Application of an engineering algorithm with software code (C4.5) for specific ion detection in the chemical industries

The development of an on-line computer-based classification system for the automatic detection of different ions, existing in different solutions, is addressed using a machine learning algorithm. Different parameters (current , mass and resistance) were collected simultaneously. Then these laboratory measurements are used by an algorithm software as a logged data file, resu lting in to inducing a decision tree. Later, a systematic software is desig ned based on the rules derived from this decision tree, to recognise the ty pe of unknown solution used in the experiment. This is a new approach to da ta acquisition in chemical industries involving conducting polymers. (C) 19 98 Published by Elsevier Science Ltd. All rights reserved.