Recall that we consider three different feature selection techniques, the Lasso, SNSS, and RDA, in combination with three different classification approaches: (1) using the same model for classification as for feature selection, (2) using the selected features in a KNN classifier, or (3) using the selected features in a Random Forests classifier.
Random forest algorithm was adopted to classify driving styles using the selected features.
A simple first order security function is designed using the selected features for classification.
However, they fail to consider the performance of some specific learning task, e.g. regression, by using the selected features.
By using the selected features, not only the number of features is reduced, but also the classification accuracy is increased to 100% for all the three mentioned artificial neural networks.
Using the selected features, we evaluated eight commonly used classification algorithms: Support Vector Machine (SVM) [42], Logistic Regression (LR) [43], Random Forest (RF) [44], Artificial Neural Networks (ANN) [45], Decision Trees (DT) [46], Naïve Bayes (NB) [47], and their boosted versions, BDT and BNB [48].
A new classifier was trained using the selected features on the marker-evaluation dataset and its classification performance was again assessed on the feature-selection dataset.
Four fifths of samples were used to train the classifier using the selected features, and one fifth of samples were used to evaluate the performance of the constructed classifier.
Moreover, we predicted the metabolic stability of drug target proteins using the selected features and found an intriguing correlation between the predicted metabolic stability of some proteins and the real half-life of the drugs designed to target them.
