Transcript
Support Vector Machine
Putri W Novianti
Victor L Jong
Biostatistics & Research Support
Julius Center for Health Sciences and Primary Care
University Medical Center Utrecht
• Binary classification method
• The method finds the best decision hyperplane that separate sample from
two classes with maximum margin
2 Support Vector Machine
3 Support Vector Machine
[1]
4 Support Vector Machine
[1]
5 Support Vector Machine
[1]
6 Support Vector Machine
[1]
7 Support Vector Machine
[1]
8 Support Vector Machine
[1]
9 Support Vector Machine
[1]
10 Support Vector Machine
[1]
11
What if the problem is not linearly separable?
Support Vector Machine
[2]
12 Support Vector Machine
13 Support Vector Machine
[1]
14 Support Vector Machine
[1]
15 Support Vector Machine
[1]
16 Support Vector Machine
[1]
17 Support Vector Machine
[4]
18 Support Vector Machine
[3]
- SVM only handle binary classification
- Although binary classification is the most common classification in microarray, multiclass outcome could be occur in practice
- Modification is needed to handle multiclass outcome
- one-versus-rest (OVR)
- one-versus-one (OVO)
19
Multiclass outcome
Support Vector Machine
[2]
Multiclass outcome
20 Support Vector Machine
[2]
OVR-SVM
21 Support Vector Machine
[2]
22
OVO-SVM
Support Vector Machine
[2]
23 Support Vector Machine
[5]
Example 1. Classification in Iris Data
24 Support Vector Machine
[5]
25 Support Vector Machine
Example 1. Classification in Iris Data
[5]
SVM for Regression
26 Support Vector Machine
SVM for Regression
27 Support Vector Machine
28 Support Vector Machine
29 Support Vector Machine
30 Support Vector Machine
31
References
[1] Zhang, X. Support Vector Machine. Lecture slides on Data Mining course. Fall 2010, KSA: KAUST
[2] Statnikov, A. et al. 2005. A comprehensive evaluation of multicategory classification methods for microarray gene expression cancer diagnosis. Bioinformatics, 21:5, 631-643
[3] Hastie, T., Tibshirani, R., Friedman, J. The elements of statistical learning, second edition. 2009. New York: Springer
[4] Guyon, I et al. 2002. Gene selection for cancer classification using support vector machines. Machine Learning, 49, 389-422
[5] Meyer, D. et al. 2012. R package: e1071.
32 Support Vector Machine
top related