Investigation of the effect of Training Data on the Performance of Support Vector Machine in Classification of BrainMR Images
Journal Title: International journal of Emerging Trends in Science and Technology - Year 2014, Vol 1, Issue 4
Abstract
In recent years, a wide research is being carried out on brain imaging which involves computer aided detection of abnormalities in brain. Out of many diagnostic imaging techniques for the early detection of any abnormal changes in brain tissues, Magnetic Resonance Imaging (MRI) is a widely-used imaging method. The shortage of radiologists for analyzing the brain MR images calls for an automated system to analyze and classify such medical images. Support Vector Machine (SVM) has been widely used in the recent years to classify brain MR images into different classes. SVM Classifiers perform the task of classification in two phases – training phase and testing phase. The amount of image data to be used for training plays a vital role in determining the accuracy of the SVM. This paper focuses on determining the optimal number of image data in the training set for which a better classification accuracy is obtained. Classification experiments with various percentages of data in the training set show that 80% of total dataset is the optimal one. Results also point out that Polynomial kernel function of SVM is more apt for brain MR images classification with classification accuracy of 100% when trained with 80% of data
Authors and Affiliations
Swetha K. T
Analyzing Sun Angles of Solar Time Dial for Design of Building Envelope Components for the Region of Andhra Pradesh, India
The solar radiation is a major factor for thermal condition in built forms. The residential and commercial buildings consume 45 to 55 percentage of the energy for thermal comforts. It was evident that the higher the ener...
Product Transfer Line
As we know that many industries carry their jobs manually and it creates defects in job. Many times we see that the job handling is difficult task. So this transfer line helps to transfer the job from one place to anothe...
Implementation and Comparison of Microstrip Patch Antenna and Co-Planar waveguide Antenna
The aim of this work is to design a microstrip patch antenna (MPA) and coplanar waveguide antenna (CPW) and then compared the performance of both antennas. The performance metrics, on the basis of which the antennas are...
Performance of a 32 Channels WDM System using Gain Flattened EDFA
The gain flattening of erbium doped fiber amplifier (EDFA) is essential for their application in wavelength division multiplexing (WDM) system. This paper attempts to design and analyse a 32 channels WDM system using EDF...
Nano-Hardness and Elasticity for Hydroxyapatite before and After of Immersing It into Simulated Body Fluid
Stoichiometric and anisotropic nanometer hydroxyapatite was made with co-precipitated method. The powder was compacted under uniaxial and isostatic press and lately sintered. Finally, the tablets were immersing in simula...