Abstract | ||
---|---|---|
In this paper, first we formalize a feature selection problem based on binary consistency as a combinatorial optimization. Next, for the purpose of increasing the number of instances explained by the features rather than decreasing the number of features themselves in feature selection, we introduce an iterative feature selection based on binary consistency and design the algorithm for it. Finally, by applying the method to nucleotide and amino acid sequences of influenza A viruses, we evaluate the advantage of the method. |
Year | DOI | Venue |
---|---|---|
2017 | 10.1109/IIAI-AAI.2017.61 | 2017 6th IIAI International Congress on Advanced Applied Informatics (IIAI-AAI) |
Keywords | Field | DocType |
consistent-based feature selection,binary consistency,iterative feature selection | Pattern recognition,Feature selection,Computer science,Combinatorial optimization,Artificial intelligence,Binary number | Conference |
ISBN | Citations | PageRank |
978-1-5386-0622-3 | 0 | 0.34 |
References | Authors | |
11 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Sho Shimamura | 1 | 0 | 0.34 |
Kouichi Hirata | 2 | 130 | 32.04 |