immediately neighboring the central sulcus are the primary motor cortex (in frontal direction), and primary sensory cortex (in occipital direction)."
If it is true that it is the central sulcus itself that is coincident with the C3/C4 positions and that primary sensory cortex is estimated at approx. 2 cm occipital/posterior, then why is primary motor cortex not estimated as 2 cm frontal / anterior? I have not seen this discussed anywhere in the literature I've reviewed so far.
I am also trying to match up the M1 & S1 homoncular maps with their approximately corresponding electrode positions, understanding that only one electrode position each intended to stimulate all of M1 or S1 is much too coarse for the application we have in mind. Does anyone have a reference they would be willing to share which ideally would match up the 10-20 electrode positions in the vicinity of C3/C4 with their approximately corresponding somatosensory & somatomotor functional homunculi with higher resolution & greater specificity?
Relevant answer
Following
  • asked a question related to Brain Computer Interfaces
Question
2 answers
Quite a few published researchers are using Amrex branded sponge electrodes with banana jack connections for 1x1 low resolution tDCS. We have attempted to use them & have encountered several problems including one serious safety problem.
The electrode in question is a 3" by 3" square non-conductive rubber frame containing conductive wire mesh overlaid with a removable coarse kitchen-type sponge that protrudes out of a 2" by 2" aperture when soaked in saline. The rubber frame is stiff & does not conform well to the curvature of the cranium, especially with smaller subjects. This in turn results in difficulty placing it accurately & reproducibly & also in making good & uniform electrical contact. Though the maximum contact area of the sponge on the scalp is ideally 4 in² (25 cm²), in practice it is considerably less & variable with only a central area of contact which can be approximated as a circular disc inscribed within the 2" by 2" square aperture. This leads in turn to the most serious problem:
Injected current levels up to 2.0 mA are routine in tDCS research. The research community generally accepts a current density limit of .08 mA/cm² for the safety of the subject's skin in contact with the electrode & also to minimize potential damage to the underlying brain tissue. Even if the 2" by 2" sponge made perfect contact with the skin, at the 2.0 mA injected current level the current density limit is reached, exactly, as bulk current density = current / cross-sectional contact area = 2.0 mA / 25 cm² = .08 mA/cm². But these electrodes do not make perfect contact even when the they are secured tightly because of the rigid frames enclosing the sponges. So the contact area is rather less, resulting in the denominator being smaller and the current density necessarily exceeding the safety limit. Even at somewhat lower levels of injected current, taking the variable contact area of the sponges into account, the current density could easily exceed the safety limit. Furthermore, this is a very coarse bulk analysis. Taking nonhomogeneity, edge & corner effects into account, local areas of unacceptably high current density are unavoidable & can be demonstrated convincibly with a more sophisticated analysis (one using finite element methods for example).
Yet another practical problem with these electrodes is they have a strong & pungent odor which research subjects find objectionable, penetrates their hair & endures on the electrodes even after successive washings. If one electrode is placed supraorbitally, as is a common position in tDCS, the obnoxious smell in close proximity to the subject's nose even has the potential to affect the outcome of the experiment because it induces stress & stress-related neurological activity that has the potential to confound results.
Relevant answer
Following
  • asked a question related to Brain Computer Interfaces
Question
6 answers
Dear All,
I want a standard data set of EEG signals for the intent of movements. I want the standard data sets for left, right, front, back, start, and stop movements of alpha, beta, and gamma signals. Please let me know, where can I find the standard data set.
  • asked a question related to Brain Computer Interfaces
Question
1 answer
I'm trying to design an SSVEP scenario and wondering if there are any ways to cross-check if the stimulus frequency is displaying accurately on the LCD screen.
Relevant answer
Answer
It may seem weird but this is what we did. If you have access to a P300 Speller (BCI2000 or OpenVibe) configure the standard 6x6 matrix to use 250 ms ISI. This will give you four stimulations per second. On OpenVibe you can use the standard p300 sample that comes with the installation bundle. You just put somebody to wear you cap or headset and instruct them to pay attention to all the letters. You get the signals from O1 and O2. If you extract all the epochs and average all of them you must see the four bumps. Now what you can do is to go step by step and reducing that value, lower and lower. You can repeat this all over until you have two good differentiable frequencies by counting the number of bumps on the averaged segments. 60 ms and 80 ms work good. You can bound gradually if you LCD screen refreshing works. Keep in mind that if you run this on Windows, it is not a RTOS, so you can have sometimes weird behavior with the timing. You need a faster computer btw.
Second option: pick an Arduino UNO and LDR light sensor with a couple of resistances. You can write a very easy code to get the light values continuously and transmit them to a serial connected computer. You put the sensor very close to the monitor, and program some UI application to generate the flashing at whatever frequency you want. If everything is OK you will see exact same frequency on the signal obtained from the Arduino and check if the LCD refreshing is OK (https://maker.pro/arduino/tutorial/how-to-use-an-ldr-sensor-with-arduino)
Finally, the attached paper proposed a very detailed procedure to verify exactly all the frequencies from the stimulation and to check if the synchronization is OK.
Hope it helps and good luck !
  • asked a question related to Brain Computer Interfaces
Question
3 answers
Hello. I am thinking of using tDCS to stimulate the motor cortex C3/C4 or the SMA Cz to study possible effects on motor imagery. But I am still undecided which area would be better.
Thank you for any advice.
Relevant answer
Answer
Will you consider to pilot test the effects of stimulating the C3/C4 vs. the SMA using a repeated-measures design by randomizing the order of test stimulations? Test stimulations may be scheduled to be two or three days apart to minimize the learning effect.
  • asked a question related to Brain Computer Interfaces
Question
8 answers
I opened this topic with hopes that someone will share with me some knowledge with regards to starting an R&D company.
