A massively parallel architecture for a self-organizing neural pattern recognition machine
Computer Vision, Graphics, and Image Processing
Algorithms for clustering data
Algorithms for clustering data
Adaptive pattern recognition and neural networks
Adaptive pattern recognition and neural networks
International Journal of Approximate Reasoning
Neural-Network-Based Fuzzy Logic Control and Decision System
IEEE Transactions on Computers - Special issue on artificial neural networks
Neural networks and fuzzy systems: a dynamical systems approach to machine intelligence
Neural networks and fuzzy systems: a dynamical systems approach to machine intelligence
Fuzzy logic, neural networks, and soft computing
Communications of the ACM
Fuzzy logic and neurofuzzy applications explained
Fuzzy logic and neurofuzzy applications explained
Neural network based fuzzy logic decision systems for multispectral image analysis
Neural, Parallel & Scientific Computations
Neuro-fuzzy and soft computing: a computational approach to learning and machine intelligence
Neuro-fuzzy and soft computing: a computational approach to learning and machine intelligence
The Fuzzy Systems Handkbook with Cdrom
The Fuzzy Systems Handkbook with Cdrom
Fuzzy Sets, Neural Networks and Soft Computing
Fuzzy Sets, Neural Networks and Soft Computing
Expert Systems: Principles and Programming
Expert Systems: Principles and Programming
Neural Fuzzy Control Systems with Structure and Parameter Learning
Neural Fuzzy Control Systems with Structure and Parameter Learning
Artificial Neural Networks for Image Understanding
Artificial Neural Networks for Image Understanding
Fuzzy Neural Network Models for Classification
Applied Intelligence
The modified self-organizing fuzzy neural network model for adaptability evaluation
LSMS'07 Proceedings of the 2007 international conference on Life System Modeling and Simulation
Hi-index | 0.00 |
In this paper, we consider neural-fuzzy models formultispectral image analysis. We consider both supervised andunsupervised classification. The model for supervisedclassification consists of six layers. The first three layersmap the input variables to fuzzy set membership functions. Thelast three layers implement the decision rules. The modellearns decision rules using a supervised gradient descentprocedure. The model for unsupervised classification consists oftwo layers. The algorithm is similar to competitive learning.However, here, for each input sample, membership functions ofoutput categories are used to update weights. Input vectors arenormalized, and Euclidean distance is used as the similaritymeasure. In this model if the input vector does not satisfy the“similarity criterion,” a new cluster is created; otherwise, theweights corresponding to the winner unit are updated using thefuzzy membership values of the output categories. We havedeveloped software for these models. As an illustration, themodels are used to analyze multispectral images.