|
We worked on the brochure (finished it) and the report. Someone worked out a function which doesnt use the average anymore, but it calculates the algebraic distance to each training key and the letter with the smallest distances, should be correct. This method isnt that succesfull, a rate about 40% with some very good exceptions.
Someone kept optimizing the sound recognition function.
We also started a new approach for calculating key patterns using the standarddeviation and the average. With these specifications we make an interval which can be used as a template.
writing to optimize the search of the hitpeak, because our earlier function sometimes used the releasepeak (when the releasepeak is higher than the hitpeak).
20-11-2012 om 17:55
geschreven door keyboard123
|
