Open AccessOptimization of Metagenome Sequence Identification with Naive Bayes and Certainty Factor
Author(s) -
Dian Kartika Utami,
Herfina,
Iyan Mulyana
Publication year - 2019
Publication title -
iop conference series. materials science and engineering
Language(s) - English
Resource type - Journals
eISSN - 1757-899X
pISSN - 1757-8981
DOI - 10.1088/1757-899x/621/1/012002
Subject(s) - naive bayes classifier , metagenomics , bayes factor , artificial intelligence , identification (biology) , bayes' theorem , phylogenetic tree , classifier (uml) , certainty , computer science , machine learning , pattern recognition (psychology) , data mining , biology , statistics , computational biology , mathematics , bayesian probability , genetics , ecology , gene , geometry , support vector machine
Metagenome studies are an important step in taxonomic grouping. Taxonomic grouping can be done using the binning method. Binning is a process to determine the contigs of each group of phylogenetic species. In this study, Binning was carried out using the Supervise Learning approach. We use the Naïve Bayes Classifier method and Certainty Factor. The classification process is carried out on phylum taxon levels. many of the organisms used were 50 organisms and the length of the fragments used was 500 bp and many readings were 1000 readings. The accuracy results obtained by the Naive Bayes method are 62.5%. While the accuracy obtained in the Certainty Factor method is 54.45%. From the results of the two methods of testing, it can be concluded that Naive Bayes is the best method of classification compared to Certainty Factor.