Abstract | ||
---|---|---|
•The proposed model preserves the local discriminant structure and local geometric structure of the data simultaneously.•It can not only improve the discriminative ability of the algorithm, but also utilize the local geometric structure information of the data.•L1-norm is introduced to constrain the feature selection matrix.•It can ensure the sparsity of the feature selection matrix and improve the algorithm's discrimination ability.•The experimental results show that the proposed algorithm is more effective than the other five feature selection algorithms. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1016/j.patcog.2019.03.026 | Pattern Recognition |
Keywords | Field | DocType |
Local discriminant model,Subspace learning,Sparse constraint,Feature selection | Convergence (routing),Pattern recognition,Subspace topology,Feature selection,Matrix (mathematics),Linear model,Discriminant,Matrix decomposition,Artificial intelligence,Discriminative model,Mathematics,Machine learning | Journal |
Volume | Issue | ISSN |
92 | 1 | 0031-3203 |
Citations | PageRank | References |
9 | 0.43 | 0 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Ronghua Shang | 1 | 556 | 33.57 |
Meng Yang | 2 | 1876 | 57.14 |
Wenbing Wang | 3 | 60 | 3.15 |
Fanhua Shang | 4 | 468 | 33.69 |
Licheng Jiao | 5 | 5698 | 475.84 |