Some background:
The focus of the research would mainly be in the neuroengineering field (BCIs in particular).
My expertise is pretty limited on this field of work and mainly focused on software engineering.
I am willing to invest as much time as it takes to learn everything needed for this idea to go forward.
My problems so far:
The budget: I have no idea how much will be required to even start up this thing.
In the short run, I could invest some money myself to keep things going but on the long run that would go down pretty quickly, so I would need to get the budget from somewhere.
Investors are an often heard idea, but, if that's the only way to go, how does one attract them/get in touch with them?
The business knowledge: My lack of knowledge on the business side of things is pretty much scaring me. I have no idea how to even start with this, on a practical way of speaking.
Any ideas on some first baby steps?
I would assume there are other things I haven't even thought about.
So please, if you could share with me some of your thoughts about this topic, I would really appreciate it.
Any guidance would mean the world to me.
Thank you,
Razvan
Relevant answer
Answer
I will try to answer from my own experience with investors and my experience in corporate R&D.
NOTE: This is not to discourage you, but to prepare you for what lies ahead.
Since the goal is a company, here are some things that an angel investor/partner will ask immediately:
From a company perspective
  1. Why should someone invest in you? What qualifies you to lead this venture(e.g. Patents, PhD thesis, previous work experience)? do you have operational/ management experience?
  2. Where is the team that will complement your skill set (financial, operations, technical)?
  3. Are you capable at this stage to secure financial support for at least 2 years?
  4. Are you able to give back 400% return on investment during that window to an angel investor for his exit window?
  5. How many rounds of investment will the company need to be able to achieve production(and when will it be profitable)?
  6. How will you balance learning with production deadlines?
  7. If the venture fails are you willing to part from all the code and intellectual property that you have developed?
  8. Who will be your customer? Do you know your customer's needs? What is the cost of customer acquisition?
  9. How will you establish the supply chain and the distribution chain?
From a concept perspective
  1. When will the concept be defined?
  2. Is it external brain interface (e.g. EEG) or are they brain implants?
  3. Will it be off the shelf hardware or is there custom production involved?
  4. Does the code require certification standard? How long will it take?
  5. what uniqueness will the product have? Can you secure patents on it?
If yo do not have the answer to these questions you will get is 10% ownership at most. As you answer these questions and you get a qualified team in place the more leverage for capital.
As you can see these are difficult questions at the stage that you are in,my suggestion is that you define the concept work on an MVP (minimum viable product), do a market analysis and get to know your customer (you can use NIST's TDMI as I do for market analysis and Steve Blanks 'customer discovery'). also prepare a project plan and gather the requirements for the resources and once you have the effort in operational terms you can then do a business plan.
Hope this helps
  • asked a question related to Brain Computer Interfaces
Question
3 answers
How to measure the cognitive load from the brain activation.?
i use to use  ERD/ERS% formula to get an indications of any increase of decease of the overall cognitive load, but i would like to know if there is any other way to measure different types of cognitive load (extraneous, intrinsic, germane).?
Relevant answer
Answer
Of course, what constitutes intrinsic or extraneous cognitive load depends on what needs to be learned. For example, if the goal of learning is to comprehend concepts incorporated in some text, using jargon may constitute an extraneous cognitive load.
  • asked a question related to Brain Computer Interfaces
Question
1 answer
Has anyone used a cheap commercially available brain computer interface, such as "NeuroSky MindWave", or "Muse: The Brain Sensing Headband" in the learning process, in gamification? Are works on this topic known?
Relevant answer
Answer
Sorry I have no medical, computing or scientific research expertise. My work is in practical learning and teaching: see ‘Inside Teaching: How to Make a Difference for Every Learner and Teacher’ (Routledge, 2017).
  • asked a question related to Brain Computer Interfaces
Question
6 answers
Why EEG trials recoded for same stimulus is different? For example, the same visual stimulus like 12hz ssvep produces comparable but unique timeseries.
Other than noise, under ideal conditions, should the eeg trial be same?
Relevant answer
Answer
Hi Sai,
The amplitude of SSVEP signals can be modulated by subjects' attention. So as the subject's attention fluctuates during the experiment, you will see SSVEP amplitude change.
Though I believe that the single trial variability mostly come from, except measurement noise and various artifacts, changes in background activity which can be influenced by your alertness, fatigue, mind wandering etc.
  • asked a question related to Brain Computer Interfaces
Question
3 answers
gtec brain cap + Gammabox  + Nihon kodhen input box + Nihon kodhen amplifier. 
If you have experience on this combination please give your comments. (Functionality, Operation, Limitations and Advantages) 
Relevant answer
Answer
I have a similar question. Can you use an off the shelf EEG cap with your existing Nihon Kohden EEG equipment? Thanks
  • asked a question related to Brain Computer Interfaces
Question
6 answers
Are there any freely available Local Field Potential (LFP) datasets available, especially recorded during motor actions?
Relevant answer
Answer
GINis a another great repository - this one in particular has massively parallel data recorded in macaque during motor tasks.
  • asked a question related to Brain Computer Interfaces
Question
29 answers
Nick Lavars, 2017, Rise of the mind-reading machines [online]. Available at: http://newatlas.com/mind-reading-machines-musk-future/48642/. Accessed 05.30.2017
As I moved thru this article, I learnt that this brain-human interface is getting closer to us as a possibility, and the dawn may come when you rise up and machines will reading your minds.
True that it would help people with stroke and we may be able to communicate with them to learn their needs BUT given in the wrong hands it may be a problem as your very personal data will reachable. I am not sure how this will translate in future. For good sometimes but bad may be in the end.
Kindly enlighten me with your views
Relevant answer
Answer
The history of brain–computer interfaces (BCIs) starts with Hans Berger's discovery of the electrical activity of the human brain and the development of electroencephalography (EEG). In 1924 Berger was the first to record human brain activity by means of EEG.
