A hybrid approach of support vector regression with genetic algorithm optimization for aquaculture water quality prediction

Liu, Shuangyin; Tai, Haijiang; Ding, Qisheng; Li, Bingbing; Xu, Ling; Wei, Yaoguang

doi:10.1016/j.mcm.2011.11.021

Cited by 207 publications

(72 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Stojanovic et al (2013) apply a self-adjusting GA to model the behavior of dams. Liu et al (2013) develop a real-time GA that forecasts water quality in river crab aquaculture. Nieto et al (2013) forecast the presence of cyanotoxins in the Trasona water reservoir of Northern Spain via GAs.…”

Section: Ga Applications In Statisticsmentioning

confidence: 99%

Genetic algorithms for cross-calibration of categorical data

Aboukhamseen

M’Hallah

2017

J. Mod. App. Stat. Meth.

View full text Add to dashboard Cite

The probabilistic problem of cross-calibration of two categorical variables is addressed. A probabilistic forecast of the categorical variables is obtained based on a sample of observed data. This forecast is the output of a genetic algorithm based approach, which makes no assumption on the type of relationship between the two variables and applies a scoring rule to assess the fitness of the chromosomes. It converges to a good-quality point probability forecast of the joint distribution of the two variables. The proposed approach is applied both at stationary points in time and across time. Its performance is enhanced when additional sampled data is included, and can be designed with different scoring rules or made to account for missing data.

show abstract

Section: Ga Applications In Statisticsmentioning

confidence: 99%

Genetic algorithms for cross-calibration of categorical data

Aboukhamseen

M’Hallah

2017

J. Mod. App. Stat. Meth.

View full text Add to dashboard Cite

show abstract

“…The CV has been used for testing the model accuracy so as to obtain the stable and reliable model structure [40]. In this paper, ten-fold cross-validation (10-CV) [41], one of the most commonly used versions of the CV, is adopted to determine the optimal and 2 of the LSSVR model for the NG consumption forecasts.…”

Section: Lssvr Model For Daily Ng Regressionmentioning

confidence: 99%

Daily natural gas consumption forecasting based on a structure-calibrated support vector regression approach

Bai

2016

Energy and Buildings

View full text Add to dashboard Cite

“…On the basis of the adaptation pattern data, the ASVM adaptation model for SA, SI, SC, and SW features can be built respectively. The radial basis kernel exp À λjjx i À x j jj 2 À Á is used as the kernel function in this example inspired by the empirical findings that radial basis kernel tends to give good performances under the general smoothness assumptions (Liu et al, 2013;Zhang et al, 2013), and by referring to our previous study (Qi et al, 2011), the reasonable values of ε and C in ASVM are set to 0.01 and 1000.…”

Section: The Construction Of Asvmmentioning

confidence: 99%