Table 5.
Summary of performance for absolute classification task for uninformed cycling, random selection, and Bayesian Exploration.
| Summary of performance | Uninformed cycling | Random selection | Bayesian exploration |
|---|---|---|---|
| Correct identifications | 49.9% | 84.1% | 95.4% |
| And converged | 36.4% | 68.3% | 89.3% |
| Median # of movements | 10* | 8 | 5 |
| PERFORMANCE DETAIL | |||
| Computer paper (T1) | 0.0% | 57.8% | 82.0% |
| Smooth cardstock (T3) | 0.0% | 81.2% | 99.6% |
| Buna-N rubber (T50) | 58.0% | 84.4% | 100.0% |
| Silicone rubber (T54) | 88.6% | 86.6% | 99.6% |
| Acrylic felt (T12) | 100.0% | 94.2% | 96.4% |
| Velour (T96) | 33.4% | 83.4% | 100.0% |
| Textured vinyl #1 (TS7) | 100.0% | 99.6% | 100.0% |
| Textured vinyl #2 (T58) | 0.0% | 51.4% | 67.2% |
| Pineapple fiber weave (T107) | 99.2% | 94.0% | 99.8% |
| Linen cloth (T111) | 14.2% | 90.6% | 99.6% |
| Plastic paper (T18) | 27.6% | 86.4% | 100.0% |
| Template plastic (T19) | 86.2% | 88.0% | 94.4% |
| Cotton duck (T102) | 100.0% | 99.2% | 100.0% |
| Jean denim (T104) | 26.6% | 91.8% | 96.8% |
| Santoprene rubber (T51) | 3.0% | 75.4% | 93.6% |
| Haplon rubber (T53) | 61.2% | 80.8% | 97.6% |
A total of 8000 Monte Carlo simulations for 16 textures from unique validation data were compared against the training data from all 117 textures to determine which of the 117 textures best fit the observed data when performing virtual explorations. Results of Bayesian exploration are compared to uninformed cycling through exploratory movements between the three signals at their most useful movements and random selection of exploratory movements from all combinations of movements and signals. The percentage of correct identifications are shown for each. The algorithm that produced the best performance for each texture is displayed in bold.*For the case of uninformed cycling the median number of movements to convergence could not be obtained as the simulation was stopped at 10 movements before half of the simulations could converge.