Abstract—Unlike direct treatment in the past, nowadays, data mining of information of diseases is very useful to cure patients. Also, with prediction of DNA sequence of specific illnesses, lots of people can avoid them. Bioinformatics, study of union of life science, biology and informatics, becomes one of the most important subject to the future medical industry. A number of scientists and engineers have developed this area and as a result, various methodologies in aligning DNA sequences such as hidden markov model, artificial neural networks and support vector machines were developed during the last few decades. Especially, Support Vector Machine(SVM) is used in Supervised Learning, finding the furthermost hyperplane that separate given data. Unlike other methods, we can get more sophisticated and accurate results with learning method. Because of using SVM that have little parameters, we can also simplify the complex pattern and it is so effective in data analysis that we can easily investigate elements which have an effect on results. Moreover, to improve exactitude our study, we search and use DNA sequence data about HIV from NCBI( National Center for Biotechnology Information ), which have reliable and numerous data.

Index Terms—Human immunodeficiency virus (HIV), support vector machine (SVM), DNA sequence.

The authors are with the Hankuk Academic of Foreign Studies, Yongin, Korea (e-mail: dydakchry@naver.com, tsyoon@hafs.hs.kr).

Cite: Cheolho Heo and Taeseon Yoon, "Deeper Understanding about Attributes of HIV Employing Support Vector Machine," International Journal of Bioscience, Biochemistry and Bioinformatics vol. 4, no. 5, pp. 336-339, 2014.