Accountable, Explainable Artificial Intelligence Incorporation Framework for a Real-Time Affective State Assessment Module

The rapid growth of artificial intelligence (AI) and machine learning (ML) solutions has seen it adopted across various industries. However, the concern of ‘black-box’ approaches has led to an increase in the demand for high accuracy, transparency, accountability, and explainability in AI/ML approac...

Full description

Bibliographic Details
Main Author: Vice, Jordan Joshua
Format: Thesis
Published: Curtin University 2022
Online Access:http://hdl.handle.net/20.500.11937/90847
Description
Summary:The rapid growth of artificial intelligence (AI) and machine learning (ML) solutions has seen it adopted across various industries. However, the concern of ‘black-box’ approaches has led to an increase in the demand for high accuracy, transparency, accountability, and explainability in AI/ML approaches. This work contributes through an accountable, explainable AI (AXAI) framework for delineating and assessing AI systems. This framework has been incorporated into the development of a real-time, multimodal affective state assessment system.