All experiments used recurrent neural networks to perform feature detection.
We also perform feature extraction by determining the silhouette likelihood.
By specializing to the Veronese kernel we can also perform feature selection with this method.
The first step in our framework is to perform feature ranking using mutual information.
Second, most current MI-based approaches perform feature selection sequentially starting from high-ranked features.
Max-pooling convolutional neural networks (MPCNNs) perform feature extraction and classification jointly.
To speed up convergence, we perform feature scaling (normalization) prior to the beginning of iterations.
An unsupervised feature selection method called orthogonal subspace projection (OSP) was used to perform feature selection and redundancy reduction simultaneously.
Therefore, complexity increases and it is necessary to perform feature selection and/or dimensionality reduction to achieve good detection accuracy.
We also test its ability to perform feature selection on a support vector machine model for the same dataset.
Principle component analysis and genetic algorithms have been utilized to perform feature reduction in seizure detection methods [18, 27].
