Biological Monitoring: a Comparison between Bayesian, Neural and Machine Learning Methods of Water Quality Classification.

摘要: Biological methods of monitoring river water quality have enormous potential but this is not presently being realised owing to inadequacies in data interpretation and classification. This paper describes the development testing several classification models based on Bayesian, neural machine learning techniques, compares their performance with two traditional models. It demonstrated, using an expertly classified test set, that ‘naive’ Bayesian multi-layered perceptrons can significantly out-perform methods. concluded these techniques provide most promising means realising full bio-monitoring, either acting separately or jointly as complementary ’experts’.