Skip to main content

Table 12 Feature selection for instrument recognition with auditory model features: number of selected features and error rates

From: A computational study of auditory models in music recognition tasks for normal-hearing and hearing-impaired listeners

Method

No selection

Channel groups

Feature groups

  

Forward

Backward

Forward

Backward

RF number of features

41 × 21=861

2 × 21=42

12 × 21=420

41 × 3=123

41 × 17=697

RF error rate

0.019

0.034

0.011

0.058

0.016

SVM number of features

41 × 21=861

2 × 21=42

12 × 21=420

41 × 3=123

41 × 8=328

SVM error rate

0.011

0.030

0.017

0.045

0.015