Sentence examples for microarray classification methods from inspiring English sources

Pirooznia et al. [ 5] compared various microarray classification methods including; SVM, RBF Neural Nets, MLP Neural Nets, Bayesian, Decision Tree and Random Forrest methods.

Our microarray-based cancer classification methods are simple and interpretable relative to most other approaches, since our classifiers are based on decision rules, and the decision rules are based on single or double genes.

This may be due to different classification methods for microarray data sets.

In the present work, we proposed a novel ANMM4CBR method for microarray classification.

The experimental results revealed that the combination of the FCBF feature selection and ICA-based RotBoost ensemble with several base learners is a robust method for microarray classification.

A parallel study was designed to address experimental issues of combining microarrays and HR MAS MRS. In the first strategy, using the microarray data and previously reported molecular classification methods, the majority of samples were classified as luminal A. Three subgroups of luminal A tumors were identified based on hierarchical clustering of the HR MAS MR spectra.

This offers further evidence for the lack of significant differences among a large number of classification methods reported for microarray applications in terms of the predictive performance[35], a conclusion also proposed by the newly-finished community-wide study, MAQC-II [24].

In this work, we addressed RotBoost ensemble classification method to cope with gene microarray classification problems.

These methods are common used in microarray classification problems [ 49- 51].

Other less rigid classification methods were developed, especially for microarray data analysis where we are usually dealing with small number of measurements.

Since ANMM4CBR is a CBR-based method, we would like to compare it with other CBR methods that have been applied to microarray classification problems.