Computable Minds -

How works the user interfaces that read the mind?

Posted on: Sep, 3rd 2011
Helmet to rea the mind
In the last years has been developed several helmets that allow read the brain, and the software responsible of make a determinate action depending on the thoughts of the user. This is, obviously, a very practical utility for a lot of people disabled and for the vaguest. Would you like to know how works this kind of technology?

- Operation of the hardware:

To read the signals of the brain the hardware used usually is a helmet full of electrodes, and the reason is because the neurons of the brain work with electrical signals. These variable electrical signals generated magnetic fields, also variables, that at the same time can generated electrical signals in conductors near of these magnetic fields (the electrodes of the helmet). The electrical signals arrive to the computer and the software tries of guess what we are thinking.

This kind of electroencephalogram isn’t the better technique to get information from the brain activity. With a magnetic resonance we can get images that allow guess a lot of better the thinking of the person. In fact, a group of Japanese investigators, led by Yukiyasu Kamitani, made a software, that allowed generated in the computer the images in that a person was thinking (the person had to look at a little image and in black and white). The problem is that isn’t technologically viable at the moment do a helmet that performs magnetic resonances.

Also is more effective the technique of put the sensors directly over the brain or in the interior of it, but the invasive techniques neither are comfortable.

- Operation of the software:

The software is implemented doing first a digital treatment of the signal where we take the important parts of it. After is passed by a pattern recognizer, which is a kind of program of artificial intelligence able of learns to identify the characteristics that define something and classify it. In this case learn to classify the signals in a concrete thought.

Normally the number of thoughts selected is very limited, can be, for instance, up, down, left, right. In this way, as the software has fewer options to classify a signal, will do fewer mistakes.

To do that the software learns, first we pass through it some signals and the thoughts that correspond to each one. To this, the user has to concentrate very well in that thought. In this way, the algorithm adjusts the way in that it has to classify each signal in a concrete thought. After, the system is tested with new signals and is made a re-count of the times that fails, to get an error rate of the system that allows decide if the technique of classification used is effective or not.

When finally we will know how interpret the signals of the brain, the next step will be generate thoughts and alternative realities on it, as already have been achieved with devices as the Dobelle’s eye.

Comments (0): Comment
Categories: ,


Copy and paste in your page:

How about you!? Don't give your opinion?

Replying to the next comments:

To check if you are human answer the question correctly:

I don't like this question, change it!

None of these data will be stored.

(Write the e-mail)

Required field.

(Write the e-mail or several e-mails separated by coma)

Required field.

To check if you are human answer the question correctly:

I don't like this question, change it!

Daiatron on Google+