Journal:Informatica
Volume 13, Issue 3 (2002), pp. 333–344
Abstract
In the paper two methods for data structure analysis and visualisation are presented: the simultaneous nonlinear mapping (Sammon, 1969) and the sequential one (Montvilas, 1995). These two methods were compared according ability to map the data on the plane, mapping accuracy and a mapping time. It was showed that the sequential nonlinear mapping has some bigger total mapping error but needs considerable less calculation time than that of the simultaneous one. Examples are given.
Journal:Informatica
Volume 10, Issue 2 (1999), pp. 231–244
Abstract
In this paper two popular time series prediction methods – the Auto Regression Moving Average (ARMA) and the multilayer perceptron (MLP) – are compared while forecasting seven real world economical time series. It is shown that the prediction accuracy of both methods is poor in ill-structured problems. In the well-structured cases, when prediction accuracy is high, the MLP predicts better providing lower mean prediction error.