Want to read Slashdot from your mobile device? Point it at m.slashdot.org and keep reading!

 



Forgot your password?
typodupeerror
×
Technology Science

Scientists Demonstrate Thought-Controlled Computer 172

Da Massive writes with a link to ComputerWorld coverage of a unique gadget shown at this past week's CeBit show. The company g.tec was showing off a brain/computer interface (BCI) in one corner of the trade hall. The rig, once placed on your head, detects the brain's voltage fluctuations and can respond appropriately. This requires training, where "the subject responds to commands on a computer screen, thinking 'left' and 'right' when they are instructed to do so ... Another test involves looking at a series of blinking letters, and thinking of a letter when it appears." Once the system is trained, you can think letters at the machine and 'type' via your thoughts. Likewise, by thinking directions you can move objects around onscreen. The article provides some background on the history of g.tec's BCI, and suggests possible uses for the technology in the near future.
This discussion has been archived. No new comments can be posted.

Scientists Demonstrate Thought-Controlled Computer

Comments Filter:
  • Re:Type thoughts? (Score:5, Insightful)

    by Amonnil ( 874821 ) on Sunday March 18, 2007 @03:11PM (#18395611)
    I think it would take a whole lot longer to train the system to respond to the hundreds of thousands of words you might want to use, instead of the few dozen characters to spell everything out. It would probably be more likely to get words confused, as well. That being said, this technology is new, as it develops, I'm sure ways will be found to speed up communication. Things like the word-completion used in phones for texting would be an obvious start. For now, I'm impressed that it's possible to hunt-and-peck with a mental keyboard.
  • Re:Type thoughts? (Score:3, Insightful)

    by CastrTroy ( 595695 ) on Sunday March 18, 2007 @03:33PM (#18395767)
    Wouldn't it make a lot of sense if you could just train it once, and then take your profile with you on a USB key? That way you wouldn't have to train the work computer, the home computer, the new laptop, the computer in the internet cafe, or any of the other computers you deal with on a daily basis.
  • by ArikTheRed ( 865776 ) on Sunday March 18, 2007 @06:28PM (#18396893) Homepage
    I'm more concerned about someone patenting "thought" as a "proprietary interface".
  • Bad bad bad... (Score:3, Insightful)

    by confused one ( 671304 ) on Sunday March 18, 2007 @07:26PM (#18397181)
    I don't get it... Why do people keep trying to do this!?

    Isn't it obvious that once a computer can read our minds, and see how messy it really is up there, they'll have all the they need to justify taking over "to protect us from ourselves"

  • Re:Type thoughts? (Score:3, Insightful)

    by dosquatch ( 924618 ) on Sunday March 18, 2007 @08:57PM (#18397637) Journal

    Exactly, human beings don't think in letters. We think words, concepts, even ideas at a time.

    That may be, but I have some serious misgivings about my computer having unrestricted access to my mind. Oh, sure, it sounds great at first, but the first time it catches me daydreaming about the printer in the field from Office Space, and suddenly my resume' would start listing my real hobbies...

  • Re:Type thoughts? (Score:3, Insightful)

    by c_fel ( 927677 ) on Sunday March 18, 2007 @09:48PM (#18397927) Homepage
    I think it would take a whole lot longer to train the system to respond to the hundreds of thousands of words you might want to use, instead of the few dozen characters to spell everything out.

    Moreover, this system surely use some type of neural network to identify a character from the actual voltage signals. As these signal are very noisy and have a relatively high frequency range, it must take a quite big network to obtain something good from it.
    Now, if you want to discriminate hundreds of thousands of words instead of some characters, you need a much bigger network ; and the time needed to learn is exponential to the size of the network. So I don't think it could be feasible at this time to get a system that could learn how to read words : it would need years to learn !
  • Re:Not Quite.... (Score:3, Insightful)

    by KDan ( 90353 ) on Monday March 19, 2007 @06:11AM (#18399605) Homepage
    That doesn't actually seem like a step in the right direction. Reading "dumb" voltages is a million miles away from reading thoughts - no breakthrough at all. In fact, they've been doing this for decades through EEGs - plugging it into a computer interface doesn't make it a breakthrough. It's a very clumsy and slow way of designing a brain interface.

    I'm much more interested in the invasive procedures which actually read body movement intentions - those are much more versatile than just reading "whether the user is concentrating"...

    Daniel

All the simple programs have been written.

Working...