  • asked a question related to Brain Computer Interfaces
Question
1 answer
I wish to purchase a Emotiv Headband for my research purpose. Can anyone suggest me with institutes utilising the same or any other similar setup in India.
Relevant answer
Answer
SRM Institute of Science and Technology having Brain Computer Interface facility in India here is its http://www.srmuniv.ac.in/content/brain-computer-interface-lab link. Few other Institutes are there which you can visit for same purpose like wise National Brain Research Center (NBRC), Center for Neurosciences IISC Banglore and National Institute of Mental Health and Neurosciences Banglore.
  • asked a question related to Brain Computer Interfaces
Question
3 answers
In today’s world using technology, we can get signals of the brain. the question is can we process these signals and obtain meaningful content? (for example, when the target brain is thinking to a number we show that number in a computer)
Relevant answer
Answer
Not yet, but we can right now define normal from abnormal brain response
We can also define ill brain tissue responsible of excessive discharge for example for epilepsy and other neurological disease
  • asked a question related to Brain Computer Interfaces
Question
3 answers
Use of electroencephalogram in the field of Brain computer interface (BCI) has acquired relevance with varied application in medicine, psychology and neuroscience, psychiatric studies to understand the brain state for predicting various brain disorders in clinical settings.
Relevant answer
Answer
Please refer to this open access article and it's wide references. It may help you a bit.
  • asked a question related to Brain Computer Interfaces
Question
4 answers
In 2010, during the Jule Vernes Corner (https://www.itu.int/ITU-T/uni/kaleidoscope/2010/julesverne.html ) my colleague panelist from Japan presented his research in Computer Human Interfaces (BCIs) or Brain-Machine Interfaces (BMIs). Since then the neurotechnology made signifact progress and there are number of implentations.
Relevant answer
Answer
HI Eduard
my personal opinion is that the development of closed-loop responsive/adaptive brain stimulation based on intracranial electrophysiological recordings will be the most exciting and most clinically useful implementation of BCI in the near future.
Using implanted electrodes a neurostimulation device can capture pathological brain activity (e.g. seizure activity/pathological oscillations in Parkinson's disease/Tourette Syndrome or similar) and adjust its stimulation to the therapeutic demand in real-time. The conducted studies are preliminary but the field is expanding rapidly right now.
Have a look here:
Best
Julian
  • asked a question related to Brain Computer Interfaces
Question
2 answers
i intend to work on Brain computer interface using EEG headset by emotiv but i am confused whether i should buy their sdk or not?
Relevant answer
Answer
I believe so, I have to use their software to see all the outputs from the EEG. If you buy it monthly its only $99/month
  • asked a question related to Brain Computer Interfaces
Question
6 answers
I'm a master student of Computer Engineering. I'm interested in BCI (Brain Computer Interface) and I want to write a thesis on this area, but I couldn't come up with a satisfying subject! I'd be glad to hear your suggestions.
Relevant answer
Answer
emotion classification based on brain signal all the best
  • asked a question related to Brain Computer Interfaces
Question
4 answers
Hi,
Has anyone got any reviews on gtec's g.nautilus dry electrode based system, g.USBamp over the g.MOBIlab+ ? I am currently using a 8-channel g.MOBIlab+ with active electrodes and am thinking of upgrading to a 16/32 channel system. I will be using the system for a BCI application.
Thanks.
Relevant answer
  • asked a question related to Brain Computer Interfaces
Question
8 answers
Researchers use machine learning classifiers to predict what brain activity means. My question is" why not just doing "signal processing" to the fMRI data to convert it into 0s and 1s , so we form what the subjected imagined easily and shortly? I just dont get this point
Relevant answer
In fMRI, the signal is modelled with double gamma functions, not waves, which is far more complex. To even increase complexity, the BOLD signal is lagged, and to make things worse, it depends on the brain region and also depends on the individual. Therefore, the signal is spatially blurred and temporarily too. So, you may expect that brain function is much more complex than satellites and TV signal (which is artificially produced). The BOLD signal also encompasses a lot of noise and the non-digitalised signal offers more paths to un-noise the signal (e.g. using smoothing, or trending; what would you get if you smooth a 0s and 1s field map? too contrasted, maybe).
When we do machine learning with neural data, the most difficult part is this one: how to convert the signal into useful features? And most of the proposed methods fail here. For example, using brain data to decode categories of emotions. They just don’t work, even the commercially available ones, not because of the mathematical part, but because of the data preprocessing. Therefore, all contributions are welcome… but I am not really getting why digitalizing the signal would be helpful to understand/model brain functioning. May you elaborate on this? You define a threshold and convert the data into 0s and 1s and…?
Here you may find one strategy that I used in the past to convert the signal into features:
In this case, I averaged the second and third value after stimulus onset (but not digitalized it). I am trying now different strategies that include time stamping in order to model the hemodynamic response (because fMRI’s temporal resolution is not optimal, this is a hard hurdle, because data is scattered).
BTW, the BOLD signal is highly nonlinear! Cheers!
  • asked a question related to Brain Computer Interfaces
Question
3 answers
In ERP/P300 signal analysis, xDAWN is well-known to find the spatial filter.
I have read several reference papers about xDAWN, such as
xDAWN Algorithm to Enhance Evoked Potentials: Application to Brain–Computer Interface
A Tutorial on EEG Signal Processing Techniques for Mental State Recognition in Brain-Computer Interfaces
But I still do not know very well about xDAWN. So far, I know that the first column of D is 0 except the positions of stimuli onset, but how about the other columns? or we do not need to know the others then we can create the Toeplitz matrix?
Would you please give me an example? Where can I find the source code of xDAWN to let me study more about it?
Relevant answer
Answer
This question is old but it is still unanswered, so here I go...
