Performance characteristics of the classifier.

1Held out dataset were annotated at report level only as being positive, negative or equivocal for IMD.Abbreviations: TN, true positives; FP, false positives; TN, true negatives; FN, false negatives;

Figshare2014-09-24 更新10

The Performance of a Prototype Classifier.

The performance of a prototype classifier for the different tasks when using the spectrograms (time+frequency information) or PSDs (frequency only). The identical decisions are as in table 3.

Figshare2015-12-02 更新00

Parameters to quantify the performance of the classifier.

Note: 1 and 2 represents two conditions. TP (true positive) is the number of LT symptoms correctly predicted; TN (true negative) is the number of MT symptoms correctly predicted; FP (false positive) i

Figshare2015-12-02 更新10