A New Adaptive Genetic Algorithm

Genetic algorithm is stochastic searching and optimization method using concept of natural evolution and genetics. Its predominance lies in effective resolving non-linear problems, which is difficult for traditional methods. Genetic algorithm has ability of global search and is easy to implement. Its few limitation on the presumption of the solution space, wide adaptability and parallelism make it successfully applied in many areas, including function optimizations, machine learning, pattern recognition and self-adaptive control systems. Genetic algorithm is becoming a hot area in artificial intelligence.Simple genetic algorithm is a heuristic searching algorithm. Its searching for the best result is not perfect. It has some shortages such as slow convergence, bad stability and premature phenomenon in application. Existing adaptive genetic algorithm has local optimization solution. In order to solve the disadvantages of simple genetic algorithm and existing adaptive genetic algorithm, some existing improved creation of the initial population and genetic operators with good capability is used. A new adaptive genetic algorithm is presented on the basic of the existing adaptive genetic algorithm to improve the crossover probability and mutation probability. It bases the fitness value to adjust the crossover probability and mutation probability automatically. Finally, some experiments show that the proposed new algorithm is clearly improved in convergent speed and stability and gets the expectation effect.