Scribd
Upload
14 views

Classification: SV III I

The document discusses using support vector machines (SVM) for classification with high-dimensional data. It describes using SVM with Gaussian RBF kernels for classification and evaluating performance with metrics like accuracy and area under the ROC curve. Experiments use SVM with different feature subsets on 2700 regions of interest to classify them and compare area under the curve results.

Uploaded by

umair
Copyright
© © All Rights Reserved
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
14 views

Classification: SV III I

The document discusses using support vector machines (SVM) for classification with high-dimensional data. It describes using SVM with Gaussian RBF kernels for classification and evaluating performance with metrics like accuracy and area under the ROC curve. Experiments use SVM with different feature subsets on 2700 regions of interest to classify them and compare area under the curve results.

Uploaded by

umair
Copyright
© © All Rights Reserved
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 2

Classification

The number of features in each region are quite large bring about the number of dimension of vector space which
we should consider to classify the data are sketching out. In addition, there is always the overlapping of the data
class corresponding to the features in the sample region. Applying Support Vector Machine (SVM), a state-of-art
classification method introduced in 1992 [15] to solve this problem takes many advantages in this case.
Given a set of training data x1 xn Rdx1 with corresponding labels yi {-1,1}. SVMs seek a separating
hyperplane with the maximum margin
1
min 1 subject to ( ) 1 and 0
2
N
TT
iiiii
i
WWCyWxb
where C is the parameter controlling the trade-off between a large margin and less constrained violation. i are slack
variables which allow for penalized constraint violation.
Equivalently, with Lagrange multipliers i for the first set of constraints can be used to write the optimization
problem for SVMs in the dual space. By solving a quadratic programming problem, the solution for the Lagrange
multiplier can be obtained. Finally, the SVM classifier takes the form
#
1
(),
SV
iii
i
f x sign yK x x b
where #SV represents the number of support vectors and the kernel function K(.,.).
In this paper, we use a nonlinear SVM classifier with Gaussian RBF kernel
2
1
( ) .exp
m
ii
i
fxxxC
where x is input data and. is constant while C and must be tuned to get the best classification performance.
402 M.P. Nguyen et al. / Procedia Computer Science 20 ( 2013 ) 399 – 405
2.4. Performance evaluation
To evaluate the performance of the SVM classifier, the Receiver Operating Characteristic (ROC) curve is used.
The ROC curve is constructed based on two statistic factors which are the sensitivity and the specificity, and the
accuracy of SVM is then computed [15]. The best possible classifier would yield when the ROC curve tends to the
upper left corner representing 100% sensitivity and 100% specificity.
The accuracy value (ACC) to estimate the performance of classification process is given by
ACC TP TN x100%
TP FP TN FN
Another parameter is used to estimate SVM performance is area under the curve (AUC). The SVM classifier is
called ideal with 100% accuracy when the AUC of its ROC approaches 1 and when AUC equals 0.5, SVM is
random classifier. AUC is given by
110
ij
1
= with ( ) ( )
nn
i j ij
AUC f xi f xi
nn
where f(.) is denoted as decision function of classifier, x+ and x-- respectively denote the positive and negative
samples and n+, n-- are respectively the number of positive and negative examples and the 1 is defined as 1 if the
predicate is holds and 0 otherwise.
3. Experiments and Discussions
Our proposed method is evaluated on total number of 2700 detected RoIs [14]. Six input features as mentioned
above and nonlinear SVM classifier with Gaussian RBF kernel are used. In this study, we use 10-fold cross
validation method to train and test the classifier. The dataset is equally partitioned into 10 folds. For each of 10
experiments, use (10-i) folds for training and i folds for testing. Each fold is used 10 times in training as well as in
testing. In this evaluation, values of i is changed from 1 to 9.
Figure 2 shows obtained AUCs with different i or different ratios between training folds and testing folds
corresponding to two feature subsets {BVLC2x2mean, BVLC3x3mean, BVLC4x4mean} or {BVLC Mean} and
{BVLC2x2var, BVLC3x3var, BVLC4x4var} or {BVLC Var}. It is easy to realize that in most of case, using
{BVLC Var} feature subset gives higher AUC value. The best AUC value is archived with i = 6.

You might also like