SVMs can efficiently perform a non-linear classification using what is called the kernel trick, implicitly mapping their inputs into high-dimensional feature spaces.

The original maximum-margin hyperplane algorithm proposed by Vapnik in 1963 constructed a linear classifier. However, in 1992, Bernhard E. Boser, Isabelle M. Guyon and Vladimir N. Vapnik suggested a way to create nonlinear classifiers by applying the kernel trick .

The following links provides resources on applications of SVMs for two class and multi class cladsification

http://www.statsoft.com/Textbook/Support-Vector-Machines#Classification SVM

https://www.cs.sfu.ca/people/Faculty/teaching/726/spring11/svmguide.pdf

http://ce.sharif.ir/courses/85-86/2/ce725/resources/root/LECTURES/SVM.pdf

http://link.springer.com/article/10.1023/A:1011215321374

http://link.springer.com/content/pdf/10.1007/978-1-84996-098-4.pdf

https://www.cs.cornell.edu/people/tj/svm_light/svm_multiclass.html

Article Least Squares Support Vector Machine Classifiers

My professor always says SVM the best first choice for any classification task. The reason: SVM is one of the most robust and accurate algorithm among the other classification algorithms.

SVMs can efficiently perform a non-linear classification using what is called the kernel trick, implicitly mapping their inputs into high-dimensional feature spaces.

The original maximum-margin hyperplane algorithm proposed by Vapnik in 1963 constructed a linear classifier. However, in 1992, Bernhard E. Boser, Isabelle M. Guyon and Vladimir N. Vapnik suggested a way to create nonlinear classifiers by applying the kernel trick .

The following links provides resources on applications of SVMs for two class and multi class cladsification

http://www.statsoft.com/Textbook/Support-Vector-Machines#Classification SVM

https://www.cs.sfu.ca/people/Faculty/teaching/726/spring11/svmguide.pdf

http://ce.sharif.ir/courses/85-86/2/ce725/resources/root/LECTURES/SVM.pdf

http://link.springer.com/article/10.1023/A:1011215321374

http://link.springer.com/content/pdf/10.1007/978-1-84996-098-4.pdf

https://www.cs.cornell.edu/people/tj/svm_light/svm_multiclass.html

Article Least Squares Support Vector Machine Classifiers

Since SVM is one of the most used techniques, you should try it. The problem is to set parameters. You can try Optimum-Path Forest as well. It is parameterless.

Best,

SVM can be used for classification as well as pattern recognition purpose. Speech data, emotions and other such data classes can be used.

thanks, all  and thanks Behrouz for sharing the links. It will be the great help for me .

We can use SVM when a number of features are high compared to a number of data points in the dataset.  By using the correct kernel and setting an optimum set of parameters.

Hi Uday

SVM is one of the best classifier but not the best. In fact, no one could be the best.  It depends upon the problem which classifier would be suitable.

As for as, SVM is concerned, it is a suitable classifier in following cases:

1) When number of features (variables) and number of training data is very large (say millions of features and millions of instances (data)).

2) When sparsity in the problem is very high, i.e., most of the features have zero value.

3) It is the best for document classification problems where sparsity is high and features/instances are also very high.

4) It also performs very well for problems like image classification, genes classsification, drug disambiguation etc. where number of features are high.

It is one of the best, because of following things:

1) It uses Kernel trick

2) It is Optimal margin based classification technique in Machine Learning.

3) Good number of algorithms are proposed which utilizes problem structures and other smaller-smaller things like problem shrinking during optimization etc.

Thanks

Vinod

Panjab University Chandigarh