Research Article
A Compressive Sensing Model for Speeding Up Text Classification
Table 1
MSEs between average distances of CS and BOW features on multiclass classification dataset when using different subrates and SRMs.
| Subrate R | SRMs | DCT | FFT | Block DCT | Block WHT | Block Gaussian |
| 0.1 | 18.78 | 18.81 | 18.38 | 18.48 | 18.62 | 0.2 | 14.37 | 14.40 | 14.38 | 14.08 | 14.51 | 0.3 | 11.39 | 11.39 | 11.17 | 11.11 | 11.78 | 0.4 | 9.14 | 9.12 | 9.018 | 9.01 | 9.33 | 0.5 | 7.36 | 7.34 | 7.19 | 7.21 | 7.33 | 0.6 | 5.92 | 5.91 | 5.96 | 5.90 | 6.03 | Avg. | 11.16 | 11.16 | 11.02 | 10.96 | 11.27 |
|
|