Data Classification with Support Vector Machine Kernel Function

Abstract

Classification,is one of the most, important tasks for ,variousa pplication such,as,data ,Classification ,image, classification ,text ,categorization, micro- array, gene, expression, tone ,recognition, proteins, structure predictions,etc.The majority, of today's supervised, classification, algorithms ,are based on traditional, statistics, which can produce optimal, results when the sample, size approaches, infinity." In practice, however, only finite ,samples may be obtained. In this paper, a unique learning, method called ,Support Vector, Machine (SVM) is used, to data with two or more, classes such as Diabetes, data, Satellite, data , Shuttle data, and Heart, data. SVM is a strong ,machine learning ,algorithm that has achieved ,substantial success in, a variety ,of fields.They were first introduced, in the early 1990s, and they ,sparked ,a surge, in interestt, in machine ,learning." Vapnik laid, the groundwork, for SVMs, which are gaining ,traction in the field of machine learning, because to their many appealing features, and promising, empirical ,outcomes."SVM method does not suffer,the limitations, of data,dimensionality, and limited samples,[1] and [2]". The SVM which are ,important for classification, are learned from, the training ,data in our experiment.For all data samples, we have given,comparison findings, using different, kernel functions, in this research."