Analysis of selected algal growth (Pyrrophyta) in tropical lake using Kohonen self organizing feature map (SOM) and its prediction using rule based system

Abstract

In this paper we describe the feasibility of applying Kohonen self organizing feature maps (SOM) and rule based system to determine the growth of selected algal division, Pyrrophyta using limnological time-series data of tropical Putrajaya Lake and Wetlands (Malaysia). A rule based model was developed based on the rules extracted from the SOM to model and predict Pyrrophyta growth. Input parameters are selected based on correlation analysis. Input parameters selected are temperature, pH and Biochemical Oxygen Demand (BOD). The effectiveness of this system was tested on an actual tropical lake data that is Putrajaya Lake and Wetlands which yields an acceptable high level of accuracy.