Water quality classification method based on improved extreme learning machine

Abstract

The invention relates to a water quality classification method based on an improved extreme learning machine. The method comprises: firstly, carrying out principal component analysis on a sample, andcarrying out k-means clustering on the sample; secondly, preprocessing the sample, and initializing an ELM model; then determining cultural gene algorithm parameters; and finally, normalizing the surface water quality parameters of each evaluation region by using a normalization formula, inputting the normalized surface water quality parameters into the established MA-ELM model to obtain an outputresult, and comparing the output result with the simulation interval table of each level of the surface water quality to obtain the level of the water quality so as to finish water quality classification. According to the water quality classification method, the cultural gene algorithm is used for optimizing the input weight and the hidden layer neuron threshold value which are originally randomly generated by the extreme learning machine, and compared with a traditional neural network method, the classification precision of the water quality classification method is greatly improved.

Description

technical field [0001] The invention relates to a water quality classification method, in particular to a water quality classification method based on an improved extreme learning machine. Background technique [0002] Surface water refers to the general term of dynamic water and static water on the land surface, also known as "land water", including various liquid and solid water bodies, mainly rivers, lakes, swamps, glaciers, ice sheets, etc. It is one of the important sources of water for human life and a major component of water resources. Human activities have greatly affected the quality of surface water, such as air pollution, sewage discharge, use of agricultural chemicals, and over-exploitation of surface water resources. This has brought enormous pressure to the surface water ecosystem, resulting in the decline of surface water quality and biodiversity, the loss of biologically important habitats, and the general decline in the quality of life of local residents. ...

AI Technical Summary

Problems solved by technology

However, the neural network model currently used for water quality data processing is prone to fall into local optimum, and the training speed is also slow

Images