Robust classification with belief functions and deep learning applied to STM
Sánchez, Luis and Rodríguez-Fernández, Victor and Vasile, Massimiliano; (2024) Robust classification with belief functions and deep learning applied to STM. In: 2024 IEEE Congress on Evolutionary Computation, CEC 2024 - Proceedings. IEEE, Piscataway, NJ. ISBN 9798350308365 (https://doi.org/10.1109/cec60901.2024.10612011)
Preview |
Text.
Filename: Sanchez-etal-IEEE-CEC-2024-Robust-classification-with-belief-functions-and-deep-learning.pdf
Accepted Author Manuscript License: Download (2MB)| Preview |
Abstract
This work proposes an approach to robust con-junction risk assessment given a sequence of Conjunction Data Messages (CDM). Dempster-Shafer theory of evidence (DSt) is used to account for epistemic uncertainty in the sequence of CDMs and derive a robust classification of conjunction events. We then use Artificial Intelligence (AI) to bypass the computationally expensive parts of DSt and directly produce a robust classification from a given sequence of CDMs. Five AI techniques are proposed: Random Forest (RF) with DSt structures, RF with CDMs, Light Gradient Boosting machine (LGBm) with CDMs, autoregressive LGBm (aLGBm), and Transformers for time series. These meth-ods were trained and tested both on synthetic and in real datasets to study their applicability to real scenarios. The results show the potential of AI techniques, especially LGBm, for robustly classifying encounters from the sequence of CDMs, provided balanced datasets are available.
ORCID iDs
Sánchez, Luis, Rodríguez-Fernández, Victor and Vasile, Massimiliano ORCID: https://orcid.org/0000-0001-8302-6465;-
-
Item type: Book Section ID code: 90331 Dates: DateEvent8 August 2024Published15 March 2024AcceptedSubjects: Science > Mathematics > Electronic computers. Computer science Department: Strategic Research Themes > Ocean, Air and Space
Faculty of Engineering > Mechanical and Aerospace EngineeringDepositing user: Pure Administrator Date deposited: 23 Aug 2024 12:16 Last modified: 01 Oct 2024 15:04 Related URLs: URI: https://strathprints.strath.ac.uk/id/eprint/90331