EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Counting Activities Using Weakly Labeled Raw Acceleration Data: A Variable-Length Sequence Approach with Deep Learning to Maintain Event Duration Flexibility

Georgios Sopidis, Michael Haslgrübler iD, Alois Ferscha

Sensors · 2023

DOI: 10.3390/s23115057 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, 2023. Verfasst von Georgios Sopidis und 2 weiteren Autor:innen. Beteiligte Einrichtung: Pro2Future GmbH, Altenberger Strasse 69, 4040 Linz, Austria. Hauptthemen laut MEDLINE: Neural Networks, Computer, Deep Learning. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Johannes Kepler Open Access Publishing Fund, federal state of Upper Austria.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This paper presents a novel approach for counting hand-performed activities using deep learning and inertial measurement units (IMUs). The particular challenge in this task is finding the correct window size for capturing activities with different durations. Traditionally, fixed window sizes have been used, which occasionally result in incorrectly represented activities. To address this limitation, we propose segmenting the time series data into variable-length sequences using ragged tensors to store and process the data. Additionally, our approach utilizes weakly labeled data to simplify the annotation process and reduce the time to prepare annotated data for machine learning algorithms. Thus, the model receives only partial information about the performed activity. Therefore, we propose an LSTM-based architecture, which takes into account both the ragged tensors and the weak labels. To the best of our knowledge, no prior studies attempted counting utilizing variable-size IMU acceleration data with relatively low computational requirements using the number of completed repetitions of hand-performed activities as a label. Hence, we present the data segmentation method we employed and the model architecture that we implemented to show the effectiveness of our approach. Our results are evaluated using the Skoda public dataset for Human activity recognition (HAR) and demonstrate a repetition error of ±1 even in the most challenging cases. The findings of this study have applications and can be beneficial for various fields, including healthcare, sports and fitness, human–computer interaction, robotics, and the manufacturing industry.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Neural Networks, ComputerDeep LearningHumansAlgorithmsMachine LearningAccelerationHuman Activities

Stichwörter der Autor:innen

artificial intelligencecountingdeep learningnon-uniform shape datavariable length sizeweakly labeled data

Autor:innen und Institutionen

  • Pro2Future GmbH, Altenberger Strasse 69, 4040 Linz, Austria.
  • Institute of Pervasive Computing, Johannes Kepler University, Altenberger Straße 69, 4040 Linz, Austria.

ORCID-Profile: Michael Haslgrübler

Förderung

  • Johannes Kepler Open Access Publishing Fund
  • federal state of Upper Austria

Zitieren

APA

Sopidis, G., Haslgrübler, M., & Ferscha, A. (2023). Counting Activities Using Weakly Labeled Raw Acceleration Data: A Variable-Length Sequence Approach with Deep Learning to Maintain Event Duration Flexibility. Sensors. https://doi.org/10.3390/s23115057

Vancouver

Sopidis G, Haslgrübler M, Ferscha A. Counting Activities Using Weakly Labeled Raw Acceleration Data: A Variable-Length Sequence Approach with Deep Learning to Maintain Event Duration Flexibility. Sensors. 2023. doi:10.3390/s23115057

BibTeX
@article{Sopidis2023,
  author = {Sopidis, Georgios and Haslgrübler, Michael and Ferscha, Alois},
  title = {Counting Activities Using Weakly Labeled Raw Acceleration Data: A Variable-Length Sequence Approach with Deep Learning to Maintain Event Duration Flexibility},
  journal = {Sensors},
  year = {2023},
  doi = {10.3390/s23115057}
}
Kostenlos starten →