It should adopt the best optimized feature selection methodology to select the adequate features for each problem.
Currently the number of chemical descriptors is so large that one of the biggest problems is selecting the most adequate features for each problem [58, 59].
Hence, feature selection methodology was found efficient to deal with high dimensional data by selecting adequate features for each problem to predict a certain property with a good performance, less computational/time cost.
Results of this work showed that the feature set leading to the highest predictive performance is not necessarily the most adequate feature set for AD characterization.
We propose here that the adequate feature set optimized for the characterization of the AD can, in theory, reveal the problematic regions if the AD is optimized using external sets.
Collectively, the present results indicate that the ΔrpoS and ΔphoP strains of S. Choleraesuis gather adequate features to be potential candidates for vaccine vectors for the specific delivery of heterologous antigens adapted to pigs.
As this knowledge is missing, one major problem in this context is to define adequate features to train the classifiers for each structural element.
Aggregating feature counts provided adequate feature density and reduced the dimensionality without discarding features that could be informative.
For this purpose, Jano provides the adequate features: only in some application specific circumstances are users (e.g., students, professors, bus drivers, etc).
It includes several disorders where a high number of medically unexplained symptoms is the main feature, for which adequate somatic examination does not reveal sufficient explanatory pathology.
It has been shown in many damage identification studies that the usage of one hidden layer is adequate for accurate feature extraction and pattern recognition (Yam et al. 2003; Zang and Imregun 2001).
