EUVIMEDOpdag EUVIMED
Open access · CC BY 4.0

Effects of Sampling Frequency on Human Activity Recognition with Machine Learning Aiming at Clinical Applications

Takahiro Yamane iD, Moeka Kimura, Mizuki Morita iD

Sensors · 2025

DOI: 10.3390/s25123780 ↗

At a glance

Journal article in Sensors, 2025. Written by Takahiro Yamane and 2 co-authors. Institution: Department of Biomedical Informatics, Graduate School of Interdisciplinary Science and Engineering in Health Systems, Okayama University, Okayama 700…. Major MEDLINE topics: Machine Learning, Accelerometry, Human Activities. Cited 13 times so far (Crossref); 43 references. The full text is freely available (open access, CC BY 4.0). Funded by: JSPS, Japan Society for the Promotion of Science (JSPS) KAKENHI.

AbstractSubjectsBibliografiske oplysningerCiteRelated studies

Abstract (original language)

Human activity recognition using wearable accelerometer data can be a useful digital biomarker for severity assessment and the diagnosis of diseases, where the relationship between onset and patient activity is crucial. For long-term monitoring in clinical settings, the volume of data collected over time should be minimized to reduce power consumption, computational load, and communication volume. This study aimed to determine the lowest sampling frequency that maintains recognition accuracy for each activity. Thirty healthy participants wore nine-axis accelerometer sensors at five body locations and performed nine activities. Machine-learning-based activity recognition was conducted using data sampled at 100, 50, 25, 20, 10, and 1 Hz. Data from the non-dominant wrist and chest, which have previously shown high recognition accuracy, were used. Reducing the sampling frequency to 10 Hz did not significantly affect the recognition accuracy for either location. However, lowering the frequency to 1 Hz decreases the accuracy of many activities, particularly brushing teeth. Using data with a 10 Hz sampling frequency can maintain recognition accuracy while decreasing data volume, enabling long-term patient monitoring and device miniaturization for clinical applications.

Subjects

MeSH terms (MEDLINE)

Machine LearningAccelerometryHuman ActivitiesHumansMaleFemaleAdultWearable Electronic DevicesMonitoring, Physiologic

Author keywords

digital biomarkersdigital healthhuman activity recognitionmachine learningsampling frequencywearable devices

Authors and institutions

  • Department of Biomedical Informatics, Graduate School of Interdisciplinary Science and Engineering in Health Systems, Okayama University, Okayama 700-8530, Japan.
  • Faculty of Health Sciences, Okayama University Medical School, Okayama 700-8558, Japan.

ORCID profiles: Takahiro Yamane, Mizuki Morita

Funding

  • JSPS
  • Japan Society for the Promotion of Science (JSPS) KAKENHI

Cite

APA

Yamane, T., Kimura, M., & Morita, M. (2025). Effects of Sampling Frequency on Human Activity Recognition with Machine Learning Aiming at Clinical Applications. Sensors. https://doi.org/10.3390/s25123780

Vancouver

Yamane T, Kimura M, Morita M. Effects of Sampling Frequency on Human Activity Recognition with Machine Learning Aiming at Clinical Applications. Sensors. 2025. doi:10.3390/s25123780

BibTeX
@article{Yamane2025,
  author = {Yamane, Takahiro and Kimura, Moeka and Morita, Mizuki},
  title = {Effects of Sampling Frequency on Human Activity Recognition with Machine Learning Aiming at Clinical Applications},
  journal = {Sensors},
  year = {2025},
  doi = {10.3390/s25123780}
}
Start for free →