A better mousetrap?

[andygates]

So Markov chains provide a good model for next-symbol probability, and touchscreens are amazingly shonky at working out what you really just typed.  Is anyone using a Markov chain to interpret the raw data from the users fat, mashy finger and determine what they really meant to press?  A second-order chain ought to be enough to pick out half a dozen likely candidate letters, most of which won't be in the area of the press.

Comments

[andygates.livejournal.com]

Darn! I'm reinventing the wheel? Again! The only time I've been ahead of the curve was with lipodiesel...

[andygates.livejournal.com]

Ah, now you're coming close to Dasher and its ilk. As long as the user can learn it easily, that's fine. Users learn finger movements, which is why I think Dasher hasn't conquered the world: -tion and -cion would need to be in predictably similar placed whenever they came up. When it was -tion, -cion and -ting, or -tion and -ting, at most one gram can remain static. There's *thought* required to find the right one, and that makes it worse than touch-typing.