Recognition of Usual Similar Activities of Dementia Patients via Smartwatches Using Supervised Learning
Sergio Staab, Johannes Luderschmidt, Ludger Martin · 2021
Currently, about 46.8 million people worldwide have dementia. More than 7.7 million new cases occur every year. Causes and triggers of the disease are currently unknown and a cure is not available. This makes dementia, along with cancer, one of the most dangerous diseases in the world. In the field of dementia care, this work attempts to use machine learning to classify the activities of individuals with dementia in order to track and analyze disease progression and detect disease-related changes as early as possible. In collaboration with two care communities, exercise data is measured using the Apple Watch Series 6. Consultation with several care teams that work with dementia patients on a daily basis revealed that many dementia patients wear watches.In this project, data from the aforementioned sensors is sent to the database at 20 data packets per second via a socket. DecisionTreeClassifier, KNeighborsClassifier, Logistic Regression, Fast Forest, Support Vector Machine, and Multilayer Perceptron classification algorithms are used to gain knowledge about locating, providing, and documenting motor skills during the course of dementia. The performance of the aforementioned algorithms for three similar activities of the dementia patients – writing, drinking and eating – will be investigated. The aim is to show the performance with which the activities can be recognized and how this knowledge can be used to support dementia documentation by nursing staff.