Predicting Bacteria in Freshwater based on Environmental Factors by Machine Learning

• Main Authors: Billy Susilo, 關華明
• Other Authors: Jui-Sheng Chou
• Format: Others
• Language: en_US
• Published: 2018
• Online Access: http://ndltd.ncl.edu.tw/handle/heyt38

碩士 === 國立臺灣科技大學 === 營建工程系 === 106 === The main goal of microbial ecology is to understand the relationship between earth’s microbial community and the environment. This study develops a bioclimatic modeling approach that leverages artificial intelligence techniques to identify the bacteria species in freshwater as a function of environmental factors. Feature reduction and selection are both utilized in the data preprocessing owing to the scarce of available data points collected and missing values of environmental attributes from the river in Southeast China. An optimized machine learner, which supports the adjustment to the multiple-output prediction form, is used in bioclimatic modeling. The accuracy of prediction and applicability of the model can help microbiologists and ecologists in quantifying the predicted bacteria species for further experimental planning with minimal expenditure, which in present day become one of the most serious issues when facing dramatic changes of environmental conditions caused by global warming scenario. This work presents a neoteric approach for potential use in predicting microbial structures in the environment.