Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Non-invasive detection of Oncostatin M and TNF-α in a microphysiological chip with embedded pH tuning capabilities.

The Analyst·2026
Same author

SPME-based investigation of thapsigargin-induced alterations in the volatilome of human melanoma cells.

Analytical and bioanalytical chemistry·2026
Same author

Muscle Fatigue Assessment in Healthcare Application by Using Surface Electromyography: A Transfer Learning Approach.

Sensors (Basel, Switzerland)·2026
Same author

Innovative active carbon fibers-based multipurpose thermal desorption tubes for the analysis of volatile organic compounds.

Journal of chromatography. A·2025
Same author

Radar-Based Activity Recognition in Strictly Privacy-Sensitive Settings Through Deep Feature Learning.

Biomimetics (Basel, Switzerland)·2025
Same author

A Systematic Review of Surface Electromyography in Sarcopenia: Muscles Involved, Signal Processing Techniques, Significant Features, and Artificial Intelligence Approaches.

Sensors (Basel, Switzerland)·2025

Related Experiment Video

Updated: Aug 13, 2025

Evaluation of a Smartphone-based Human Activity Recognition System in a Daily Living Environment
06:49

Evaluation of a Smartphone-based Human Activity Recognition System in a Daily Living Environment

Published on: December 11, 2015

9.0K

Human Postures Recognition by Accelerometer Sensor and ML Architecture Integrated in Embedded Platforms: Benchmarking

Alessandro Leone1, Gabriele Rescio1, Andrea Caroppo1

  • 1National Research Council of Italy, Institute for Microelectronics and Microsystems, 73100 Lecce, Italy.

Sensors (Basel, Switzerland)
|January 21, 2023
PubMed
Summary

A new system uses a tri-axial accelerometer and optimized Machine Learning to recognize elderly posture in real-time. This portable, low-power solution achieves 98% accuracy, improving well-being monitoring for seniors.

Keywords:
ageing adultsembedded platformmachine learningposture classificationwearable sensor

More Related Videos

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

4.0K
Quantified Assessment of Infant's Gross Motor Abilities Using a Multisensor Wearable
09:24

Quantified Assessment of Infant's Gross Motor Abilities Using a Multisensor Wearable

Published on: May 17, 2024

1.5K

Related Experiment Videos

Last Updated: Aug 13, 2025

Evaluation of a Smartphone-based Human Activity Recognition System in a Daily Living Environment
06:49

Evaluation of a Smartphone-based Human Activity Recognition System in a Daily Living Environment

Published on: December 11, 2015

9.0K
Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

4.0K
Quantified Assessment of Infant's Gross Motor Abilities Using a Multisensor Wearable
09:24

Quantified Assessment of Infant's Gross Motor Abilities Using a Multisensor Wearable

Published on: May 17, 2024

1.5K

Area of Science:

  • Biomedical Engineering
  • Computer Science
  • Gerontology

Background:

  • Wearable embedded systems are crucial for monitoring the health of aging populations.
  • Existing systems often rely on power-intensive, non-portable personal computers.
  • There is a need for efficient, portable hardware-software platforms for elderly health monitoring.

Purpose of the Study:

  • To develop a portable, energy-efficient system for real-time postural recognition in the elderly.
  • To overcome the limitations of high-resource computing systems for health monitoring.
  • To detect potentially inappropriate behavioral habits in older adults.

Main Methods:

  • Developed an automatic tri-axial accelerometer-based system for postural recognition.
  • Created and optimized a real-time posture recognition Machine Learning algorithm for low-power embedded platforms.
  • Integrated and tested the software on low-cost embedded platforms (Raspberry Pi 4, Odroid N2+).
  • Experimented with pre-trained Machine Learning classifiers using data from seven elderly users.

Main Results:

  • Achieved approximately 98% accuracy in classifying four postures: Standing, Sitting, Bending, and Lying down.
  • Demonstrated comparable accuracy to state-of-the-art classifiers running on personal computers.
  • Showcased a significantly lower computational load on embedded platforms.

Conclusions:

  • The developed system offers a viable, low-cost, and energy-efficient solution for real-time elderly posture recognition.
  • This technology can enhance the usability and deployment of wearable health monitoring devices for seniors.
  • The optimized Machine Learning algorithm performs effectively on resource-constrained embedded hardware.