A hybrid PSO optimized SVM-based method for predicting of the cyanotoxin content from experimental cyanobacteria concentrations in the Trasona reservoir: A case study in Northern Spain
作者：
Highlights：
• A hybrid PSO–SVM-based model is built as a predictive model of the cyanotoxin content.
• Chlorophyll is a relevant parameter used to estimate the biomass production.
• The biological and physical–chemical variables in this process are studied in depth.
• The obtained regression accuracy of the hybrid PSO–RBF–SVM-based model is about 95%.
• The results show that PSO–SVM-based models can assist in the diagnosis of the cyanotoxin presence.
摘要
•A hybrid PSO–SVM-based model is built as a predictive model of the cyanotoxin content.•Chlorophyll is a relevant parameter used to estimate the biomass production.•The biological and physical–chemical variables in this process are studied in depth.•The obtained regression accuracy of the hybrid PSO–RBF–SVM-based model is about 95%.•The results show that PSO–SVM-based models can assist in the diagnosis of the cyanotoxin presence.
论文关键词：Support vector machines (SVMs),Particle swarm optimization (PSO),Harmful algal blooms (HABs),Cyanotoxins,Cyanobacteria,Regression analysis
论文评审过程：Received 9 February 2015, Available online 7 April 2015.
论文官网地址：https://doi.org/10.1016/j.amc.2015.03.075
