Efficient and decision boundary aware instance selection for support vector machines

• Support vector machines (SVMs) are powerful classifiers that have high computational complexity in the training phase, which can limit their applicability to large datasets. An effective approach to address this limitation is to select a small subset of the most representative training samples such that desirable results can be obtained. In this study, a novel instance selection method called border point extraction based on locality-sensitive hashing (BPLSH) is designed. BPLSH preserves instances that are near the decision boundaries and eliminates nonessential ones. The performance of BPLSH is benchmarked against four approaches on different classification problems. The experimental results indicate that BPLSH outperforms the other methods in terms of classification accuracy, preservation rate, and execution time. The source code of BPLSH can be found in https://github.com/mohaslani/BPLSH. 

Ämnesord

NATURVETENSKAP  -- Data- och informationsvetenskap -- Datavetenskap (hsv//swe)

NATURAL SCIENCES  -- Computer and Information Sciences -- Computer Sciences (hsv//eng)

Nyckelord

Big data

Data reduction

Instance selection

Machine learning

Support vector machines

Classification (of information)

Large dataset

% reductions

Border points extraction

Decision boundary

Effective approaches

Large datasets

Locality sensitive hashing

Machine-learning

Support vectors machine

Training phasis

Datoriserad bildbehandling

Computerized Image Processing

Publikations- och innehållstyp

ref (ämneskategori)

art (ämneskategori)