A preprocessing method for improving data mining techniques. Application to a large medical diabetes database.
Alain DuhamelM. C. NuttensPatrick DevosMonique PicavetRégis BeuscartPublished in: MIE (2003)
Keyphrases
- preprocessing
- database
- data mining techniques
- similarity measure
- databases
- significant improvement
- computational cost
- high precision
- medical data
- dynamic programming
- cost function
- pairwise
- computational complexity
- machine learning
- data mining
- support vector machine svm
- clustering method
- detection method
- neural network
- data sets