Please use this identifier to cite or link to this item: http://hdl.handle.net/2440/128516
Citations
Scopus Web of Science® Altmetric
?
?
Type: Conference paper
Title: Linear support vector machine to classify the vibrational modes for complex chemical systems
Author: Le, H.T.
Tran, T.T.
Lam, K.H.
Citation: Proceedings of the 2nd International Conference on Machine Learning and Soft Computing (ICMLSC 2018), 2018 / pp.10-14
Publisher: Association for Computing Machinery
Publisher Place: New York
Issue Date: 2018
ISBN: 9781450363365
Conference Name: 2nd International Conference on Machine Learning and Soft Computing (ICMLSC) (02 Feb 2018 - 04 Feb 2018 : Phu Quoc Island, Vietnam)
Statement of
Responsibility: 
Triet Huynh Minh Le, Tung Thanh Tran, Lam Kim Huynh
Abstract: Classification of vibrational modes into hindered internal rotation (HIR) and harmonic oscillation modes is important to obtain correct thermodynamic data for a chemical species for a wide range of temperatures. In this study, we propose a multivariate linear support vector machine (SVM) model to solve this challenging binary classification problem. The results of the proposed model were found to be similar to those of logistic regression and 2-5% better than those of the rule-based method. Moreover, the number of features found by linear SVM was also fewer than that of logistic regression (five versus six), which makes it easier to be interpreted by chemists. The detailed explanation of such differences is also presented. The three models were implemented in the GUI of the Multi-Species Multi-Channel Software Suite (Duong et al., Int. J. Chem. Kinet, 2015, 564) to facilitate the determination of HIR modes as well as the calculation of thermodynamic properties for a chemical species of interest.
Keywords: Machine learning; Data mining; Classification; Multivariate linear support vector machine; Hindered internal rotation
Rights: © 2018 Copyright is held by the owner/author(s). Publication rights licensed to ACM.
RMID: 1000014911
DOI: 10.1145/3184066.3184087
Published version: https://dl.acm.org/doi/proceedings/10.1145/3184066
Appears in Collections:Computer Science publications

Files in This Item:
There are no files associated with this item.


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.