Feature selection is the process of refining input data by removing irrelevant and/or redundant features. Feature selection deals with selection of a subset of relevant features (variables) from an input data. Feature selection does not produce new features – all selected features are subsets of the original feature vector.
In my spare time, i enjoy working on some NP complete problems. The latest ones include(but not limited to) feature selection, computer vision, classification, TSP, VRP, VRPTW, CVRP etc. I use sub-optimal population-based stochastic algorithms (e.g. Genetic Programming and Genetic Algorithms) in most of my works.
Genetic Algorithm and Ant Colony Optimization was tested on a TSP. According to the results, ACO outperformed GA on the TSP problem.
I am the community owner and administrator of the "Evolutionary Algorithms" group on g+
I am the community owner and administrator of the "Genetic Programming" group on g+