Learning internal representations by error propagation
Parallel distributed processing: explorations in the microstructure of cognition, vol. 1
Instance-Based Learning Algorithms
Machine Learning
C4.5: programs for machine learning
C4.5: programs for machine learning
Data mining: concepts and techniques
Data mining: concepts and techniques
A Fuzzy-Rough Approach for Case Base Maintenance
ICCBR '01 Proceedings of the 4th International Conference on Case-Based Reasoning: Case-Based Reasoning Research and Development
Hi-index | 0.00 |
Knowledge acquisition for a case-based reasoning system from domain experts is a bottleneck in the system development process. With the huge amounts of data that have become available, it would be useful to derive automatically representative cases from available databases rather than acquiring them from domain experts. This paper presents two algorithms using similarity-based rough set theory to derive cases automatically from available databases. The first algorithm SRS1 requires the user to decide the similarity thresholds for the objects in a database, while the second algorithm SRS2 can automatically select proper similarity thresholds. These algorithms require fewer parameters from domain experts than other case generation algorithms. Also they can tackle noise and inconsistent data in the database and select a reasonable number of the representative cases from the database. The experimental results were compared with those from well-known data mining systems, such as rule induction systems and neural network systems.