A new approach to construct basic probability assignment and its applications in data classification

Authors

  • M. Kaur Jaypee Institute of Information Technology, Noida (Uttar Pradesh), India
  • A. Srivastava Jaypee Institute of Information Technology, Noida (Uttar Pradesh), India

DOI:

https://doi.org/10.31926/but.mif.2025.5.67.1.19

Keywords:

Classification, Belief function, Dempster-Shafer (D-S) evidence theory, BPA generation

Abstract

In the present work, we have proposed a classification algorithm that uses Dempster Shafer (D-S) evidence theory since it has emerged as an effective tool in handling data classification problems. As basic probability assignment (BPA) is a pre-requisite for applying D-S theory, how to generate it is a hot issue. This paper proposes a novel method for generating basic probability assignments (BPAs) from training data. Dempster Shafer’s (D-S) rule of Combination is utilized for the unification of these BPAs and finally, classify each data item using these unified BPAs. Testing is carried out using some popular benchmark data sets consisting of three classes. Evaluated results show that the classification accuracy is comparatively high.

Author Biographies

M. Kaur, Jaypee Institute of Information Technology, Noida (Uttar Pradesh), India

Department of Mathematics

A. Srivastava, Jaypee Institute of Information Technology, Noida (Uttar Pradesh), India

Department of Mathematics

Downloads

Published

2025-01-14

Issue

Section

COMPUTER SCIENCE