Skip to main content
. 2016 Sep 21;11(9):e0163041. doi: 10.1371/journal.pone.0163041

Table 3. Confusion matrix considering the classification of all eight classes of vocalizations using OPF with Manhattan distance and 90% of the samples for training set.

True class[%]
Alarm Chirp Loud-shrill Phee Seep Trill Tsik Twitter
Classified as[%] Alarm 78.4 0.0 4.7 4.1 4.3 0.7 2.5 0.0
Chirp 3.9 89.5 0.0 1.6 0.0 0.0 4.4 7.0
Loud-shrill 5.9 0.0 75.3 5.9 0.0 19.2 0.0 0.4
Phee 4.3 0.1 4.3 83.0 0.0 0.9 0.0 0.5
Seep 5.7 0.0 0.0 0.0 90.6 0.0 8.3 0.0
Trill 1.6 0.0 15.7 0.0 0.0 74.0 0.0 0.0
Tsik 0.2 1.0 0.0 0.0 5.1 0.0 77.5 0.0
Twitter 0.0 9.4 0.0 5.4 0.0 5.2 7.3 92.1