This study discusses the development of a microcontroller-based water dispensing system by comparing two approaches: the conventional method and the decision tree algorithm. The system was tested on various volume variations and analyzed in terms of error and accuracy. The results show that the conventional method produced an average error of 20.5%, particularly high at smaller volumes. In contrast, the decision tree algorithm achieved an average error of only 2.0% and consistently maintained accuracy above 98%. Therefore, the decision tree algorithm proves to be superior in improving the accuracy and reliability of the automatic water dispensing system.
Copyrights © 2025