2009:Audio Tag Classification (Mood Set) Results

General Legend

Team ID

BP1 = Juan José Burred, Geoffroy Peeters
BP2 = Juan José Burred, Geoffroy Peeters
CL1 = Chuan Cao,Ming Li
CL2 = Chuan Cao,Ming Li
CL3 = Chuan Cao,Ming Li
CL4 = Chuan Cao,Ming Li
GP = Geoffroy Peeters
GT1 = George Tzanetakis
GT2 = George Tzanetakis
LWW1 = Hung-Yi Lo,Ju-Chiang Wang,Hsin-Min Wang
LWW2 = Hung-Yi Lo,Ju-Chiang Wang,Hsin-Min Wang
HCB = Matthew D.Hoffman,David M. Blei,Perry R.Cook

Overall Summary Results (Binary)

file /nema-raid/www/mirex/results/tag/Mood/summary_binary.csv not found

Summary Binary Relevance F-Measure (Average Across All Folds)

file /nema-raid/www/mirex/results/tag/Mood/binary_avg_Fmeasure.csv not found

Summary Binary Accuracy (Average Across All Folds)

file /nema-raid/www/mirex/results/tag/Mood/binary_avg_Accuracy.csv not found

Summary Positive Example Accuracy (Average Across All Folds)

file /nema-raid/www/mirex/results/tag/Mood/binary_avg_positive_example_Accuracy.csv not found

Summary Negative Example Accuracy (Average Across All Folds)

file /nema-raid/www/mirex/results/tag/Mood/binary_avg_negative_example_Accuracy.csv not found

file /nema-raid/www/mirex/results/tag/rounded/tag.affinity_tag_AUC_ROC.csv not found

Overall Summary Results (Affinity)

file /nema-raid/www/mirex/results/tag/Mood/summary_affinity.csv not found

Summary AUC-ROC Tag (Average Across All Folds)

file /nema-raid/www/mirex/results/tag/Mood/affinity_tag_AUC_ROC.csv not found

Friedman's Test Results

Tag F-measure (Binary) Friedman Test

The following table and plot show the results of Friedman's ANOVA with Tukey-Kramer multiple comparisons computed over the F-measure for each tag in the test, averaged over all folds.

file /nema-raid/www/mirex/results/tag/Mood/binary_FMeasure.friedman.tukeyKramerHSD.csv not found

AUC-ROC Tag Friedman Test

The following table and plot show the results of Friedman's ANOVA with Tukey-Kramer multiple comparisons computed over the Area Under the ROC curve (AUC-ROC) for each tag in the test, averaged over all folds.

file /nema-raid/www/mirex/results/tag/Mood/affinity.AUC_ROC_TRACK.friedman.tukeyKramerHSD.csv not found

AUC-ROC Track Friedman test

The following table and plot show the results of Friedman's ANOVA with Tukey-Kramer multiple comparisons computed over the Area Under the ROC curve (AUC-ROC) for each track in the test. Each track appears in exactly once over all three folds of the test. However, we are uncertain if these measurements are truly independent as an multiple tracks from each artist are used.

file /nema-raid/www/mirex/results/tag/friedmansTables/tag.affinity.AUC_ROC_TRACK.friedman.tukeyKramerHSD.csv not found

Tag Classification Accuracy Friedman test

The following table and plot show the results of Friedman's ANOVA with Tukey-Kramer multiple comparisons computed over the classification accuracy for each tag in the test, averaged over all folds.

file /nema-raid/www/mirex/results/tag/friedmansTables/tag.binary_Accuracy.friedman.tukeyKramerHSD.csv not found

Beta-Binomial test results

Accuracy on positive examples Beta-Binomial results

The following table and plot show the results of simulations from the Beta-Binomial model using the accuracy of each algorithm's classification only on the positive examples. It only shows the relative proportion of true positives and false negatives, and should be considered with the classification accuracy on the negative examples. The image shows the estimate of the overall performance with 95% confidence intervals.

file /nema-raid/www/mirex/results/tag/tag.binary.per.fold.positive.example.accuracy.betabinomial.csv not found

File:Binary per fold positive example Accuracy.png

The plots for each tag are more interesting and the 95% confidence intervals are much tighter. Since there are so many of them, it is difficult to post them to the wiki. You can download a tar.gz zip file containing all of them here.

Accuracy on negative examples Beta-Binomial results

The following table and plot show the results of simulations from the Beta-Binomial model using the accuracy of each algorithm's classification only on the negative examples. It only shows the relative proportion of true negatives and false positives, and should be considered with the classification accuracy on the positive examples. The image shows the estimate of the overall performance with 95% confidence intervals.

JUST CHECKING

file /nema-raid/www/mirex/results/tag/Mood/binary_FMeasure_per_track.friedman.tukeyKramerHSD.csv not found

File:Binary per fold negative example Accuracy.png

The plots for each tag are more interesting and the 95% confidence intervals are much tighter. Since there are so many of them, it is difficult to post them to the wiki. You can download a tar.gz file containing all of them here.

Assorted Results Files for Download

AUC-ROC Clip Data

(Too large for easy Wiki viewing)
tag.affinity_clip_AUC_ROC.csv

CSV Files Without Rounding (Averaged across folds)

tag.affinity.clip.auc.roc.csv
tag.affinity.clip.auc.roc.csv
tag.binary.accuracy.csv
tag.binary.fmeasure.csv
tag.binary.negative.example.accuracy.csv
tag.binary.positive.example.accuracy.csv

CSV Files Without Rounding (Fold information)

tag.binary.per.fold.positive.example.accuracy.csv
tag.binary.per.fold.negative.example.accuracy.csv
tag.binary.per.fold.fmeasure.csv
tag.binary.per.fold.accuracy.csv
tag.affinity.tag.per.fold.auc.roc.csv

Results By Algorithm

(.tar.gz)
LB = L. Barrington, D. Turnbull, G. Lanckriet
BBE 1 = T. Bertin-Mahieux, Y. Bengio, D. Eck (KNN)
BBE 2 = T. Bertin-Mahieux, Y. Bengio, D. Eck (NNet)
BBE 3 = T. Bertin-Mahieux, D. Eck, P. Lamere, Y. Bengio (Thierry/Lamere Boosting)
TB = Bertin-Mahieux (dumb/smurf)
ME1 = M. I. Mandel, D. P. W. Ellis 1
ME2 = M. I. Mandel, D. P. W. Ellis 2
ME3 = M. I. Mandel, D. P. W. Ellis 3
GP1 = G. Peeters 1
GP2 = G. Peeters 2
TTKV = K. Trohidis, G. Tsoumakas, G. Kalliris, I. Vlahavas