Research on Availability of Satellite Images Based on Immune Feedback Learning Fuzzy Neural Network.
ABSTRACT In this paper, we propose a fuzzy neural network based on immune feedback learning (FNNBIFL) for the availability classifier of satellite images, which accelerates the learning speed, solves the problem of being trapped in the local minimum and improves the learning performance of fuzzy neural network. Using 122 satellite images, we compare the recognition results of the availability classifier trained by FNNBIFL or the traditional BP algorithm. Those results show that the recognition errors of FNNBIFL are reduced by 5.1%, and its learning speed is improved by 55%.
Conference Proceeding: A self-tuning immune feedback controller for controlling mechanical systems[show abstract] [hide abstract]
ABSTRACT: Summary form only given. The application of biological-information processing mechanisms to control systems promises greater flexibility and may make it possible to construct a control system whose performance is better than that of conventional control systems. Biological immune systems have learning, memory, and pattern-recognition abilities. The application of some of these abilities to control/sensing systems has been studied; we have focused on the immune feedback mechanism. An immune feedback mechanism simultaneously responds to foreign materials and stabilizes itself. We examine an engineering application of a biological immune system and propose an immune feedback controller. We propose an immune feedback law based on the functioning of biological T-cells; it includes both at active term, which controls response speed and an inhibitive term, which controls stabilization effect. We also describe a self-tuning immune feedback controller based on the immune feedback law whose parameters are automatically tuned by using neural networks. Experimental results for velocity tracking control of a DC servo motor confirmed the validity of our immune feedback law and also demonstrated the effectiveness of the self-tuning immune feedback controller for controlling practical systemsAdvanced Intelligent Mechatronics '97. Final Program and Abstracts., IEEE/ASME International Conference on; 07/1997
- [show abstract] [hide abstract]
ABSTRACT: The architecture and learning procedure underlying ANFIS (adaptive-network-based fuzzy inference system) is presented, which is a fuzzy inference system implemented in the framework of adaptive networks. By using a hybrid learning procedure, the proposed ANFIS can construct an input-output mapping based on both human knowledge (in the form of fuzzy if-then rules) and stipulated input-output data pairs. In the simulation, the ANFIS architecture is employed to model nonlinear functions, identify nonlinear components on-line in a control system, and predict a chaotic time series, all yielding remarkable results. Comparisons with artificial neural networks and earlier work on fuzzy modeling are listed and discussed. Other extensions of the proposed ANFIS and promising applications to automatic control and signal processing are also suggestedIEEE Transactions on Systems Man and Cybernetics 06/1993;
Conference Proceeding: Bayesian Learning of Neural Networks by Means of Artificial Immune Systems[show abstract] [hide abstract]
ABSTRACT: Once the design of artificial neural networks (ANN) may require the optimization of numerical and structural parameters, bio-inspired algorithms have been successfully applied to accomplish this task, since they are population-based search strategies capable of dealing successfully with complex and large search spaces, avoiding local minima. In this paper, we propose the use of an artificial immune system for learning feedforward ANN's topologies. Besides the number of neurons in the hidden layer, the algorithm also optimizes the type of activation function for each node. The use of a Bayesian framework to infer the weights and weight decay terms as well as to perform model selection allows us to find neural models with high generalization capability and low complexity, once the Occam's razor principle is incorporated into the framework. We demonstrate the applicability of the proposal on seven classification problems and promising results were obtained.Neural Networks, 2006. IJCNN '06. International Joint Conference on; 01/2006