Way to Brain-Computer Interface and Convolutional Neural Networks

Part 1:The big picture of brain-computer interface and AI + Research papers

Part 2:
In-depth explanation of neural networks used with BCI

DEFINATION OF Brain-Computer Interface and Convolutional Neural Networks:

Brain-Computer Interface (BCI): devices that enable its users to interact with computers by mean of brain-activity only, this activity being generally measured by ElectroEncephaloGraphy (EEG).

Electroencephalography (EEG): physiological method of choice to record the electrical activity generated by the brain via electrodes placed on the scalp surface.

Functional magnetic resonance imaging (fMRI): measures brain activity by detecting changes associated with blood flow.

Functional Near-Infrared Spectroscopy (fNIRS): the use of near-infrared spectroscopy (NIRS) for the purpose of functional neuroimaging. Using fNIRS, brain activity is measured through hemodynamic responses associated with neuron behaviour.

Convolutional Neural Network (CNN): a type of artificial neural network used in image recognition and processing that is specifically designed to process pixel data.

Visual Cortex: part of the cerebral cortex that receives and processes sensory nerve impulses from the eyes

What are these brain-computer interfaces actually capable of?

brain neurone is connected with computer

It depends who you ask and whether or not you are willing to undergo surgery. “For the purpose of this thought-experiment, let’s assume that healthy people will only use non-invasive BCIs, which don’t require surgery. In that case, there are currently two main technologies, fMRI and EEG. The first requires a massive machine, but the second, with consumer headsets like Emotiv and Neurosky, has actually become available to a more general audience.” 

Conclusion

In this paper, we have presented a novel approach that combines deep learning with the EEG2Code method to predict properties of a visual stimulus from EEG signals. We could show that a subject can use this approach in an online BCI to reach an information transfer rate (ITR) of 1237 bit/min, which makes the presented BCI system the fastest system by far. In a simulated online experiment with 500,000 targets, we could further show that the presented method allows differentiating 500,000 different stimuli based on 2 s of EEG data with an accuracy of 100% for the best subject. As the presented method can extract more information from the EEG than can be used for BCI control, we discussed a ceiling effect that shows that more powerful methods for brain signal decoding do not necessarily translate into better BCI control, at least for BCIs based on visual stimuli. Furthermore, it is important to differentiate between the performance of a method for decoding brain signals and its performance for BCI control.