Advantages of support vector machine in QSPR studies for predicting auto-ignition temperatures of organic compounds

Predicting the auto-ignition temperatures of organic compounds from molecular structure using support vector machine

“…As our similar previous work [33], a general comparison is also presented. Regarding the input parameters used in the models, our previous work [33] employed the same six molecular descriptors as used in reference [4] and [5], which included unconventional physicochemical parameters such as critical pressure and parachor, while the presented model employs nine theoretical descriptors which can be calculated solely from the molecular structure.…”

“…Regarding the input parameters used in the models, our previous work [33] employed the same six molecular descriptors as used in reference [4] and [5], which included unconventional physicochemical parameters such as critical pressure and parachor, while the presented model employs nine theoretical descriptors which can be calculated solely from the molecular structure. Regarding the statistical parameters of the models, the presented model is developed based on larger number of compounds in the dataset (446 vs. 142), although the same number of compounds (90 vs. 90) are employed in the external prediction set for two models.…”

“…Originally, SVM was developed for solving classification problems [26][27][28][29]. Recently, with the introduction of ε-insensitive loss function, it has been extended to solve regression problems, and has shown great performance in QSPR studies due to its ability to interpret the nonlinear relationships between molecular structure and properties [30][31][32][33]. Basic theories of SVM for regression, the task involved in this study, can be found in the tutorials for SVM [25].…”

Prediction of dissolved oxygen concentration in hypoxic river systems using support vector machine: a case study of Wen-Rui Tang River, China

“…The basic concept behind SVM is to map the original data sets to higher dimensional features of space and construct an optimal separating plane (SP), from which the distance to all the data points is minimal (Lin et al 2008;Pan et al 2008;Qu and Zuo 2010). Detailed expression of SVM has been extensively reported in numerous studies (Cristianine and Taylor 2000;Raghavendra and Deka, 2014;Vapnik 1998).…”

A novel QSPR model for prediction of lower flammability limits of organic compounds based on support vector machine

“…Originally, SVM was developed for classification problems, and has demonstrated a good performance in solving these problems by numerous successful applications [17][18][19][20][21][22]. In recent years, with the introduction of ε-insensitive loss function, SVM has also been extended to solve regression problems, and has shown great performance in QSPR studies due to its remarkable ability to interpret the nonlinear relationships between molecular structure and properties [23][24][25][26][27][28]. In the most of these cases, the performance of SVM modeling either matches or is significantly better than that of traditional machine learning approaches [25].…”