An Improved Expression for Information Quality of Basic Probability
Assignment and Its Application in Fault Diagnosis
- Hanwen Li ,
- Rui Cai
Abstract
Information quality is widely used in many applications. However, how to
measure information quality in basic probability assignment accurately
is still an open issue. Generalized expression for information quality
is an effective method to measure information quality in basic
probability assignment. Nevertheless, the counter-intuitive results may
be obtained when statements are of intersection. To address this issue,
a new expression for information quality of basic probability assignment
is proposed in this paper considering the frame of discernment and the
influence of intersection among statements which can cause changes of
uncertainty. Numerical examples are illustrated to demonstrate the
effectiveness of the proposed method. In addition, an application in
fault diagnosis is used to show the effectiveness of the proposed
method.