EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Experimental Study of Long Short-Term Memory and Transformer Models for Fall Detection on Smartwatches

Syed Tousiful Haque, Minakshi Debnath iD, Awatif Yasmin iD, Tarek Mahmud iD, Anne Hee Hiong Ngu

Sensors · 26.09.2024 · 24 (19) · 6235

DOI: 10.3390/s24196235 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 26.09.2024. Verfasst von Syed Tousiful Haque und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science, Texas State University, San Marcos, TX 78666, USA. Hauptthemen laut MEDLINE: Accidental Falls. Die Arbeit wurde bisher 20-mal zitiert (Crossref) und nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Science Foundation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Falls are the second leading cause of unintentional injury deaths worldwide. While numerous wearable fall detection devices incorporating AI models have been developed, none of them are used successfully in a fall detection application running on commodity-based smartwatches in real time. The system misses some falls, and generates an annoying amount of False Positives for practical use. We have investigated and experimented with an LSTM model for fall detection on a smartwatch. Even though the LSTM model has high accuracy during offline testing, the good performance of offline LSTM models cannot be translated to the equivalence of real-time performance. Transformers, on the other hand, can learn long-sequence data and patterns intrinsic to the data due to their self-attention mechanism. This paper compares three variants of LSTM and two variants of Transformer models for learning fall patterns. We trained all models using fall and activity data from three datasets, and the real-time testing of the model was performed using the SmartFall App. Our findings showed that in the offline training, the CNN-LSTM model was better than the Transformer model for all the datasets. However, the Transformer is a preferable choice for deployment in real-time fall detection applications.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Accidental FallsHumansWearable Electronic DevicesNeural Networks, ComputerAlgorithms

Stichwörter der Autor:innen

LSTMdeep learningfall detectiontransformerswearables

Autor:innen und Institutionen

  • Department of Computer Science, Texas State University, San Marcos, TX 78666, USA.

ORCID-Profile: Minakshi Debnath, Awatif Yasmin, Tarek Mahmud

Förderung

  • National Science Foundation

Zitieren

APA

Haque, S. T., Debnath, M., Yasmin, A., Mahmud, T., & Ngu, A. H. H. (2024). Experimental Study of Long Short-Term Memory and Transformer Models for Fall Detection on Smartwatches. Sensors, 24(19), 6235. https://doi.org/10.3390/s24196235

Vancouver

Haque ST, Debnath M, Yasmin A, Mahmud T, Ngu AHH. Experimental Study of Long Short-Term Memory and Transformer Models for Fall Detection on Smartwatches. Sensors. 2024;24(19):6235. doi:10.3390/s24196235

BibTeX
@article{Haque2024,
  author = {Haque, Syed Tousiful and Debnath, Minakshi and Yasmin, Awatif and Mahmud, Tarek and Ngu, Anne Hee Hiong},
  title = {Experimental Study of Long Short-Term Memory and Transformer Models for Fall Detection on Smartwatches},
  journal = {Sensors},
  year = {2024},
  volume = {24},
  number = {19},
  pages = {6235},
  doi = {10.3390/s24196235}
}
Kostenlos starten →