Exploratory Analysis of Machine Learning Methods for the Prognosis of Falls in Elderly Care Based on Accelerometer Data
L. Klein, C. Ostrau, M. Thies, W. Schenck, U. Rückert, in: D. Salvi, P. Van Gorp, S.A. Shah (Eds.), Pervasive Computing Technologies for Healthcare. 17th EAI International Conference, PervasiveHealth 2023, Malmö, Sweden, November 27-29, 2023, Proceedings, Springer Nature Switzerland, Cham, 2024, pp. 423–437.
Download
Es wurde kein Volltext hochgeladen. Nur Publikationsnachweis!
Konferenzbeitrag
| Veröffentlicht
| Englisch
Autor*in
Herausgeber*in
Salvi, Dario;
Van Gorp, Pieter;
Shah, Syed Ahmar
Abstract
This paper investigates the feasibility of employing machine learning techniques to categorize individuals into fall-risk and non-fall-risk groups based solely on accelerometer data. The research utilizes a publicly available movement monitoring dataset, containing accelerometer data from a diverse group of individuals. The study pursues three primary objectives. First, it develops a preprocessing pipeline to prepare raw accelerometer data, which includes noise reduction, data cleaning, and identification of walking segments and the extraction of over twenty gait-related features. The second objective is to systematically explore the influence of these features on machine learning model performance. Gait stability-related parameters, known from medical literature, are of particular interest. To fulfil this objective, different machine learning algorithms are evaluated using an automated exploration framework. The third objective centres on finding a balanced combination of features and lightweight machine learning models suitable for embedded systems, which typically have limited computational resources. The emphasis here is on computational efficiency, an original aspect of this study. The results indicate that gradient boosting algorithms, such as XGBoost, LightGBM, and CatBoost, outperform other models, achieving promising performance results, including an area under the curve (AUC) score of up to 0.949.
Erscheinungsjahr
Titel des Konferenzbandes
Pervasive Computing Technologies for Healthcare. 17th EAI International Conference, PervasiveHealth 2023, Malmö, Sweden, November 27-29, 2023, Proceedings
Seite
423-437
Konferenz
17th EAI International Conference, PervasiveHealth
Konferenzort
Malmö, Schweden
Konferenzdatum
2023-11-27 – 2023-11-29
ISBN
ISSN
eISSN
FH-PUB-ID
Zitieren
Klein, Lukas ; Ostrau, Christoph ; Thies, Michael ; Schenck, Wolfram ; Rückert, Ulrich: Exploratory Analysis of Machine Learning Methods for the Prognosis of Falls in Elderly Care Based on Accelerometer Data. In: Salvi, D. ; Van Gorp, P. ; Shah, S. A. (Hrsg.): Pervasive Computing Technologies for Healthcare. 17th EAI International Conference, PervasiveHealth 2023, Malmö, Sweden, November 27-29, 2023, Proceedings, Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering. Cham : Springer Nature Switzerland, 2024, S. 423–437
Klein L, Ostrau C, Thies M, Schenck W, Rückert U. Exploratory Analysis of Machine Learning Methods for the Prognosis of Falls in Elderly Care Based on Accelerometer Data. In: Salvi D, Van Gorp P, Shah SA, eds. Pervasive Computing Technologies for Healthcare. 17th EAI International Conference, PervasiveHealth 2023, Malmö, Sweden, November 27-29, 2023, Proceedings. Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering. Cham: Springer Nature Switzerland; 2024:423-437. doi:10.1007/978-3-031-59717-6_27
Klein, L., Ostrau, C., Thies, M., Schenck, W., & Rückert, U. (2024). Exploratory Analysis of Machine Learning Methods for the Prognosis of Falls in Elderly Care Based on Accelerometer Data. In D. Salvi, P. Van Gorp, & S. A. Shah (Eds.), Pervasive Computing Technologies for Healthcare. 17th EAI International Conference, PervasiveHealth 2023, Malmö, Sweden, November 27-29, 2023, Proceedings (pp. 423–437). Cham: Springer Nature Switzerland. https://doi.org/10.1007/978-3-031-59717-6_27
@inproceedings{Klein_Ostrau_Thies_Schenck_Rückert_2024, place={Cham}, series={Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering}, title={Exploratory Analysis of Machine Learning Methods for the Prognosis of Falls in Elderly Care Based on Accelerometer Data}, DOI={10.1007/978-3-031-59717-6_27}, booktitle={Pervasive Computing Technologies for Healthcare. 17th EAI International Conference, PervasiveHealth 2023, Malmö, Sweden, November 27-29, 2023, Proceedings}, publisher={Springer Nature Switzerland}, author={Klein, Lukas and Ostrau, Christoph and Thies, Michael and Schenck, Wolfram and Rückert, Ulrich}, editor={Salvi, Dario and Van Gorp, Pieter and Shah, Syed AhmarEditors}, year={2024}, pages={423–437}, collection={Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering} }
Klein, Lukas, Christoph Ostrau, Michael Thies, Wolfram Schenck, and Ulrich Rückert. “Exploratory Analysis of Machine Learning Methods for the Prognosis of Falls in Elderly Care Based on Accelerometer Data.” In Pervasive Computing Technologies for Healthcare. 17th EAI International Conference, PervasiveHealth 2023, Malmö, Sweden, November 27-29, 2023, Proceedings, edited by Dario Salvi, Pieter Van Gorp, and Syed Ahmar Shah, 423–37. Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering. Cham: Springer Nature Switzerland, 2024. https://doi.org/10.1007/978-3-031-59717-6_27.
L. Klein, C. Ostrau, M. Thies, W. Schenck, and U. Rückert, “Exploratory Analysis of Machine Learning Methods for the Prognosis of Falls in Elderly Care Based on Accelerometer Data,” in Pervasive Computing Technologies for Healthcare. 17th EAI International Conference, PervasiveHealth 2023, Malmö, Sweden, November 27-29, 2023, Proceedings, Malmö, Schweden, 2024, pp. 423–437.
Klein, Lukas, et al. “Exploratory Analysis of Machine Learning Methods for the Prognosis of Falls in Elderly Care Based on Accelerometer Data.” Pervasive Computing Technologies for Healthcare. 17th EAI International Conference, PervasiveHealth 2023, Malmö, Sweden, November 27-29, 2023, Proceedings, edited by Dario Salvi et al., Springer Nature Switzerland, 2024, pp. 423–37, doi:10.1007/978-3-031-59717-6_27.