Performance improvement via bagging in probabilistic prediction of chaotic time series using similarity of attractors and LOOCV predictable horizon.
Shuichi KurogiMitsuki ToidaniRyosuke ShigematsuKazuya MatsuoPublished in: Neural Comput. Appl. (2018)
Keyphrases
- chaotic time series
- short term
- mackey glass
- phase space
- neural network
- recurrent neural networks
- phase space reconstruction
- rbf network
- similarity measure
- dynamic behavior
- long term
- back propagation neural network
- prediction accuracy
- ensemble methods
- random forest
- feed forward neural networks
- chaotic systems
- genetic algorithm
- decision trees
- machine learning
- training set
- multi object
- function approximation
- learning algorithm
- artificial neural networks
- fault diagnosis
- probabilistic model