Evolving a least square support vector machine using real coded shuffled complex evolution for property estimation of aqueous ionic liquids

被引：7

作者：

Razaz, Seyyedeh Parisa Seyyedi ^{[1
]}

Bazooyar, Bahamin ^{[2
]}

Pirhoushyaran, Tahereh ^{[1
]}

Shaahmadi, Fariborz ^{[1
]}

机构：

[1] Islamic Azad Univ, Dept Chem Engn, Dezful Branch, Dezful, Iran

[2] Staffordshire Univ, Turbulent Combust, Stoke On Trent ST4 2DE, Staffs, England

来源：

THERMOCHIMICA ACTA | 2018年 / 670卷

关键词：

Osmotic coefficient; LSSVM; SCE; Ionic liquids; Intelligent models; OSMOTIC COEFFICIENTS; THERMODYNAMIC PROPERTIES; BINARY-MIXTURES; WATER; PREDICTION; CHLORIDE; ELECTROLYTES; SOLUBILITY; BROMIDE; SYSTEM;

D O I：

10.1016/j.tca.2018.10.005

中图分类号：

O414.1 [热力学];

学科分类号：

摘要：

In this study, we demonstrate how least square support vector machine (LSSVM) evolution with the shuffled complex evolution (SCE) ameliorates the predictability and reliability of the support vector machine as an estimation tool for thermodynamic of ionic liquids solutions. This strategy is applied to forecast the osmotic coefficient of the 26 different ionic liquids by utilizing the 1409 available archival literature data points. Our methodology is the development of a hybrid SCE-LSSVM algorithm. Shuffled complex evolution is used to decide the hyper parameters of support vector machines so that all the initial weights can be searched and obtained intelligently. The evolution operators and parameters are carefully designed and set to avoid premature convergence and permutation problems. The results demonstrate that carefully designed SCE-LSSVM outperforms the structural risk minimization of support vector machines, predicting the properties of aqueous solutions in a way, even better than the available models.

引用

页码：27 / 34

页数：8

共 48 条

[41] Pattern detection of atherosclerosis from Carotid Artery Doppler Signals using fuzzy weighted pre-processing and Least Square Support Vector Machine (LSSVM) [J].

Polat, Kemal ;

Kara, Sadik ;

Latifoglu, Fatma ;

Gunes, Salih .

ANNALS OF BIOMEDICAL ENGINEERING, 2007, 35 (05) :724-732

[42] Statistically validated QSAR study of some antagonists of the human CCR5 receptor using least square support vector machine based on the genetic algorithm and factor analysis [J].

Mohsen Shahlaie ;

Afshin Fassihi ;

Alireza Pourhossein ;

Elham Arkan .

Medicinal Chemistry Research, 2013, 22 :1399-1414

[43] Statistically validated QSAR study of some antagonists of the human CCR5 receptor using least square support vector machine based on the genetic algorithm and factor analysis [J].

Shahlaie, Mohsen ;

Fassihi, Afshin ;

Pourhossein, Alireza ;

Arkan, Elham .

MEDICINAL CHEMISTRY RESEARCH, 2013, 22 (03) :1399-1414

[44] A Multi-Joint Continuous Motion Estimation Method of Lower Limb Using Least Squares Support Vector Machine and Zeroing Neural Network based on sEMG signals [J].

Zhongbo Sun ;

Xin Zhang ;

Keping Liu ;

Tian Shi ;

Jing Wang .

Neural Processing Letters, 2023, 55 :2867-2884

[45] Estimation of nitrogen, phosphorus, and potassium contents in the leaves of different plants using laboratory-based visible and near-infrared reflectance spectroscopy: comparison of partial least-square regression and support vector machine regression methods [J].

Zhai, Yanfang ;

Cui, Lijuan ;

Zhou, Xin ;

Gao, Yin ;

Fei, Teng ;

Gao, Wenxiu .

INTERNATIONAL JOURNAL OF REMOTE SENSING, 2013, 34 (07) :2502-2518

[46] Comparison of partial least square, artificial neural network, and support vector regressions for real-time monitoring of CHO cell culture processes using in situ near-infrared spectroscopy [J].

Zavala-Ortiz, Daniel A. ;

Denner, Aurelia ;

Aguilar-Uscanga, Maria G. ;

Marc, Annie ;

Ebel, Bruno ;

Guedon, Emmanuel .

BIOTECHNOLOGY AND BIOENGINEERING, 2022, 119 (02) :535-549

[47] Stream Flow Forecasting of Poorly Gauged Mountainous Watershed by Least Square Support Vector Machine, Fuzzy Genetic Algorithm and M5 Model Tree Using Climatic Data from Nearby Station [J].

Adnan, Rana Muhammad ;

Yuan, Xiaohui ;

Kisi, Ozgur ;

Adnan, Muhammad ;

Mehmood, Asif .

WATER RESOURCES MANAGEMENT, 2018, 32 (14) :4469-4486

[48] A robust combination approach for short-term wind speed forecasting and analysis - Combination of the ARIMA (Autoregressive Integrated Moving Average), ELM (Extreme Learning Machine), SVM (Support Vector Machine) and LSSVM (Least Square SVM) forecasts using a GPR (Gaussian Process Regression) model [J].

Wang, Jianzhou ;

Hu, Jianming .

ENERGY, 2015, 93 :41-56

← 1 2 3 4 5 →