The Toeplitz matrix is just the beginning of the algorithm, and these are just matrices where all the values from the same diagonal have the same constant value. In this case, as you will have a 1 in the first column of the matrix, in the k-th row, every other column will have to have a one on that only diagonal, zero elsewhere. Think of it as the identity matrix "pushed" downwards.
They used it to represent the time-locked delay of the ERP, i.e. how many sample points do you need to wait since the onset of the stimulus until you actually start seeing the ERP. Because you multiply this matrix with A, which is the ERP signal, the result is the A matrix, representing the ERP, pushed also downwards and delayed k units.
I like the idea of "evoked potential algebra" that the authors use in the paper ( )
Page 138 of Lotte's Brain Computer Interfaces 1 book offers a brief explanation of the algorithm that perhaps may help you as well (optimization).
You can find an implementation in OpenVibe's source code and also in the MNE-Python package.
  • asked a question related to Brain Computer Interfaces
Question
3 answers
Anyone who can assist me in doing this project
Relevant answer
Answer
The project looks interesting, may we know details of the project such as the goals or the desired outcomes? Can you also expand on why use brain computer interface for speech emotion recognition? 
  • asked a question related to Brain Computer Interfaces
Question
4 answers
Can anyone provide me Arduino and  Open BCI code for  connecting two external button on 8 channel Open Brain computer interface system ( ADS1299). Please ?
Relevant answer
Answer
Thank You Dibakar Pal, but Link is not working.
  • asked a question related to Brain Computer Interfaces
Question
4 answers
I'm looking for an off-the-shelf device that we can extract data from, in an out-of-lab environment.
Relevant answer
Answer
understood.
thanks again.
  • asked a question related to Brain Computer Interfaces
Question
26 answers
Hi , i am currently working on motor imagery BCI (Brain Computer Interface). I am completely new to this field. I had downloaded data from BCI competition IV (data set -2-b, Left hand and right hand class ). I extracted alpha(8-12)Hz and beta( 14-30) Hz signal using band pass filter for C3 and C4 electrods for different trials , then i calculated average power for all trials. But i dont know how to calculate Event related desynchronization/synchronization ( ERD/ERS) in MATLAB. i dont know ho to calculate baseline power and change in relative power of %ERD/ERS. Can any body tell me how to do in MATLAB, please ?
Relevant answer
Answer
Hi Niraj,
I am also completely new to the field and I can't help you directly  but you should take a look at Mike Cohen's website (http://mikexcohen.com/lectures.html). It has very good lectures on time-frequency based analyses and all the computations are done in Matlab (with downloadable scripts).
Hope it helps
  • asked a question related to Brain Computer Interfaces
Question
3 answers
I am working with the NeuroSky headset and while there are many advantages to using it such as being cheap, portability etc, I would like to know what common problems or limitations other researchers have experienced while using the kit.
Relevant answer
Answer
It depends on the tasks.
  • asked a question related to Brain Computer Interfaces
Question
3 answers
We are currently working on a project which requires to identify a target response in EEG, while the subject is viewing a video stream. During the experiment, the subjects are asked to watch a live feed of video, if a target, let’s say, a target car which has been shown to the subject previously, entered into the screen. Then we try to identify the target induced EEG changes.
As far as the target response is of concern, the RSVP or “oddball” paradigm is usually employed in the existing literature. Did anyone have any experience of using video as stimulus to identify the target response?
Relevant answer
Answer
Hi Yubo,
in addition to the suggestions of Samer and Sam, can it happen that you focuse your search in the occipital channels? (having in mind that visual info in processed in that lobe)...
  • asked a question related to Brain Computer Interfaces
Question
16 answers
I have an EEG data set which is about 5 minutes long for each subject. I want to detect and correct existing artifacts using ICA approach. I can apply this method on the whole data of each person or first epoch this data and then apply ICA on each epoch separately. Which one is more accurate? 
Relevant answer
Answer
ICA algorithms typically take sample*channel matrices. So epoching itself will not have any effect on the results of the algorithm because the data is re-concatenated in most packages/programs (e.g. EEGLAB)  before submission to the algorithm. 
Removing data samples in the form of entire epochs will have an effect on the results of ICA algorithms. Especially if those epochs contain large, unique movement artifacts. ICA algorithms will typically place unique movement artifacts in single components.
It would probably be best to submit all epochs to the algorithm unless there are some egregious movement artifacts in the recording. No EEG will be able to be recovered during periods of large movement artifact.
Was this helpful? I've attached a book chapter for reference. Section 6 contains the relevant discussion. 
  • asked a question related to Brain Computer Interfaces
Question
4 answers
Is it possible to extract the data (neural information) from brain by using Radio waves ?
1. Is the any tech. for Brain computer interface using Radio wave technology.
2. In other words, can we do something by using radio waves to extract data from neurons or knowing about neuron activities.
Technology that's use Radio wave, can help for Brain computer interface?  
Note: if it's possible please suggest me more scientific Article regarding it. 
Relevant answer
Answer
Brain Computer Interfaces typically acquires signals generated from the brain (Neurons) and then extracting some information from those signals. Those are low frequency signals around 0-80Hz. In BCIs no signals are applied onto the brain for getting information.
But there are some other technologies/works that apply signals on brain for different tasks. e.g. "Deep Brain Stimulation" 
  • asked a question related to Brain Computer Interfaces
Question
3 answers
I would like to create realistic visualizations of neural implants (see image attached for a science fiction version) and need some details regarding the electrodes used. Diameter of electrodes is comparable to diameter of large neurons, am I right? Are alway single neurons targeted? Where are the electrodes attached (cell body, axon)? Maybe sometimes groups of neurons are sufficient? And what about measuring in close to vicinity of neurons? Referring to neuronal tissue, what is the percentage of neurons targeted?...
