Data surveyor: the nuggets in parallel
Advances in knowledge discovery and data mining
Machine Learning for the Detection of Oil Spills in Satellite Radar Images
Machine Learning - Special issue on applications of machine learning and the knowledge discovery process
Bump hunting in high-dimensional data
Statistics and Computing
Expert Systems with Applications: An International Journal
Responder identification in clinical trials with censored data
Computational Statistics & Data Analysis
PRIM versus CART in subgroup discovery: When patience is harmful
Journal of Biomedical Informatics
Expert Systems with Applications: An International Journal
Hi-index | 12.05 |
This paper deals with process optimization, which establishes the optimal settings of process variables to achieve a better quality. To this end, the patient rule induction method (PRIM), widely used in various application areas, could be adopted. However, the PRIM may fail to provide successful solutions when some process variables are in discrete types. Thus, we propose a new PRIM-like method specially to deal with ordinal discrete variables. For an illustrative purpose, the proposed method is applied to a real steel-making process. Also, performance of the proposed method is compared with the original PRIM through an extensive simulation using artificial data sets.