Implementation of mutual information and bayes theorem for classification microarray data

• Published in: Journal of physics. Conference series Vol. 971; no. 1; pp. 12011 - 12018
• Main Authors: Purbolaksono, Mahendra Dwifebri, Widiastuti, Kurnia C, Mubarok, Mohamad Syahrul, Adiwijaya, Ma'ruf, Firda Aminy
• Format: Journal Article
• Language: English
• Published: Bristol IOP Publishing 01.03.2018
• Subjects: Bayes Theorem; Bayesian analysis; Classification; Machine learning; Physics; Statistical analysis
• ISSN: 1742-6588; 1742-6596
• DOI: 10.1088/1742-6596/971/1/012011

Microarray Technology is one of technology which able to read the structure of gen. The analysis is important for this technology. It is for deciding which attribute is more important than the others. Microarray technology is able to get cancer information to diagnose a person's gen. Preparation of microarray data is a huge problem and takes a long time. That is because microarray data contains high number of insignificant and irrelevant attributes. So, it needs a method to reduce the dimension of microarray data without eliminating important information in every attribute. This research uses Mutual Information to reduce dimension. System is built with Machine Learning approach specifically Bayes Theorem. This theorem uses a statistical and probability approach. By combining both methods, it will be powerful for Microarray Data Classification. The experiment results show that system is good to classify Microarray data with highest F1-score using Bayesian Network by 91.06%, and Naïve Bayes by 88.85%.