作者: Sirilak Areerachakul , Siripun Sanguansintukul , None
DOI: 10.20533/IJICR.2042.4655.2010.0004
关键词:
摘要: Water quality is one of the major concerns countries around world. This study endeavors to automatically classify water quality. The classes are evaluated using 6 factor indices. These factors pH value (pH), Dissolved Oxygen (DO), Biochemical Demand (BOD), Nitrate Nitrogen (NO3N), Ammonia (NH3N) and Total Coliform (T-Coliform). methodology involves applying data mining techniques classification regression tree (CART) compared with multilayer perceptron (MLP) neural network models. consisted 288 canals in Bangkok, Thailand. obtained from Department Drainage Sewerage Bangkok Metropolitan Administration during 2003-2007. results trees perform better than network. Classification exhibit a high accuracy rate at 99.96% classifying Bangkok. Subsequently, this encouraging result could be applied plan management source