Summing the feature weights for each network, the results revealed that the cingulo-opercular control network had the greatest sum total of feature weights, suggesting that they were the best relative predictors.
For a better overview we grouped features into three distinct sets - functional similarity (BP, CC, MF, MeanSim; total of 4 features), sequence features (ELM, disorderedness, total of 8 features), and network features (degree, Affinity PageRank, betweenes, EGDV, total of 71 features).
The combined feature set contains all 20 individual features and all 20 network features yielding a total of 40 features.
If data set contain ( l ) class of objects, the total number of features is ( x ) and total number of objects is ( y ).
The expert panel recommended that all 107 features on the preliminary list be retained, and suggested the addition of seven new features, making a total of 114 features.
This led to a total of 64 features and 8 rhythmic features.
We thus had data for a total of 7,320 features with 2027 putatively identified features from both columns, noting that some features overlap between the two columns.
The 80 wavelet-based features and 20 statistics-based features are combined, resulting a total of 100 features for each protein sequence.
Since results in soft-biometrics improve with higher amount of features, a total of 23 different features have been used in this work.
