Performance Improvement via Bagging in Ensemble Prediction of Chaotic Time Series Using Similarity of Attractors and LOOCV Predictable Horizon.
Mitsuki ToidaniKazuya MatsuoShuichi KurogiPublished in: ICONIP (4) (2016)
Keyphrases
- chaotic time series
- ensemble methods
- neural network
- ensemble learning
- prediction accuracy
- phase space
- mackey glass
- short term
- ensemble classifier
- base classifiers
- recurrent neural networks
- rbf network
- random forest
- imbalanced data
- ensemble selection
- classifier ensemble
- ensemble members
- phase space reconstruction
- dynamic behavior
- long term
- decision trees
- back propagation neural network
- generalization ability
- training set
- learning algorithm
- feed forward neural networks
- chaotic systems
- radial basis function
- multi object
- machine learning
- ordinary differential equations
- feature selection
- function approximation
- feature subset