Classification Problem of ANN in Assessment of Environmental Quality

摘要

The advantage of artificial neural network is that there is no need to devise a mathematical model in order to perform a specific task. It processes information through interconnected processing elements (neurons). In assessment of environmental quality, ANN is an efficient and objective classification method. However according to our experience, ANN produces are not always comply with real situation, and sometimes, it can cause large errors with testing samples. These problems are caused by the nature of ANN itself. Studying of these problems increases our understanding of ANN classification.