Quantifying Uncertainty in Machine Learning-Based Pervasive Systems: Application to Human Activity Recognition

TL;DR

This paper addresses the challenge of quantifying uncertainty in machine learning systems, particularly in human activity recognition, to improve reliability and assist domain experts in real-world applications.

Contribution

It proposes a set of techniques to evaluate model prediction relevance at runtime and demonstrates their effectiveness in human activity recognition systems.

Findings

Techniques effectively quantify uncertainty in HAR models

Assists domain experts in interpreting model predictions

Improves reliability of ML-based pervasive systems

Abstract

The recent convergence of pervasive computing and machine learning has given rise to numerous services, impacting almost all areas of economic and social activity. However, the use of AI techniques precludes certain standard software development practices, which emphasize rigorous testing to ensure the elimination of all bugs and adherence to well-defined specifications. ML models are trained on numerous high-dimensional examples rather than being manually coded. Consequently, the boundaries of their operating range are uncertain, and they cannot guarantee absolute error-free performance. In this paper, we propose to quantify uncertainty in ML-based systems. To achieve this, we propose to adapt and jointly utilize a set of selected techniques to evaluate the relevance of model predictions at runtime. We apply and evaluate these proposals in the highly heterogeneous and evolving domain of Human Activity Recognition (HAR). The results presented demonstrate the relevance of the approach, and we discuss in detail the assistance provided to domain experts.