期刊
SAUDI JOURNAL OF BIOLOGICAL SCIENCES
卷 24, 期 3, 页码 556-562出版社
ELSEVIER SCIENCE BV
DOI: 10.1016/j.sjbs.2017.01.026
关键词
Chemical mechanism; Algae growth; Water blooms; Prediction; Multi-factor
类别
资金
- Innovation ability promotion project of Beijing municipal colleges and universities [PXM2014_014213_000033]
- National Natural Science Foundation of China [51179002]
- Beijing Municipal Education Commission science and technology development plans [SQKM201610011009]
The formation process of algae is described inaccurately and water blooms are predicted with a low precision by current methods. In this paper, chemical mechanism of algae growth is analyzed, and a correlation analysis of chlorophyll-a and algal density is conducted by chemical measurement. Taking into account the influence of multi-factors on algae growth and water blooms, the comprehensive prediction method combined with multivariate time series and intelligent model is put forward in this paper. Firstly, through the process of photosynthesis, the main factors that affect the reproduction of the algae are analyzed. A compensation prediction method of multivariate time series analysis based on neural network and Support Vector Machine has been put forward which is combined with Kernel Principal Component Analysis to deal with dimension reduction of the influence factors of blooms. Then, Genetic Algorithm is applied to improve the generalization ability of the BP network and Least Squares Support Vector Machine. Experimental results show that this method could better compensate the prediction model of multivariate time series analysis which is an effective way to improve the description accuracy of algae growth and prediction precision of water blooms. (C) 2017 The Authors. Production and hosting by Elsevier B.V. on behalf of King Saud University.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据