Embedded techniques achieve an interaction between the channel selection and the classification.
Approaches to feature selection are generally categorized into filter, wrapper, and embedded techniques.
In the embedded techniques, the channels are selected based on criteria generated during the learning process of a specific classifier because the selection is included into the classifier construction [9].
Embedded techniques are defined for a specific classification method.
Filter approach does not interact with the classifier, contrarily to wrapper and embedded techniques, usually resulting in lower performance.
The multivariate feature selection approaches can be broadly divided into the following categories: (1) filter techniques (e.g., fast correlation-based algorithm [ 11]), (2) wrapper techniques (e.g., GA/KNN method (combining a Genetic Algorithm (GA) and the k-Nearest Neighbor (KNN) method) [ 12]), and (3) embedded techniques (e.g., random forest [ 13]).
In the bottom embedding technique [25], the logo is embedded to S as the last r bottom lines.
The tissues were processed by routine paraffin embedding technique and the sections were cut at 5 µm thickness.
A fruitful research direction, proposed by Thodi and Rodriguez [14], is prediction-error expansion (PE) embedding technique.
We leverage the recently advanced word embedding technique in natural language processing to efficiently train the neural network.
