Resolution: standard / high

Figure 2.

A split based on a question that maximizes the increase in log likelihood. NT and Nall are the number of true samples reaching node d and the total number of samples (true and false) assigned to node d. <a onClick="popup('http://asmp.eurasipjournals.com/content/2012/1/10/mathml/M7','MathML',630,470);return false;" target="_blank" href="http://asmp.eurasipjournals.com/content/2012/1/10/mathml/M7">View MathML</a> and <a onClick="popup('http://asmp.eurasipjournals.com/content/2012/1/10/mathml/M8','MathML',630,470);return false;" target="_blank" href="http://asmp.eurasipjournals.com/content/2012/1/10/mathml/M8">View MathML</a> are the numbers of the true and all samples at child yes, <a onClick="popup('http://asmp.eurasipjournals.com/content/2012/1/10/mathml/M9','MathML',630,470);return false;" target="_blank" href="http://asmp.eurasipjournals.com/content/2012/1/10/mathml/M9">View MathML</a> and <a onClick="popup('http://asmp.eurasipjournals.com/content/2012/1/10/mathml/M10','MathML',630,470);return false;" target="_blank" href="http://asmp.eurasipjournals.com/content/2012/1/10/mathml/M10">View MathML</a> are the numbers of the true and all samples at child no, respectively

Akamine and Ajmera EURASIP Journal on Audio, Speech, and Music Processing 2012 2012:10   doi:10.1186/1687-4722-2012-10
Download authors' original image