A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
A novel projection twin support vector machine for pattern recognition
A novel projection twin support vector machine (PTSVM), termed as NPTSVM, is presented in this paper for binary classification. Although this method determines two projection vectors using the same way as PTSVM, it has more advantages than existing PTSVMs. First, NPTSVM does not have to calculate inverse matrices during the learning process, which makes the training speed of NPTSVM be much faster than existing PTSVMs. Second, NPTSVM transforms nonlinear optimization problems to linear ones using kernel trick akin to the traditional SVM instead of the empirical kernel applied in existing PTSVMs. In addition, it maps the distance between the class center and each sample from the same class, not the sample itself like existing PTSVMs, into a nonlinear kernel space, which reduces the computational complexity to a certain extent while maintains the classification capability. Experimental results validate the efficacy and feasibility of our method.
A novel projection twin support vector machine for pattern recognition
A novel projection twin support vector machine (PTSVM), termed as NPTSVM, is presented in this paper for binary classification. Although this method determines two projection vectors using the same way as PTSVM, it has more advantages than existing PTSVMs. First, NPTSVM does not have to calculate inverse matrices during the learning process, which makes the training speed of NPTSVM be much faster than existing PTSVMs. Second, NPTSVM transforms nonlinear optimization problems to linear ones using kernel trick akin to the traditional SVM instead of the empirical kernel applied in existing PTSVMs. In addition, it maps the distance between the class center and each sample from the same class, not the sample itself like existing PTSVMs, into a nonlinear kernel space, which reduces the computational complexity to a certain extent while maintains the classification capability. Experimental results validate the efficacy and feasibility of our method.
A novel projection twin support vector machine for pattern recognition
Hua, Xiaopeng (author) / Xu, Sen (author) / Gao, Jun (author)
2017-09-01
219215 byte
Conference paper
Electronic Resource
English
Embedded Speech Recognition Based on Multiclass Support Vector Machine
| British Library Online Contents | 2011
Implementation of digital twin and support vector machine in structural health monitoring of bridges
| DOAJ | 2023
A Robust Fuzzy Support Vector Machine for Two-class Pattern Classification
| British Library Online Contents | 2006