Trustworthy insights: A novel multi-tier explainable framework for ambient assisted living

Integrating transparency, interpretability, and accountability into the design of Artificial Intelligence (AI) tools for Ambient Assisted Living (AAL) enhances user trust and acceptance. Clear explanations of the AI system's operations and decision-making process are vital, enabling users to comprehend the factors influencing predictions and recommendations. This paper introduces a novel explainable framework tailored for AAL, representing a structured approach to comprehensively understand feature importance in the decision-making process of machine learning models. The framework adopts a hierarchical approach, commencing with an overview of feature importance for the entire AAL system (Tier 0) and subsequently organising explanations into smaller subsets (Tiers 1, 2 and 3) based on user-defined measures, such as accuracy, activity types in AAL, and specific time periods. By facilitating metadata exploration and offering in-depth insights, the proposed framework augments model interpretability and user trust, ultimately empowering informed decision-making within AAL contexts.