Innovative Decision and Forecasting Approach on Navigation Risk

Bo Li,Xiaohui Li,Huawei Yi,Haonan Tian

doi:10.1109/access.2020.3016720

Bo Li, Xiaohui Li + Show 2 more

Open Access

https://doi.org/10.1109/access.2020.3016720

Copy DOI

Abstract

In view to the unstable navigation risk assessment and make the future navigation risk forecasting, an innovative decision and forecasting approach is put forward in this study. Different from the existing literature, at the current time step, we first deduce an enhanced evidence combination rule to integrate uncertain and conflicting evidences by using weighted basic probabilistic assignment and matrix operation. As a result, a stable decision is effectively achieved no matter what characteristics of the available evidences are. Further, an improved α-β filter is designed with its adaptive coefficients in the novel filtering framework in order to forecast the future navigation risk. What's more, it is an excellent communication between the combined basic probabilistic assignment and the improved α-β filter for the first time. After the deep analysis of the computational complexity, a plenty of numeric simulations and actual experiments are provided to indicate the reliability and efficiency of the proposed approach.

Highlights

Modern transportation has an important role in the advances of global trade and natural resources recently
We select a typical set of raw basic probabilistic assignment (BPA) in order to analyze the decision performance
The primary challenges are to deal with the unstable performance of the existing methods on the navigation risk assessment

Summary

Introduction

Modern transportation has an important role in the advances of global trade and natural resources recently. Proceeding from the existing assessment methods of navigation risk, we can find that the analytic hierarchy process (AHP) is an important multi-evidence decisionmaking method [5,6,7,8]. In the field, [9] presented a ship integrated navigation system based on AHP in order to assess navigation risk. An improved D-S evidence theory on safety risk perception was proposed in [17], where the combination rule and weighted rule were utilized to synthesize multi-evidence. Concerning on the waterways risk, a navigation assessment model based on D-S evidence theory was proposed in [18], which utilized the evidential reasoning and index level to merge BPA. By merging some interval-valued fuzzy sets, the D-S evidence theory provides the systematic

Methods

Results

Conclusion