Vous suivez désormais cette soumission
- Les mises à jour seront visibles dans votre flux de contenu suivi
- Selon vos préférences en matière de communication il est possible que vous receviez des e-mails
This simple code, generates the ECOC matrix for both dense and sparse schemes. It is more efficient in terms of speed than previously seen Matlab files to generate ECOC codes. This efficiency is due to two improvements:
1- it produces each column at a single command
2- Before generation of the whole matrix, it checks the validity of the ECOC Matrix by checking two criteria:
A: 1st criterion: each column had to have at least one +1 and one -1 value
B: 2nd criterion: each column and its negative should not be the same as its previous columns
This efficiency is more important in problems with relatively large number of classes..
Please kindly cite:
Bagheri, M. A., Gao, Q. and Escalera, S., "Efficient pairwise classification using Local Cross Off strategy", to appear, The 25th Canadian Conference on Artificial Intelligence (AI 2012), Toronto, May 28 - 30, 2012.
Citation pour cette source
Mohammad Ali Bagheri (2026). Generate "Error Correcting Output Codes (ECOC)" matrix (https://fr.mathworks.com/matlabcentral/fileexchange/36223-generate-error-correcting-output-codes-ecoc-matrix), MATLAB Central File Exchange. Extrait(e) le .
Catégories
En savoir plus sur Support Vector Machine Classification dans Help Center et MATLAB Answers
Informations générales
- Version 1.0.0.0 (2,38 ko)
Compatibilité avec les versions de MATLAB
- Compatible avec toutes les versions
Plateformes compatibles
- Windows
- macOS
- Linux
| Version | Publié le | Notes de version | Action |
|---|---|---|---|
| 1.0.0.0 |
