The scores for the precision, recall, F1-score, and accuracy metrics are shown for all four classification methods. The method with the highest score for each metric is highlighted in bold. The (†) symbol by the thresholding methods indicates that these methods only classified 18 zones, whereas the neural network methods classified 21 zones.</p
<p>This table reports average <i>F</i><sub>1</sub>, Precision, Recall scores of five methods in thre...
<p>Each column presents a different clustering measure (see <a href="http://www.ploscompbiol.org/art...
<p>The classification accuracy is plotted over different number of training samples. For a given num...
The application of a simple thresholding technique to help assess the satisfactory performance of cl...
<p>Comparison of the average precision rates, recall rates and F1 values for the different classific...
The accuracy as a function of the history length (seconds) is displayed for the three classification...
<p>Upper panels – Mouse, Lower panels- Human. Each column presents a different clustering measure (s...
Performance metrics of the method as a function of the detection range (m) for the PLN-ARIS dataset:...
(a) ROC curve before (yellow) and after (blue) augmentation for the classifier based on unbalanced d...
<p>The precision-recall curve (A), receiver operating characteristic curve (B), the significance lev...
Bars indicate the median value of each coefficient, and intervals indicate the 2.5% and 97.5% percen...
In each set of boxes corresponding to different sample size (SS) values, Precision, NA_perc (percent...
<p>Values are F1-score (recall/precision) (%)</p><p>Comparison of two methods in term recognition: r...
Comparison of the average classification accuracy of the networks used in DeephESC and DeephESC 2.0....
For feature selection using coefficient of variation (CV), the filtering thresholds from left to rig...
<p>This table reports average <i>F</i><sub>1</sub>, Precision, Recall scores of five methods in thre...
<p>Each column presents a different clustering measure (see <a href="http://www.ploscompbiol.org/art...
<p>The classification accuracy is plotted over different number of training samples. For a given num...
The application of a simple thresholding technique to help assess the satisfactory performance of cl...
<p>Comparison of the average precision rates, recall rates and F1 values for the different classific...
The accuracy as a function of the history length (seconds) is displayed for the three classification...
<p>Upper panels – Mouse, Lower panels- Human. Each column presents a different clustering measure (s...
Performance metrics of the method as a function of the detection range (m) for the PLN-ARIS dataset:...
(a) ROC curve before (yellow) and after (blue) augmentation for the classifier based on unbalanced d...
<p>The precision-recall curve (A), receiver operating characteristic curve (B), the significance lev...
Bars indicate the median value of each coefficient, and intervals indicate the 2.5% and 97.5% percen...
In each set of boxes corresponding to different sample size (SS) values, Precision, NA_perc (percent...
<p>Values are F1-score (recall/precision) (%)</p><p>Comparison of two methods in term recognition: r...
Comparison of the average classification accuracy of the networks used in DeephESC and DeephESC 2.0....
For feature selection using coefficient of variation (CV), the filtering thresholds from left to rig...
<p>This table reports average <i>F</i><sub>1</sub>, Precision, Recall scores of five methods in thre...
<p>Each column presents a different clustering measure (see <a href="http://www.ploscompbiol.org/art...
<p>The classification accuracy is plotted over different number of training samples. For a given num...