A GA-based algorithm for searching optimal parameters in n-dimension space

Problems as function optimization and building discrimination function for pattern classification can be transferred into the problem to search optimal parameters in n-dimension space. The approaches based on ANN or gradient hill climb algorithm have limitations such as the function form and local optimum. A GA-based algorithm for searching optimal parameters in n-dimension space is presented, which encodes movement direction and distance and searches from coarse to precise. The algorithm can realize global optimization and improve the search efficiency, can be applied effectively in industrial optimization, data mining, and pattern recognition. Two examples are given to prove the effect of the algorithm.