AUTHOR=Javed Abdul Rehman , Khan Habib Ullah , Alomari Mohammad Kamel Bader , Sarwar Muhammad Usman , Asim Muhammad , Almadhor Ahmad S. , Khan Muhammad Zahid 

TITLE=Toward explainable AI-empowered cognitive health assessment

JOURNAL=Frontiers in Public Health

VOLUME=11

YEAR=2023

URL=https://www.frontiersin.org/journals/public-health/articles/10.3389/fpubh.2023.1024195

DOI=10.3389/fpubh.2023.1024195

ISSN=2296-2565

ABSTRACT=<p>Explainable artificial intelligence (XAI) is of paramount importance to various domains, including healthcare, fitness, skill assessment, and personal assistants, to understand and explain the decision-making process of the artificial intelligence (AI) model. Smart homes embedded with smart devices and sensors enabled many context-aware applications to recognize physical activities. This study presents <italic>XAI-HAR</italic>, a novel XAI-empowered human activity recognition (HAR) approach based on key features identified from the data collected from sensors located at different places in a smart home. <italic>XAI-HAR</italic> identifies a set of new features (i.e., the total number of sensors used in a specific activity), as <italic>physical key features selection (PKFS)</italic> based on weighting criteria. Next, it presents <italic>statistical key features selection (SKFS)</italic> (i.e., mean, standard deviation) to handle the outliers and higher class variance. The proposed <italic>XAI-HAR</italic> is evaluated using machine learning models, namely, random forest (RF), K-nearest neighbor (KNN), support vector machine (SVM), decision tree (DT), naive Bayes (NB) and deep learning models such as deep neural network (DNN), convolution neural network (CNN), and CNN-based long short-term memory (CNN-LSTM). Experiments demonstrate the superior performance of <italic>XAI-HAR</italic> using RF classifier over all other machine learning and deep learning models. For explainability, <italic>XAI-HAR</italic> uses Local Interpretable Model Agnostic (LIME) with an RF classifier. <italic>XAI-HAR</italic> achieves 0.96% of F-score for health and dementia classification and 0.95 and 0.97% for activity recognition of dementia and healthy individuals, respectively.</p>