Sentence examples for most informative descriptors from inspiring English sources

Despite the numerous statistical approaches for feature or descriptor selection, real users that want to extract the most informative descriptors to understand or predict a property/activity still face an important challenge.

The correlation and discriminative power of descriptors were used to select a non-redundant subset of most informative descriptors.

g Scorings models composed of the subset of 18 most informative descriptors The combined L score for a given miRNA hairpin was calculated as the product of all S values of descriptors considered in a scoring model.

In total, 23 scoring models were built, based on 23 distinct taxonomic sets and the subset of 18 most informative descriptors, with the LDF parameterized at 90% of the CDF and using individual weighting of descriptors.

Using a dataset of known miRNA hairpins from the miRBase database and an exhaustive set of genomic hairpins identified in the genome of Caenorhabditis elegans, a subset of 18 most informative descriptors was selected after detailed analysis of correlation among and discriminative power of individual descriptors.

For the 18 most informative descriptors, the threshold used did represent the same cut-off value between the S = 1 and S < 1 fraction of the LDF, at 95% of the CDF at the side(s) of the distribution as listed in Table 1.

As can be seen from Figure 10, for activation and dominance, mfcc are the most informative low-level descriptors followed by logarithmic power of Mel-frequency bands (LogMelFreqBand).

To select a subset of descriptors that was most informative for the combined assessment of miRNA hairpins by the L classifier, descriptors that either correlated with a more discriminative descriptor (κ>0.4) or that showed low discriminative power (< 1.1) were discarded from the initial set.

Based on the correlations among chemical descriptors (Results S3), and the correlations between chemical descriptors and properties of inhibition (Results S4 and S5), we selected the descriptors which were most informative regarding the mode of action of SCIs (Results S4).

To effectively incorporate the DSRF descriptors in the skeletal representation, a skeleton is decomposed into five parts and the most informative part method is raised for offering compact representation.

Specifically, performance of models in local regions of chemical space, as inferred here from feature descriptors included in successful models, could be used to prioritize where qHTS data would be most informative and important for prediction.