Oldest Adults Daily Living Activities Detection using Machine Learning

Abstract

This research focuses on accurately recognising and monitoring Activities of Daily Living (ADLs) among older adults, with a specific emphasis on individuals with dementia. The study aims to evaluate and compare different machine learning models to identify the most effective approach for ADL classification. Models such as Artificial Neural Network (ANN), Random Forest (RF), Decision Tree (DT), Multinomial NB, and Logisticn Regression (LR) was tested on a dataset containing ADL features. The results revealed that the RF and DT models achieved the highest accuracy of 95.61% in classifying ADLs. These models demonstrated their ability to capture complex patterns in ADL data, making them promising candidates for ADL recognition and monitoring, especially for older adults with dementia.