Classifying multiple (2+) features
4 vues (au cours des 30 derniers jours)
Afficher commentaires plus anciens
tafteh
le 20 Oct 2015
Réponse apportée : Walter Roberson
le 20 Oct 2015
Hi All, I have 2 (or more) feature variables in the dataset which are labeled 0 and 1 (total 2 classes). I am now using classify command in Matlab to do LDA classification. I am wondering if I use 3 or more features, would "classify" command accurately do the classification for me or not? It other words, does it classify using multiple features or only good for have 2 features in the dataset.
My other question is: how does it (classify/LDA) different from fisher's algorithm? Is it the same? Do I have to go to SVM instead all the above?
I would appreciate your assistance/guid on above. Best,
0 commentaires
Réponse acceptée
Walter Roberson
le 20 Oct 2015
classify() uses Discriminant Analysis and can handle multiple classes.
For other classification techniques, you can use the new http://www.mathworks.com/help/stats/classificationecoc-class.html which can handle any binary classifier (not just SVM)
0 commentaires
Plus de réponses (0)
Voir également
Catégories
En savoir plus sur Statistics and Machine Learning Toolbox dans Help Center et File Exchange
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!