Open Access
Table 2.
Accuracy and time cost for algorithms.
| Algorithm | Accuracy | Time cost |
|---|---|---|
| Decision tree | 92.6% | 96 s |
| Linear discrimination | 86.9% | 26 s |
| Bayesian | 74.3% | 10 s |
| SVM | 96.4% | 90 min |
| k-NN | 95.7% | 23 min |
| AdaBoost | 92.0% | 3 min |
| Random forest | 96.2% | 7 min |
Notes. The last column is the rough training time cost for the training sample. The “s” stands for second and “m” is for minute. See Fisher (1936) for details about the linear discrimination algorithm.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.