Abstract
Wandering is considered to be one of the most common behavioral symptoms of dementia. Designing robust models which are capable of detecting wandering episodes in people living with dementia would allow the prevention of the consequences of this behavior. To tackle this problem, this study proposes a framework where the skeletal trajectories are used to extract patterns from the movements of the participants. These patterns are utilized to classify a movement between wandering and non-wandering behavior using three machine learning methods. The proposed models were assessed based on two datasets collected in different environments consisting of trajectories that are associated with lapping, pacing, and random movements that represent wandering episodes. The predictive model based on the LSTM network achieved the best classification results in terms of macro F1-scores on both datasets with an overall accuracy higher than 70%. The findings of this study present the potential of LSTM-based predictive models in addressing the wandering recognition problem in a real-world scenario with patients suffering from dementia.
Original language | English |
---|---|
Title of host publication | PETRA 2021: The 14th PErvasive Technologies Related to Assistive Environments Conference |
Publisher | Association for Computing Machinery |
Pages | 446-452 |
Number of pages | 7 |
ISBN (Electronic) | 978-1-4503-8792-7 |
DOIs | |
Publication status | Published - 29 Jun 2021 |
Event | The 14th ACM International Conference on PErvasive Technologies Related to Assistive Environments - Virtual Conference (University of Texas at Arlington, Texas, USA Duration: 29 Jun 2021 → 1 Jul 2021 https://dl.acm.org/action/showFmPdf?doi=10.1145%2F3453892 |
Conference
Conference | The 14th ACM International Conference on PErvasive Technologies Related to Assistive Environments |
---|---|
Abbreviated title | PETRA 2021 |
Period | 29/06/21 → 1/07/21 |
Internet address |