Distributed GEP function mining on consistency merger in grid environment

摘要

Distributed function mining is an important field of distributed data mining. In order to solve local model merger of function mining in grid environments, this paper presents consistency merger of local function model (CMLFM). On the basis of CMLFM, distributed GEP function mining on consistency merger (DGEPFM-CM) is proposed which combines with grid service. Simulated experiments show that the time-consuming of DGEPFM-CM is less than traditional GEP. With the increasing of grid nodes, the global fitting error of DGEPFM-CM apparently decreases.