High-dimensionality priority selection scheme of bioinformatics information using Bernoulli distribution

Recently, as the amount of genetic information has been increasing following the completion of the human genome project, bioinformatics information management has been coming to the fore. However, since bioinformatics information is composed of diverse kinds of genetic information, users cannot easily approach and use it. In the present paper, a high-dimensionality information management scheme is proposes that enables users to select those pieces of bioinformatics information that are highly frequently used using the Bernoulli distribution so that users can easily approach those pieces of bioinformatics information that are preferred by them. The proposed scheme is an approach to high-dimensionality priority selection that requires the presentation of two or more pieces of bioinformatics information. In addition, in the case of the proposed scheme, since the order of priority of information is determined based on the kinds, functions, and characteristics of bioinformatics information, users can easily approach bioinformatics information according to their purpose of use of the information. According to the results of experiments, the proposed scheme showed a success rate 11.6 % higher than that of existing schemes in terms of bioinformatics information searches and the delay time of bioinformatics information services used by independent users was shown to be 17.3 % shorter than that of existing schemes .