Timeseries-aware Uncertainty Wrappers for Uncertainty Quantification of Information-Fusion-Enhanced AI Models based on Machine Learning
Preprint
Abstract
As the use of Artificial Intelligence (AI) components in cyber-physical systems is becoming more common, the need for reliable system architectures arises. While data-driven models excel at perception tasks, model outcomes are usually not dependable enough for safety-critical applications. In this work,we present a timeseries-aware uncertainty wrapper for dependable uncertainty estimates on timeseries data. The uncertainty wrapper is applied in combination with information fusion over successive model predictions in time. The application of the uncertainty wrapper is demonstrated with a traffic sign recognition use case. We show that it is possible to increase model accuracy through information fusion and additionally increase the quality of uncertainty estimates through timeseries-aware input quality features.Keywords
All Related Versions
This publication has 19 references indexed in Scilit:
- Architectural Patterns for Handling Runtime Uncertainty of Data-Driven Models in Safety-Critical Perception2022
- Towards a Common Testing Terminology for Software Engineering and Data Science Experts2021
- Could We Relieve AI/ML Models of the Responsibility of Providing Dependable Uncertainty Estimates? A Study on Outside-Model Uncertainty Estimates2021
- Testing machine learning based systems: a systematic mappingEmpirical Software Engineering, 2020
- A Framework for Building Uncertainty Wrappers for AI/ML-Based Data-Driven Components2020
- A Systematic Approach to Analyzing Perception Architectures in Autonomous Vehicles2020
- Neural Simplex Architecture2020
- State-of-the-art in artificial neural network applications: A surveyHeliyon, 2018
- Uncertainty in Machine Learning Applications: A Practice-Driven Classification of Uncertainty2018
- Experiments with Classifier Combining Rules2000