The phrase "as informative features" is correct and usable in written English.
It can be used when discussing elements or characteristics that provide information or insights in a particular context, such as data analysis or research.
Example: "The study identified several variables as informative features that significantly impacted the results."
Alternatives: "as data points" or "as key indicators".
For vibration signals one of the most intuitive approaches of obtaining signal with expected properties, such as clearly visible informative features, is prefiltration with appropriately prepared filter.
When the generalised and combinational ROC curves were applied to the samples using sera from the healthy women as the controls these curves were not as informative as some of the individual features (see Figure 4B) but in these latter cases, only a small number of sera were positive (see Figure 3A).
Identification of informative features as obtained from the feature usage scores of DT revealed that the oligomeric interface are predominantly occupied by hydrophobic residues with a few electrostatic residues engaging in salt bridges.
This is probably because of the lack of informative features: as the classification problem becomes more difficult, fewer features are informative for the outcome (also see Figure 1).
A predictor, or classifier, in this article is defined as a set of informative features (generated by a particular feature-selection method) and a trained discrimination rule (produced by applying a particular classification algorithm).
However, the prediction performance can be further improved by incorporating other informative features, such as the predicted secondary structures.
More recently, Zhang et al. proposed the RDpred method to predict RD values by applying several informative features such as predicted secondary structure, residue position and PSI-BLAST profile, which has achieved correlation coefficients of 0.67/0.67 between observed and predicted RD values, when evaluated using 3-fold/10-fold cross-validations [37].
In addition, the method proved effective in discovering informative features such as genes that are especially relevant for the classification and therefore might be critically important for the biological processes under investigation.
The efficiency in using the transformed dataset to perform normal/tumor classification was investigated using feature partitioning with informative features (gene annotation) as discriminating axes (single gene expression or pair-wise gene expression ratio).
The next step in the feature generation stage is to extract informative features from film reviews (as shown from the second row in Table 1).
