Development of a self-organizing neural network for estimating environmental factors characterizing a microbial community.

Research Project

Project/Area Number	15K16066
Research Category	Grant-in-Aid for Young Scientists (B)
Allocation Type	Multi-year Fund
Research Field	Soft computing
Research Institution	Ube National College of Technology
Principal Investigator	Misawa Hideaki 宇部工業高等専門学校, 電気工学科, 准教授 (40636099)
Project Period (FY)	2015-04-01 – 2018-03-31
Project Status	Completed (Fiscal Year 2017)
Budget Amount *help	¥2,600,000 (Direct Cost: ¥2,000,000、Indirect Cost: ¥600,000) Fiscal Year 2016: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000) Fiscal Year 2015: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
Keywords	自己組織化ニューラルネットワーク / 異種データ統合 / 環境要因 / 微生物群集 / 自己組織化ネットワーク / 自己組織化マップ / 微生物群集解析
Outline of Final Research Achievements	The objective of this research was to develop a method for analyzing microbial community data based on an extended model of the self-organizing map. We developed a new learning algorithm for self-organizing maps including relational and higher-rank self-organizing maps to estimate common factors from two data sets. The proposed method was applied to artificial data sets and its performance was confirmed. In addition, the proposed method was applied to a real microbial community data set and the possibility of applying the proposed to real data sets was confirmed.

Report

(4 results)