In this subsection, the selected feature selection methods are reviewed under this framework.
If a feature selection method has poor stability, the selected feature subsets change significantly due to the variation of training data.
where F f is the union between the selected features and the optimal feature f to be selected in the current selection, F j (j=1,2,…,i−1) represents the selected feature subset, and |F f ∩F j | and |F f ∪F j | represent the intersection and union between feature sets F f and F j, respectively.
Feature selection is the most important step because the selected feature words directly affect the accuracy of the classifier.
After the feature selection is completed, we parameterized the SVMs using the selected feature set and the same grid search as above.
As we mentioned in Section Introduction, the predictive power and the inner redundancy of the selected feature subset are two key points in feature selection methods.
The effectiveness of the selected feature is assessed using both cross-correlation and cross-coherence metrics.
The selected feature set was fed into an ensemble of neural network classifiers.
Optical flow distributions of the selected feature points allow us to quantify the accuracy of the optical flow estimate in any direction.
Moreover, the accuracy of detecting pathological oscillations depends greatly on the selected feature(s) that must objectively distinguish epileptic events from average activity, a task that visual review is inevitably too subjective and insufficient to resolve.
(3) When fifty randomly selected 20% of landslide pixels (PLS) and 20% of non-landslide pixels (PNLS) (i.e., 20% of PLS and PNLS) were utilized in addition to the selected feature subsets for training, the test sets (i.e., the remaining 80% of PLS and PNLS) yielded an average overall classification accuracy of 78.24%.
