Sonderkolloquiumsvortrag: Prof. Dr. Petchporn Chawakitchareon (Environmental Engineering Department, Chulalongkorn University, Bangkok, Thailand)

09.04.2019 von 17:00 bis 18:00

Raum 408a, Hermann-Rodewald-Str. 3

Titel: Water Quality Index Analysis and Prediction

Abstract: Artificial neural network is a common method which has been used in many data science projects. This talk presents a comparison of prediction methods for water quality indexes using for classifying the water quality in rivers or canals. We compare data analysis and data mining results that can be obtained on the basis of full data records obtained in Thailand for the decade 2007-2017. Special attention is directed towards M5P, M5Rules and REPTree analysis algorithms compared to results from multilayer perceptron - one type of artificial neural network. Our experimental results show that the REPTree method yielded the highest accuracy to predict Water quality indexes comparing to other methods. For M5P and M5Rules, building models by using smoothing procedures and unpruned techniques appears to give out the best model to predict with the highest accuracy.

Prof. Dr. Bernhard Thalheim

Diesen Termin meinem iCal-Kalender hinzufügen