From: Hybrid deep learning approach to improve classification of low-volume high-dimensional data
Dataset | #Samples | #Classes | #Features | Best predictive model | Best accuracy | Class frequency |
---|---|---|---|---|---|---|
WISDM | 27,452 | 6 | 320 | Hybrid (1-block, layer: 5) | 0.793 | Walk 4588 |
 |  |  |  |  |  | Upstairs 4416 |
 |  |  |  |  |  | Downstairs 4438 |
 |  |  |  |  |  | Sit 4678 |
 |  |  |  |  |  | Stand 4698 |
 |  |  |  |  |  | Jog 4634 |
HAR | 10,299 | 6 | 561 | Hybrid (5-blocks, layer: 10–12) | 0.925 | Walk 1722 |
 |  |  |  |  |  | Upstairs 1544 |
 |  |  |  |  |  | Downstairs 1406 |
 |  |  |  |  |  | Sit 1777 |
 |  |  |  |  |  | Stand 1906 |
 |  |  |  |  |  | Lie 1944 |
Amazon | 1000 | 2 | 100 | Hybrid (3-blocks, layer: 5) | 0.797 | Review > 2 500 |
 |  |  |  |  |  | Review ≤ 2 500 |
Yelp | 1000 | 2 | 100 | Hybrid (3-blocks, layer: 2) | 0.776 | Review > 2 500 |
 |  |  |  |  |  | Review ≤ 2 500 |
IMDb | 748 | 2 | 100 | Hybrid (3-blocks, layer: 5) | 0.797 | Review > 2 374 |
 |  |  |  |  |  | Review ≤ 2 374 |
Gene Promoter | 106 | 2 | 57 × 4 | Hybrid (3-blocks, layer: 1) | 0.952 | Promoter 53 |
 |  |  |  |  |  | Non-promoter 53 |