| Presentation | 2005-12-09 Splitting the feature subset selection of multiclass support vector machines Xin HU, Mauricio KUGLER, Anto Satriyo NUGROHO, Susumu KUROYANAGI, Akira IWATA, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | One drawback on the use of Support Vector Machines (SVM) in real applications is its slow classification speed, proportional to the product of number of features and number of support vectors. Feature Subset Selection (FSS) is one way for reducing the dimensionality, normally reducing the number of support vectors, and consequently the recognition time. However, for the multiclass SVM, applying FSS in the whole input space does not achieve an optimal feature subset for each independent binary classifier. This work proposes a new structure, in which the FSS is performed independently for each SVM. The experiments with real world data showed a much higher average dimensionality reduction, decreasing the recognition time by several orders with a comparable performance with the full features set. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | feature subset selection / support vector machine / multiclass SVM / support vectors / multiclass classification problems / SBS |
| Paper # | NC2005-86 |
| Date of Issue |
| Conference Information | |
| Committee | NC |
|---|---|
| Conference Date | 2005/12/2(1days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | |
| Vice Chair | |
| Secretary | |
| Assistant | |
| Paper Information | |
| Registration To | Neurocomputing (NC) |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Splitting the feature subset selection of multiclass support vector machines |
| Sub Title (in English) | |
| Keyword(1) | feature subset selection |
| Keyword(2) | support vector machine |
| Keyword(3) | multiclass SVM |
| Keyword(4) | support vectors |
| Keyword(5) | multiclass classification problems |
| Keyword(6) | SBS |
| 1st Author's Name | Xin HU |
| 1st Author's Affiliation | The authors are with the Department of Computer Science & Engineering, Nagoya Institute of Technology() |
| 2nd Author's Name | Mauricio KUGLER |
| 2nd Author's Affiliation | The authors are with the Department of Computer Science & Engineering, Nagoya Institute of Technology |
| 3rd Author's Name | Anto Satriyo NUGROHO |
| 3rd Author's Affiliation | The author is with the School of Life System Science & Technology, Chukyo University |
| 4th Author's Name | Susumu KUROYANAGI |
| 4th Author's Affiliation | The authors are with the Department of Computer Science & Engineering, Nagoya Institute of Technology |
| 5th Author's Name | Akira IWATA |
| 5th Author's Affiliation | The authors are with the Department of Computer Science & Engineering, Nagoya Institute of Technology |
| Date | 2005-12-09 |
| Paper # | NC2005-86 |
| Volume (vol) | vol.105 |
| Number (no) | 457 |
| Page | pp.pp.- |
| #Pages | 6 |
| Date of Issue | |