MCoMat: a New Performance Metric for Imbalanced Multi-layer Activity Recognition DatasetReviewed
Sayeda Shamma Alia, Paula Lago, Sozo Inoue,
Ubicomp Workshop on Human Activity Sensing Corpus and Applications (HASCA)
232 - 237
Existing performance metrics assess classifiers on single granularity layer. Having multi-layer labels is also possible such as activity recognition datasets. Semantic annotations could be given with multiple granularity layers in these datasets e.g., ...