Hyperspectral data processing was carried out applying first principal component analysis (PCA) for data exploration and then partial least square-discriminant analysis (PLS-DA) to build classification models.
Here, experimental results of the screening have been used to build classification models using SMF descriptors and ISIDA modeling tools (Naïve Bayes (NB) and SVM modules).
ACM is a data mining framework that employs association rule mining (ARM) methods to build classification systems, also known as associative classifiers.
To test every module of ChemSAR and to build a model with high prediction performance, we employed five methods (RF, SVM, k-NN, NB, DT) to build classification models.
However, when it comes to massive data, it is difficult for current data mining algorithms to build classification models with serial algorithm running on single machines, not to mention accurate models.
We approach this task in a standard supervised learning setting: we extract discriminative features from the sensor data and use state-of-the-art classifiers (SVM, Logistic Regression and Decision Tree Family) to build classification models.
The evaluation results indicate that the SAAR system enables ecologists with little knowledge of machine learning techniques to collaboratively build classification models with high levels of accuracy, sensitivity, precision and specificity.
PCA has been successfully applied to build classification models from metabolomics data [15], [16], [17], [18].
They used phylogenetic analysis of catalytic domains to build classification trees, used as a basis for the classification in 55 distinct subfamilies.
More recently a supervised method, partial least squares discriminant analysis (PLS-DA), has been described in which latent variables (LVs) rather than principal components are used for input to build classification models [37], [38].