Relevant answer
Answer
Thank you Benjamin and Vladimir for your answers! I am astonished that the considerable progress in neural implants is possible with extracellular recording... I had a similar answer in the facebook neuroscience group, although with slightly different measures (40 - 50 micrometers for large neurocyte cell bodies). And I had information on the spacing of the Utah-array to be about 400 micrometers. From this I concluded that a single electrode might be about 50 micrometers or comparable to a neurocyte cell body and produced the image attached to this post. (Precise measures are not that much important here... And, yes, I am producing these images myself.) I am planning to produce some more specific images displaying neurocytes in the retina and cochlea (and a very similar tip) and composing this to a little news feature on my website (http://news.scivit.com). This should be available in a few weeks. Many thanks again and comments helping improve my visualizations are always welcome,
Thomas
  • asked a question related to Brain Computer Interfaces
Question
2 answers
I want to know how the  blood perfusion values spreads in brain tumors, is that there is a blood flow distribution patterns in some types of brain tumors (for example the value in the contours is higher than the center of the tumor)?
Relevant answer
Answer
Thank you Dirk for your reply, I know there are many types of brain tumors but my goal is to know if there is a distribution  pattern of  blood perfusion  that characterizes some tumors, I not study a specific brain tumor.
  • asked a question related to Brain Computer Interfaces
Question
12 answers
I have performed CSP on EEG data and ended up with a complex projection matrix . Is it normal ? or Am I doing wrong processing ? 
Relevant answer
Answer
The reason could be the that the covariance matrix does not have full rank anymore, e.g., its inverse turns out complex. And a reason for that could be common average electrode spatial filtering. Did you check for this?
  • asked a question related to Brain Computer Interfaces
Question
1 answer
I'm currently thinking of buying the V-probe, but heard a rumor that they are not as reliable as the U-probe. Any comments or experiences with either of these? 
Relevant answer
Answer
Hi Edward,
I have some experience with the U-probe. It's really durable and perfect for repeatedly penetration. I'd say I love this probe if it's not that expensive. One thing I should point out is, due to the low impedance, the signal recorded from U-probe is not as good as regular single electrode (still all right for isolation). 
I have no idea about the V-probe. Presumably they should be similar except the shank. Hope someone else could share their experiences.
-Ji Dai 
  • asked a question related to Brain Computer Interfaces
Question
6 answers
Any possible reasons, explanations will be great!
Relevant answer
Answer
Perhaps there is one good explanation for a focus on midline electrodes: a frequent enrollment of homologous cortices, making for a bilateral signal whose combined field is maximal medially. But other than that, it is generally a mistake to focus only on some electrodes, midline or otherwise. This is true both under the aim of interpreting one signal (its spatial organization is important: even as one can get good measurement of some properties at peak electrodes, the investigation should not stop there), and under the aim of interpreting several simultaneous signals. If your question was tongue-in-cheek, then I share your stupefaction that so many investigators would go through the trouble of preparing, collecting and analyzing 64, 128 or more electrodes, only to redact a report that shows very few of them. A lot of EEG misconceptions are hidden in this limited release of spatial information, such as inappropriately identified rhythmic activity, e.g. an alpha rhythm interpreted as mu just because it has residual power at electrode CZ.
  • asked a question related to Brain Computer Interfaces
Question
5 answers
Hi! I'm looking for books or journals related to the use of brain-computer interfaces in the accessibility area.
Relevant answer
Answer
Also take a look at the Proceedings of ACM ASSETS Conference.
  • asked a question related to Brain Computer Interfaces
Question
5 answers
NIRS to detect sleep patterns.
Relevant answer
Answer
Thanks!
  • asked a question related to Brain Computer Interfaces
Question
2 answers
I am currently trying to employ measures of fractal dimension to analyse EEG data. In particular, the methods proposed by Higuchi, Maragos & Sun, Petrosian, as well as the box-counting dimension.
In one way or another, each method calculates the fractal dimension from the slope of a double logarithmic plot, where the abscissa is given as Ln(1/k) - where k represents a scaling parameter.
However, there appears to be no guidance provided in the literature that suggests which value of k, or how many k points should be used to accurately calculate the FD. 
I appreciate that the choice of the scaling parameter k is specific to each fractal dimension. 
Any advice on how to define the scaling parameter region, either on a global level or for one of the individual fractal measures mention above, would be greatly appreciated.
Thank you in advance,
Matt.
Relevant answer
Answer
I do not know how this question found its way to me.My expertise is topics on psychology and neuroscience.  This program obviously has more work required. 
Sorry. Bob Webb
  • asked a question related to Brain Computer Interfaces
Question
1 answer
Is there any intracranial EEG system available, which is fully implantable - i.e. like the NeuroPace system, but without the responsive stimulation part?
If you are aware of such a product, or of research groups doing advanced research on such a device, I would strongly appreciate your information.
best regards
KS
Relevant answer
Answer
Hello Kaspar Schindler
please check pdfs
  • asked a question related to Brain Computer Interfaces
Question
9 answers
In the complex system of the executive functions the basal ganglia are of great significance. These control cognitive activities such as spatial memories, the execution of motor actions in a specific context and motivational elements of learning. The cortex and the basal ganglia are closely linked and control, also through the cerebellum, the motivational aspects of a movement (the preparation for the action), the contextual aspects (the execution of the movement) and its state of execution. Now, in what way does this complex system generate rapid and unexpected actions?
