Table 1.
Partial confusion matrix of the final classification of our experiment (excluding candidates found by the oracle).
| Predicted | Actual class |
||
|---|---|---|---|
| class | Single peak | Double peak | Uninteresting |
| Single peak | 97.5% (3 484) | 1.5% (53) | 1.0% (37) |
| Double peak | 3.1% (18) | 93.4% (548) | 3.6% (21) |
Notes. The numbers show the percentage and counts (in brackets) of correctly predicted spectra of all spectra predicted for a given class. The 4161 spectra in this table are all the candidates predicted as single or double peaks after the long training. After we visually reviewed all of them, we found that 58 of candidates are uninteresting spectra (37 predicted as single peaks and 21 predicted as double peaks). The target classes also include some misclassification: 53 double peaks are classified as single peaks, and 18 single peaks are classified as double peaks. We note that we were unable to compute the last row of the uninteresting class because it would mean visually classifying all the four million spectra that are predicted as uninteresting.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.