Discovering Behavioral Predispositions in Data to Improve Human Activity Recognition
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2022
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911983051210752 |
|---|---|
| author | Popko, Maximilian Bader, Sebastian Lüdtke, Stefan Kirste, Thomas |
| author_facet | Popko, Maximilian Bader, Sebastian Lüdtke, Stefan Kirste, Thomas |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2207_08816 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | Discovering Behavioral Predispositions in Data to Improve Human Activity Recognition Popko, Maximilian Bader, Sebastian Lüdtke, Stefan Kirste, Thomas Machine Learning Artificial Intelligence 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. |
| title | Discovering Behavioral Predispositions in Data to Improve Human Activity Recognition |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2207.08816 |