Relevant answer
Answer
Thanks, Vsevolod! But the question is: how does our brain behave when faced with unforeseen situations, those not determined by innate motor skills? For a long time, little attention was paid to this problem. It was for the most part studied with regard to theories of the executive functions: the functions that allow an individual to design, plan objectives, carry out projects aimed at one purpose, monitor (and if necessary anticipate) his/her own actions to adapt to environmental changes. Numerous sub-skills are included in this sphere which are coordinated between themselves: for example, the inhibition of a response at an inappropriate moment (or its deferral to a more appropriate moment); the implementation of a plan of sequences of action useful for a purpose; the representation of the task that includes relevant information (memorised or perceived immediately) associated with the desired result. The associative cortex of the frontal lobe supervises these functions at three different levels of operation: a) the dorsomedial, assigned with functions of working memory necessary for the selection and maintenance in the memory of the aims of the behaviour; b) the mesial, assigned with the integration of the emotional and motivational aspects necessary for the continuation of the action and c) the orbital, assigned chiefly with the inhibition of behaviour and instinctual impulses. For the effective completion of the movement they collaborate with the frontal lobe, the cerebellum, the basal ganglia and the spinal cord for an effective execution of the movement.
 In this representation, the space for new sequences of action is reserved for lower levels of the motor control, where the procedures for the correction of the errors proceed from a superior to an inferior order and the individual movements are combined in routine and subroutine sequences that lead to the goal directed action. This hierarchical model renders the motor functions subordinate to the higher brain activities and drastically limits the understanding of new sequences of action. 
Catching a flying object, hitting a moving target, pronouncing words with great fluidity or playing a piano, call for such fast times that exclude the possibility of corrections by means of sensory feedback: an action may have success or failure, but due to the time constraints it cannot be correct. In what way, therefore, can the brain achieve such rapid muscle action sequences, to the point of overcoming the temporal limits of the neural circuits?
  • asked a question related to Brain Computer Interfaces
Question
5 answers
Dear group, we're trying to connect 2X32 ch. EEG caps on 1 64ch. device. Does anyone have the experience in what way the ground electrodes should be placed? We can use NuAmps, Deymed or SynAmps EEG devices.
Relevant answer
Answer
Hi Hessel,
The most important part is that you want independent recording to avoid spurious synchrony.
Moreover I do not recommend to have asymmetrical setup. While the GND location on the body is not of great interest (but the convention is earlobe/forehead), just place the GND electrode at the same location for both subject.
Louis
  • asked a question related to Brain Computer Interfaces
Question
2 answers
Hi,
I want to analyze a size volume of intense spots in a MRI data file in FIJI (ImageJ)
I firstly project this file to 3D format using the Stacks -> 3D project tool.
Using the point tool, I can select which intensity should be used for calculating (for which I now only know 3D object counter, but this is a bit messy in my view, options? :) ).
Then using 3D object counter it calculates the amount of available spots.
But now I want only to use part of the 3D scan (which I compiled first) to be able to analyze only the intense spots in the frontal lobe and prefrontal cortex and in the hippocampus.
Is there an easy way to calculate this? (total volume of hyperintense spots in frontal lobe and hippocampus from MRI (.nii) data)
Thanks in advance,
A
Relevant answer
Answer
Hi Mr. Barthel,
Thank you for your answer. Unfortunately the project is already finished. I quantified the volumes manually or using 3D object counter per slice. But I will try your suggestion later.
Regards,
Alexander
  • asked a question related to Brain Computer Interfaces
Question
1 answer
Hi,Hope you are fine. I am a student of Master's in Mechatronics Engineering (Air University "Islamabad Pakistan") and currently doing my research in fNIRS Based BCI (Brain Computer Interface) system. I have gone through Journal Paper “ A regularized discriminative framework for EEG analysis with application to brain–computer interface, Volume 49, Issue 1, pp 415-432,January 2010. In it a new algorithm that unifies feature extraction,feature selection,feature combination and classification is presented. Its very informative and i am trying to get through it but facing difficulty in understanding the algorithm.I only have raw data (which i got from brain). I am a bit confuse how above mentioned features can be unified. It's my humble request that kindly provide the regularized discriminative framework code and helping material which can be used for selection so that I could able to continue my research. I shall acknowledge your work properly and cite by my research papers .Thanks
Relevant answer
Answer
Dear Rayyan! Please try to evaluate some papers in the attachment ro my letter. I hope you will find your own way...
Vladimir
  • asked a question related to Brain Computer Interfaces
Question
2 answers
I used labchart program v.5 for recording EEG signals in anethetized rats. Using lab chart reader v.8 i drew parameters such as maximum power, amplitude, duration, etc. I woul like o know for Quantitative EEG analysis which parameters are best o use?
Relevant answer
Answer
I think the mean amplitude would be the jest one (if I cirrectly underdtand what you mean in your question).
  • asked a question related to Brain Computer Interfaces
Question
3 answers
How to find out ERP component in Prospective memory task after stimulus presentation and which ERP component (Peak) is represent it?
Relevant answer
Answer
Pankaj,
The 2011 review paper from Neuropsychologia is probably the most complete review of the ERP and prospective memory literature. There are some newer studies that have appeared in the last couple of years; however, these have not really introduced new component but rather refined our understanding of components identified in previous research. I have attached a PDF of the Neuropsychologia paper, I hope that you find it useful in your research. Cheers, Rob
  • asked a question related to Brain Computer Interfaces
Question
4 answers
References:
*Kalen et al. 'Age-related changes in the lipid composition...' Lipids 1989; 24: 579-85.
*Alehagen and Aaseth.'Selenium and Q10 interrelationship...' J Trace Elem Med Biol 2015; 31:157-62. 
Relevant answer
Answer
Together with Urban Alehagen, we used a combination of selenium and Q10, but perhaps only the selenium component was responsible for the preventive effect?
 Alehagen, U., & Aaseth, J. (2015). Selenium and coenzyme Q10 interrelationship in cardiovascular diseases–A clinician's point of view. Journal of Trace Elements in Medicine and Biology, 31, 157-162.
