This book explains the principles of different types of Neural Networks such as Feed Forward, Cascade Feed Forward and Radial Basis Function Neural Networks. It also describes Fuzzy Logic concepts and Membership Functions. It is needed to mention that Neuron-Fuzzy Inference systems are come from Fuzzy Logic and Neural Network concepts; these are adaptive techniques that are given in detail in this book. Support Vector Machines are presented here as well. Applications such as direct current motors, student administration system, and electrical faults are employed to implement the above soft computing techniques.
This book is an extension of the Ph.D. dissertationentitled “Design of Intelligent Control System Basedon Soft Computing.” Three soft computing approachesbased lifelong learning control systems are presentedin this book. These systems can adapt variousenvironments through adjusting their own rule bases,such as fuzzy rule base or symbolic rule base,online. The adaptive mechanism emulates humanadaptive behaviors, and has capacities forintrospection, self-criticism and exploration. Thefirst two systems, i.e., SEICS (Self-Explorationprocess based Intelligent Control System) and mSEICS(multi-objective Self-Exploration process basedIntelligent Control System), are devoted to theadaptability with lifelong learning by means ofautomatically adjusting their fuzzy control rules.The third system, i.e., SCICS (Self- Creation processbased Intelligent Control System), concentrates onmimicking creative procedure of human via the fourstages: creative objectives, creative process,creativity measurement and knowledge transformation.
The study done in this book was designed as a focused preliminary exploration into the power of the genetic algorithm and fuzzy logic system to the prediction of cancer survival, The results of the experiments were very positive, comparing the outcome of the GA model with that of FL it shows the robustness of the GA model as prediction system.The two principal designs indicate that the use of genetic algorithms and fuzzy logic in NPC is definitely a fruitful endeavour. The results would suggest that genetic algorithms as standalone classifier models are better (based on the system designed in this research) for this sort of task than a fuzzy logic model.
Intelligent Transport System (ITS) is the intelligence invoked in the Transport System so that probability of occurrence of accidents can be reduced, to avoid accidents between vehicles it is necessary to classify the targets properly and then providing that information to each of the vehicles communicated with the network , and it will be possible when a efficient radar imaging technique will be there, by applying that technique and using returned energy from the target to the radar receiver, images of the targets can be constructed but due to presence of clutter it is not possible to get the returned energy only from the target to the radar. So there must be a efficient Clutter rejection technique that rejects the clutter in the radar receiver from the energy of interest to construct the radar image and to classify the targets. In this book Radar image is constructed by Joint time-frequency transform method, Target classification is done using the concepts of Supervised Artificial Neural Network,Clutter is rejected by MTI filtering technique and using Artificial Neural Network.
Economic operation is one of the important tasks in the operation and planning of power systems. In essence, it is a highly non-linear constrained optimization problem and its objective is to reduce the total generation cost of units, while satisfying several linear, non-linear equality and inequality constraints. Conventionally, several classical methods have been applied to solve constrained economic generation problems. In these conventional classical methods for solution of economic generation problems, an essential assumption is that the incremental cost curves of the units are monotonically increasing piecewise-linear functions. Unfortunately, this assumption may render these methods infeasible because of nonlinear characteristics in practical systems. These nonlinear characteristics of a generator include discontinuous prohibited zones, ramp rate limits, and cost functions which are not smooth or convex. The problem becomes more complicated when one desires to reduce the effects of harmful pollutants simultaneously. This book explores the applications of modern soft computing techniques to solve constrained economic generation problems.