Explainable Deep Learning Framework for Human Activity Recognition

TL;DR

This paper introduces a model-agnostic, data augmentation-based framework that improves the interpretability of human activity recognition models, making explanations more accessible and efficient without sacrificing accuracy.

Contribution

It presents a novel, model-agnostic interpretability framework for HAR that uses competitive data augmentation to generate intuitive explanations efficiently.

Findings

Enhanced interpretability of HAR models.

No significant performance loss.

Faster explanation generation (under 20 seconds).

Abstract

In the realm of human activity recognition (HAR), the integration of explainable Artificial Intelligence (XAI) emerges as a critical necessity to elucidate the decision-making processes of complex models, fostering transparency and trust. Traditional explanatory methods like Class Activation Mapping (CAM) and attention mechanisms, although effective in highlighting regions vital for decisions in various contexts, prove inadequate for HAR. This inadequacy stems from the inherently abstract nature of HAR data, rendering these explanations obscure. In contrast, state-of-th-art post-hoc interpretation techniques for time series can explain the model from other perspectives. However, this requires extra effort. It usually takes 10 to 20 seconds to generate an explanation. To overcome these challenges, we proposes a novel, model-agnostic framework that enhances both the interpretability and efficacy of HAR models through the strategic use of competitive data augmentation. This innovative approach does not rely on any particular model architecture, thereby broadening its applicability across various HAR models. By implementing competitive data augmentation, our framework provides intuitive and accessible explanations of model decisions, thereby significantly advancing the interpretability of HAR systems without compromising on performance.