Review on Feature Selection and Classification using Neuro-Fuzzy Approaches

Abstract

This research article attempts to provide a recent survey on neuro-fuzzy approaches for feature selection and classification. Feature selection acts as a catalyst in reducing computation time and dimensionality, enhancing prediction performance or accuracy and curtailing irrelevant or redundant data. The neuro-fuzzy approach is used for feature selection and for providing some insight to the user about the symbolic knowledge embedded within the network. The neuro–fuzzy approach combines the merits of neural network and fuzzy logic to solve many complex machine learning problems. The objective of this article is to provide a generic introduction and a recent survey to neuro-fuzzy approaches for feature selection and classification in a wide area of machine learning problems. Some of the existing neuro-fuzzy models are also applied on standard datasets to demonstrate the applicability of neuro-fuzzy approaches.

Research in Metabolomics via Nuclear Magnetic Resonance Spectroscopy: Data Mining, Biochemistry and Clinical Chemistry

“…Together with glutamate, glutamine is also involved in the pathway of alanine, aspartate and glutamate metabolism, which was also found altered according to metabolic pathway analysis (Figure S8a,b in Supplementary Materials). Glutamine and glutamate were also found affected in the study of Kitchin et al [57], in which the effect of TiO 2 and CeO 2 nanomaterials on human liver HepG2 cells was examined. A significant decrease in glutamine was observed, similar to observations from our study.…”

Precision Medicine Approaches with Metabolomics and Artificial Intelligence

“…When compared to wrapper and embedded feature selection methods, filter techniques are faster and less computationally expensive. Nonetheless, filter feature selection methods have some disadvantages; for example, they do not take into account the interaction of features between them [ 30 ].…”

Improving the search of learning classifier systems through interpretable feature clustering

“…There exist three main categories of feature selection algorithm: filter, wrapper, and embedded [7]. Filter methods perform feature selection as a separate task to the main machine learning problem, selecting features based only on the relationships in the data.…”