Thumbs-Down Songs on Pandora with Your Mind

[Steven] likes music. Like many of us, he uses Pandora to enjoy the familiar and to discover new music. Now, Pandora means well, but she gets it wrong sometimes. [Steven] has had a Mindwave Mobile EEG headset lying around for a while and decided to put it to good use. With the aid of a Raspberry Pi and a bluetooth module, he built a brainwave-controlled Pandora track advancing system.

The idea is to recognize that you dislike a song based on your brainwaves. The Mindwave gives data for many different brainwaves as well as approximating your attention and meditation levels. Since [Steven] isn’t well-versed in brainwavery, he used Bayesian estimation to generate two multivariate Gaussian models. One represents good music, and the other represents bad music. The resulting algorithm is about 70% accurate, so [Steven]‘s Python script waits for four “bad music” estimations in a row before advancing the track.

[Steven] streams Pandora through pianobar and has a modified version of the control-pianobar script in his GitHub repo His script will also alert you if the headset isn’t getting good skin contact, a variable that the Mindwave reports on a scale of 0 to 200.

Stick around for a demo of [Steven] controlling Pandora with his mind. If you don’t have an EEG headset, you can still control Pandora with a Pi, pianobar, and some nice clicky buttons.

[Read more...]

Tug of War… with your mind, man!

Challenge your friends to a little mental Tug of War thanks to the Omaha Maker Group’s Red Bull Creation contest entry. The power struggle is all in your mind, and can only be won if you’re able to concentrate deeply and quickly. The headsets worn by each competitor monitor brain waves over a ten second window. If you concentrate more deeply than your opponent they’ll get a squirt of water in the face. If no one is concentrating well the contest is a draw the measurements start again. The screenshot above was taken from the test footage found after the break.

Hardware details are scant on this one. Obviously the Bullduino is the centerpiece of the build, taking readings from the headsets. A motor moves the water nozzle along a slit cut in the top of the sphere.  Progress during the 10-second window is displayed by that nozzle, which starts in the center yellow ‘safe’ zone and moves to one side or another to enter the green ‘kill’ zone.

[Read more...]

Mind control via serial port

brain-control-via-serial-port

[Zibri] found a very simple method for using brain waves as a controller via a DB9 serial port. He’s using Uncle Milton’s Force Trainer which we saw yesterday in the brain controlled Arduino. In that project the Arduino tapped into the LEDs and interfaced those signals with a computer via USB. This time the connection was made using an RS-232 transceiver to pass data from the programming header inside of the toy’s base unit to a computer over the serial port. Tapping into the programming header has a lot more potential and should be more reliable than sniffing logic out of LED connections. [Zibri] has written an application to display the received data but it doesn’t look like he’s made the code available for download.

Apparently he tipped us off about a week ago. We recall seeing this submission but as you can tell it’s a little bit light on the detail. So if you want your tips to be at the front of the line, make sure you do what you can to fill us in on all the details of your project. At our request [Zibri] provided a picture of the PCB from the Force Trainer’s base unit. See it after the break. [Read more...]

Open source neural activity monitors

Yesterday we linked to an OCZ Neural Acutator Interface teardown. Several in the comments wanted to know more about the sensor electrodes. Check out the OpenEEG project and OpenEEG mailing list for information on sensing, amplifying, and recording brain activity (EEG). The OpenEEG project maintains an open source Simple ModularEEG design. Two other open source variants of the ModularEEG are the MonolithEEG and [Joshua Wojnas'] Programmable Chip EEG BCI. All three projects use Atmel microcontrollers, with designs in Cadsoft Eagle.

Brain activity is measured using passive or active electrodes. Passive electrodes require a conductive paste to make proper contact with the skin (examples: 1, 2). Active EEG sensors don’t need conductive goop because they have an amplifier directly on the electrode (examples: 1, 2, 3).

[via anonymous reader, comments]

Follow

Get every new post delivered to your Inbox.

Join 93,621 other followers