The feature selection approach in this study is based on the dimension reduction issue.
Initially, some projection methods as PCA [10][11], MLHL [12][13] and CMLHL [1] are applied.
In a first step they aim to analyse the internal structure of a representative data set of a case of study.
If after applying these models a clear internal structure can be identified,
this means that the data recorded is informative enough. Otherwise, data must be properly collected.