A Practical Method Based on Bayes Boundary-Ness for Optimal Classifier Parameter Status Selection.
David HaYuya TomotoshiMasahiro SendaHideyuki WatanabeShigeru KatagiriMiho OhsakiPublished in: J. Signal Process. Syst. (2020)
Keyphrases
- high accuracy
- high precision
- preprocessing
- synthetic data
- clustering method
- smoothing parameter
- feature extraction
- significant improvement
- cost function
- dynamic programming
- computational cost
- real world
- classification accuracy
- selection scheme
- bayes classifier
- segmentation method
- mutual information
- support vector machine
- prior knowledge
- artificial neural networks
- video sequences
- decision trees