In order to solve the problem that the traditional radial basis function (RBF)\nneural network is easy to fall into local optimal and slow training speed in the\ndata fusion of multi water quality sensors, an optimization method of RBF\nneural network based on improved cuckoo search (ICS) was proposed. The\nmethod uses RBF neural network to construct a fusion model for multiple\nwater quality sensor data. RBF network can seek the best compromise between\ncomplexity and learning ability, and relatively few parameters need to\nbe set. By using ICS algorithm to find the best network parameters of RBF\nnetwork, the obtained network model can realize the non-linear mapping between\ninput and output of data sample. The data fusion processing experiment\nwas carried out based on the data released by Zhejiang province surface water\nquality automatic monitoring data system from March to April 2018. Compared\nwith the traditional BP neural network, the experimental results show\nthat the RBF neural network based on gradient descent (GD) and genetic algorithm\n(GA), the new method proposed in this paper can effectively fuse the\nwater quality data and obtain higher classification accuracy of water quality.
Loading....