  • asked a question related to Brain Computer Interfaces
Question
7 answers
I've been doing some research with Emotiv Epoc, but it has a lot of disadvantages, for example it is almost impossible to evaluate female participants with long hair and small heads - the device does not get any signal from them. Furthermore Emotiv sometimes looses signal from some single electrodes and the quality of the data that it provides is not so great.
Do you know any other low-cost EEG devices that you would recommend for studies regarding emotions?
Relevant answer
Answer
Here's a recent paper evaluating OpenBCI performance relative to other commercial grade equipment. By Jeremy Frey, presented at the BCI Society 2016 meeting this week in Pacific Grove, CA (Asilomar Conference Center).
  • asked a question related to Brain Computer Interfaces
Question
4 answers
Hi,
Is there a publication on dataset 1 describing the class label (original class label) for testing data of BCI competition 3?
Thanks.
Relevant answer
Answer
Dear Akshay Raj Gollahalli 
Goals of the organizers
The goal of the "BCI Competition III" is to validate signal processing and classification methods for Brain-Computer Interfaces (BCIs). Compared to the past BCI Competitions, new challanging problems are addressed that are highly relevant for practical BCI systems, such as
session-to-session transfer (data set I)
small training sets, maybe to be solved by subject-to-subject transfer (data set IVa),
non-stationarity problems (data set IIIb, data set IVc),
multi-class problems (data set IIIa, data set V, data set II,),
classification of continuous EEG without trial structure (data set IVb, data set V).
Also this BCI Competition includes for the first time ECoG data (data set I) and one data set for which preprocessed features are provided (data set V) for competitors that like to focus on the classification task rather than to dive into the depth of EEG analysis.
The organizers are aware of the fact that by such a competition it is impossible to validate BCI systems as a whole. But nevertheless we envision interesting contributions to ultimately improve the full BCI.
Goals for the participants
For each data set specific goals are given in the respective description. Technically speaking, each data set consists of single-trials of spontaneous brain activity, one part labeled (training data) and another part unlabeled (test data), and a performance measure. The goal is to infer labels (or their probabilities) for the test set from training data that maximize the performance measure for the true (but to the competitors unknown) test labels. Results will be announced at the Third International BCI Meeting in Rensselaerville, June 14-19, and on this web site. For each data set, the competition winner gets a chance to publish the algorithm in an article devoted to the competition that will appear in IEEE Transactions on Neural Systems and Rehabilitation Engineering.
  • asked a question related to Brain Computer Interfaces
Question
7 answers
I am doing some literature review on non parametric regression techniques.
I would like to ask those familiar with the topic if you may know the disadvantages and advantages of ANNs compared to other non parametric regression techniques like :
- MARS (Multiple Adaptive Regression Spline)
- Projection Pursuit Regression
- Gaussion Process Models (?)
- Additive Models
Is There Anyone who has a comparative literature on it?
Your Contribution will be of great help.
Relevant answer
Answer
Hi Yves,
Maybe this paper where ANN is compared among other models (MARS, PPR, SVR, RF) is useful to you.
Cheers,
Manuel
  • asked a question related to Brain Computer Interfaces
Question
1 answer
I am working on Neurosky EEG heatset. I can get wave parameters like alpha beta gamma attention meditation levels. as per my survey , researchers work on Brain computer intration (BCI) with eeg signal. I need to know the impact on brain waves in real time wireless sensor network?. 
Relevant answer
Answer
Unfortunately I can not tell you much about the quality of the data sent, which I didn't test (if this is what you mean), but there are more info about the packages in the documentations on the developer website. 
  • asked a question related to Brain Computer Interfaces
Question
2 answers
What the methods or transforms (other than CCA )can be used for SSVEP signal detection?
I am using SSVEP signal for BCI speller.
Relevant answer
Answer
I am working on BCI based SSVEP speller. I am acquiring SSVEP data with the help of flickering block (with a particular frequency) on the computer screen. CCA is the most common method to detect the frequency of the signal.  What can be the other possible classification methods or feature extraction transforms I can apply to detect the accurate frequency of the obtained signal?  and What are the features which can be used for the classification of biomedical  signals?
  • asked a question related to Brain Computer Interfaces
Question
2 answers
So far I found the below equation to measure concentration level but the reference is not that solid and I can not relay on. Any one has other equation or solid reference that support this equation will be highly appreciated.
concentration level = ( (SMR + Beta) / Theta)
where SMR  = SensoriMotor Rhythm
Relevant answer
Answer
Dear Atef!  suggest you get acquainted with the detailed work in this direction. Please read the first one informative article in the application.
  • asked a question related to Brain Computer Interfaces
Question
4 answers
Hello,
I have two volumes:  one structural MRI, and a functional NIFtii atlas. And I need to coregister these two volumes. 
What can be the suitable software to do this task (slicer,  freesurfer)? Slicer is a friendly software with a GUI, but I don't know how much the result is accurate. 
What are your suggestions? 
Relevant answer
Answer
Niftireg is also very good for the kind of registration you want to do.
  • asked a question related to Brain Computer Interfaces
Question
4 answers
I would like to implement the approximated surface Laplacian (SL) estimated using Hjorth Algorithm but I can't find an open literature on the approximation of The SL at scalp edges as suggested in "Spatial Filter Selection for EEG Based Communication" by McFarland et al.
They mention Zhou's work for edge electrodes SL approximation but I do not have access to that literature.
Does anyone have relevant literature on that?
Or Does anyone Know How To Compute The Large Laplacian also called" next nearest neighbor SL" (up to the edge of the scalp)?
Relevant answer
Answer
Hi Yves,
you might want to check out the (open-source) implementation in the FieldTrip Matlab toolbox:
In FieldTrip, Hjorth's method is implemented within the function ft_scalpcurrentdensity, see: http://www.fieldtriptoolbox.org/reference/ft_scalpcurrentdensity
  • asked a question related to Brain Computer Interfaces
Question
7 answers
Has anyone got any reviews and practical recommendations about portable neuroimaging equipment that can be used to record during normal everyday activities?
