|
Discovering behavioural predispositions in data to improve human activity recognition
Popko, Maximilian
;
Bader, Sebastian
;
Lüdtke, Stefan
;
Kirste, Thomas
|
DOI:
|
https://doi.org/10.1145/3558884.3558892
|
|
URL:
|
https://dl.acm.org/doi/fullHtml/10.1145/3558884.35...
|
|
Additional URL:
|
https://www.researchgate.net/publication/362123432...
|
|
Document Type:
|
Conference or workshop publication
|
|
Year of publication:
|
2023
|
|
Book title:
|
iWOAR '22: Proceedings of the 7th International Workshop on Sensor-Based Activity Recognition and Artificial Intelligence : September 19-20, 2022, Rostock, Germany
|
|
Page range:
|
1-7
|
|
Conference title:
|
iWOAR 2022
|
|
Location of the conference venue:
|
Rostock, Germany
|
|
Date of the conference:
|
19.-20.09.2022
|
|
Publisher:
|
Aehnelt, Mario
;
Kirste, Thomas
|
|
Place of publication:
|
New York, NY, USA
|
|
Publishing house:
|
Association for Computing Machinery
|
|
ISBN:
|
978-1-4503-9624-0
|
|
Publication language:
|
English
|
|
Institution:
|
Außerfakultäre Einrichtungen > Institut für Enterprise Systems (InES)
|
|
Subject:
|
004 Computer science, internet
|
|
Individual keywords (German):
|
wearable sensors , clustering , human activity recognition, machine learning
|
|
Abstract:
|
The automatic, sensor-based assessment of challenging behavior of persons with dementia is an important task to support the selection of interventions. However, predicting behaviors like apathy and agitation is challenging due to the large inter- and intra-patient variability. Goal of this paper is to improve the recognition performance by making use of the observation that patients tend to show specific behaviors at certain times of the day or week. We propose to identify such segments of similar behavior via clustering the distributions of annotations of the time segments. All time segments within a cluster then consist of similar behaviors and thus indicate a behavioral predisposition (BPD). We utilize BPDs by training a classifier for each BPD. Empirically, we demonstrate that when the BPD per time segment is known, activity recognition performance can be substantially improved.
|
 | Dieser Eintrag ist Teil der Universitätsbibliographie. |
 Search Authors in
You have found an error? Please let us know about your desired correction here: E-Mail
Actions (login required)
 |
Show item |
|
|
