MuseSDK 3.0.1 Released


MuseSDK 3.0.1 Released!

Download it here:

One of the main new features is that it is a one-click install. There is no need to install additional libraries to make muse-player work.

The other big update is that we have included additional algorithms in muse-io:

[B]Band Power Session Scores[/B] - Session scores gives values between 0 and 1 by comparing the user’s current band power value to an average of their recent historical values of that same band. For example, if the user’s historical alpha power has been between 0.2 and 0.4, and their current alpha power is 0.3, then their session score will be 0.5 since 0.3 is halfway between 0.2 and 0.4.

[B]Concentration and Mellowness (Experimental)[/B] [SIZE=13px] These are high level values that can be used in applications where you don’t care about building your own algorithms and want to use something that will work out of the box.
Note that it will take approximately 1 minute with Muse on the head before these values will start producing something relevant.

This is based on gamma, but with additional processing to make it more reflective of the user’s experience.[/SIZE]
This value goes up by focusing on something particular, thinking about something with intensity[SIZE=13px], waiting in expectation for something to happen, trying to solve a problem, or working your intellectual mind. [/SIZE]
Warning: If you tense up your muscles, it can get confuse this measure in that this value may go up.
This is based on alpha, but with additional processing to make it more reflective of the user’s experience.
This value goes up when you are relaxing, letting go of judgement, letting go of trying to control things, letting go of attachment to outcome, not thinking about anything with a goal. You are not engaged in strenuous mental processing but still alert to your senses. Being without an active task, but alert. A ready waiting state.

See the updated documentation on muse-io paths here:


good news.


This is cause of Android app now crashing perpetually?

If indeed it is, how to go back to old Android app?


Good news Paul, installed it over the old and works fine. I like that the DSP option is in MuseLab now, intrigued by the attention/mellow data. So now here is the “one thing”;
on thing I cant find is how to turn on the horseshoe in in the new MuseLab (1.7.0 build-281).


@AntariS - The SKD has nothing to do with the Calm app. for Android or any other smartphone or tablet device. The SKD is only for desktops.

@Unawoo - I’ve just noticed that too, MuseLab does not show anymore the horseshoe indicators (I would guess that the old /muse/dsp/elements/horseshoe is hardcoded inside MuseLab and the path is now /muse/elements/horseshoe)

But, Indeed, very good news. Specially because we can see that the Muse Team is really commited to listen to the community requests … that’s really great, congratulations !!!

Just look at some frequent requests:

  • absolute, relative and session_score pb are now available for anyone who want to study these things, but don’t know how to implement them ( like me :o) )
  • those much asked measures like focus/relax (or attention / calm levels) are now there (that suggests something like what the Calm app. does, if I’m not wrong).

The installation process is now a one click.
It would be great if in addition to the new muse-player.exe, also the muse-player scripts were available too with the new installation - I’ve started learning to develop in Python with those scripts and have made a lot of changes, including creating some new optional arguments adding a few more functionality, for example:

  • taking all arguments from a text file instead of from the command line (like: @myargs.txt), and I have many “args.txt” files for each kind of task I want.

  • reformated all screen-dump display so all muse elements fields are perfectly aligned, made much easier to see what’s scrolling and can quickly see with a brief pause key.

  • added a new -p parameter (for example: -p0.5 or -p1) that automatically pauses the screen dump for half a second or 1 second whenever a bad signal is beeing displayed (eg. a bad horseshoe, or bad is_good), also for eye-blink and jaw_clench - this adds some extra marks (like [;], [X], *) at the end of the line signaling an eye-blink or a jaw_clench or a horseshoe <> 1 or a is_good = 0.

  • if there are many bad signals, of course the dump gets out of sync if you are taking input directly from Muse (does not matter if input is from a muse file), but you can allways press the space bar to disable the -p parameter for awhile until the screen get in sync again, and press space again to re-enable it.

I’ve learned more about Python from the muse scripts than from the manuals :slight_smile:

NOTE: The muse-io --dsp parameter does not exist anymore, if you add it to the command line, muse-io just show the help screen and stops.
(–dsp is the default now). If you don’t want the pre-processed algorityhms use --no-dsp instead.

BTW, there are still many mistakes at the Developers Site pages, including the new MuseIO 3.6.1 Command Line Options and OSC Paths - 3.6.1 … I’ll try to compile what I’ve noticed so far and will make a DOC and will post later.

Thanks to all, and to the Muse Team efforts.

EDIT: disregard my note about --dsp


nothing at all about mobile device tools/samples to assist in making mobile apps (without a desktop present). am i missing something or is that issue getting deliberately ignored?