Timeseries-aware Uncertainty Wrappers for Uncertainty Quantification of Information-Fusion-Enhanced AI Models based on Machine Learning
This work addresses the need for dependable uncertainty quantification in AI models for cyber-physical systems, though it appears incremental as it builds on existing information fusion techniques.
The paper tackled the problem of unreliable uncertainty estimates in AI models for safety-critical applications by introducing a timeseries-aware uncertainty wrapper combined with information fusion, demonstrating increased model accuracy and improved uncertainty quality in a traffic sign recognition use case.
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.