Modeling and design of evolutionary neural network for heart disease detection
This research is having purpose to find the alternatives to
the solution of complex medical diagnosis in detection of
heart disease where human knowledge is apprehended in a
general fashion. Successful application examples shown
previously that human diagnostic capabilities are
significantly worse than the neural diagnostic system. This
paper describes a new system for detection of heart disease
based on feed forward neural network architecture and
genetic algorithm. Hybridization has applied to train the
neural network using Genetic algorithm and proved
experimentally, proposed learning is more stable compare
to back propagation. Detail analysis has given with respect
to genetic algorithm behavior and its relationship with
learning performance of neural network. Affect of
tournament selection has analyzed to get more detailed
knowledge what is happening internally. With the proposed
system we hope that, design of diagnosis system for heart
disease detection will become easy, cost effective, reliable
and efficient.
Keywords: Heart disease, Neural network, Genetic
algorithm, Tournament selection
Download Full-Text
