An Interactive Algorithm to Construct an Appropriate Nonlinear Membership Function Using Information Theory and Statistical Method.
Takashi HasuikeHideki KatagiriHiroe TsubakiPublished in: Complex Adaptive Systems (2015)
Keyphrases
- information theory
- k means
- clustering method
- initial values
- information theoretic
- relative entropy
- rate distortion theory
- computational complexity
- membership functions
- mdl principle
- fuzzy membership functions
- scaling factors
- learning algorithm
- membership degrees
- benchmark data sets
- fuzzy sets
- fuzzy logic
- similarity measure
- fuzzy controller
- fuzzy neural network
- support vector machine
- decision making
- conditional entropy
- cross validation
- computational intelligence
- motion estimation
- fuzzy reasoning
- image analysis
- artificial neural networks
- feature selection
- real time