Output details
11 - Computer Science and Informatics
Brunel University London
Extending twin support vector machine classifier for multi-category classification problems
<28> Solving a multi-category data classification problem is challenging and this paper proposes a one-versus-all twin support vector machine classifier that achieves this with high accuracy. The complex problem was transformed into simpler quadratic programming ones, saving considerable computational time. Both theoretical analysis of the approach and extensive experimental results on many datasets show that the classifier is efficient and consistently outperforms traditional approaches. The work is part of a long-term international collaboration between British and Chinese researchers in data science.