Relevant answer
Answer
Hi Mitzi,
there are basically only two types of portable neuroimaging techniques, one being EEG (see e.g. products by TMSi, ANT neuro or gtec) the other is NIRS (near-infrared spectroscopy). While the former is measuring electrical brain activity, the latter measures hemodynamic responses. The stationary equivalents would roughly be MEG and fMRI respectively.
For more information about NIRS, see e.g. our website:
We happen to be the world leading company in creating portable NIRS devices, and of course offer great support prior and after sales. See http://www.artinis.com for our product portfolio. For some background literature and reviews, we gathered some relevant papers here: http://www.artinis.com/publications Should you require any of these or would like more information, feel free to contact me.
Disclaimer: Obvisouly, I am working for Artinis Medical Systems.
Edit: I could also tell a story or two about EEG, but I consider the reference to above mentioned companies to be a good starting point for further research.
  • asked a question related to Brain Computer Interfaces
Question
11 answers
I am working on Brain Computer Interface and would like to ask the scientific community if there is an existing mathematical model that can simulate neural adatation of the brain more importantly for application in Sensorimotor rythms based Brain Computer Interface.
Your Input will be of great help.
Thanks.
Relevant answer
Answer
Yves, this paper might be useful to you:
Eliasmith et al (2012) "A Large-Scale Model of the Functioning Brain"
  • asked a question related to Brain Computer Interfaces
Question
2 answers
In EEG classification systems (for BCI), consider two scenarios where
1) Acc = 90%; T = 3 sec; (time window)
2) Acc = 70%; T = 1sec;
ITR for condition 2 is higher than condition 1 even though there is significant decrease in accuracy.
So, is ITR always a better option (than accuracy) to consider the efficiency of model ?
Relevant answer
Answer
If your BCI system is used to control an external device (e.g., a robot), accuracy may be more important. If your BCI system is used for communication, such as a P300-based  BCI speller, ITR may be the better criterion.
  • asked a question related to Brain Computer Interfaces
Question
6 answers
I am struggulling with OpenVine for 3 weeks. I will use P300 magic for visual event related potantial BCI application. Images and backround can be changed easily for request.
1. a. In acquistion.xml data recorded in signal folder. Here subject ID must be exist in data file name. How can I add ID to filename?
b. Acquistion.xml trial and session number in gui are not same as application.
c. Why all images do not stimuli in aquiation.xml ? Only some of them flashes. In acquistion, I think data from all images must be recorded.
d. I tried to convert .ov file in to .csv or .edf as follows, generic file reader and csv/edf writer but it failed.
2. a. In train-classifier.xml file, defaultly generic stream reader reads signal/bcı-p300-signal.ov. Why only one file is used? For example, how can I data from 18 subjects?
b. How can MATLAB classifer be applied in this part?
Please help me.
Relevant answer
Answer
I agree that it may be frustrating when you don't get an answer to your problem, but you have to realize that this is a free and open-source software, meaning people are not making money out of it. So people who answer on the forum or write the documentation have to have the knowledge, motivation and time to do so, as they are doing it for free, purely out of good will...
  • asked a question related to Brain Computer Interfaces
Question
6 answers
Looking for a simple technique/algorithm for artifact correction(not rejection) for analyzing oscillatory processes in EEG signals.
Relevant answer
Answer
There are a variety of ICA algorithms -- some more computationally demanding than others, which can be found here:
Hope this helps,
-Michael
  • asked a question related to Brain Computer Interfaces
Question
20 answers
Where can I get an EEG signal database for emotion detection of neuro or behavioral disorders?
Relevant answer
Answer
Hope the following links will be useful
"In order to obtain the password to access the data please send an email to ashkan.yazdani@epfl.ch"
DEAP dataset:EEG (and other modalities) emotion recognition.
Enterface dataset: This EEG experiment was named "Emotion Detection in the Loop from Brain Signals and Facial Images".
(The file is attached)
  • asked a question related to Brain Computer Interfaces
Question
5 answers
What had been used in the attached journal is the ICMS pattern for the CBI ( Computer Brain Interface). I would be grateful if you let me know is there any instruments or toolbox to generate this pattern. unfortunately I don't have an access to intracellular electrodes so is there any way to simulate BCI signals as invasive?
it might be useful that the experimented animal is rat.
Relevant answer
Answer
High-side digitally current controlled biphasic bipolar microstimulator
Authors
Timothy L Hanson, Björn Ómarsson, Joseph E O'Doherty, Ian D Peikon, Mikhail Lebedev, Miguel AL Nicolelis
Publication date
2012/5
Journal
Neural Systems and Rehabilitation Engineering, IEEE Transactions on
Volume
20
Issue
3
Pages
331-340
Publisher
IEEE
Description
Abstract—Electrical stimulation of nervous tissue has been extensively used as both a tool in
experimental neuroscience research and as a method for restoring of neural functions in
patients suffering from sensory and motor disabilities. In the central nervous system,
intracortical microstimulation (ICMS) has been shown to be an effective method for inducing
or biasing perception, including visual and tactile sensation. ICMS also holds promise for
enabling brain–machine–brain interfaces (BMBIs) by directly writing information into the ...
  • asked a question related to Brain Computer Interfaces
Question
9 answers
In BCI competition III: data set 2 there is 2 subject i.e. subject A and subject B.
In both case there is train data and test data. In training data set there is target character but in test data there is no target character. So, after classification of test data with which I should compare the result?
Relevant answer
Answer
Sure, I have the load_bci function that you need to load the recordings to matlab, it is a standard function of the BCI2000. Please send me a direct message or an e-mail and I'll send you back the info that you need.