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

Multifunctional Microgels: From Material Design to Skin Wound Healing Applications.

Small (Weinheim an der Bergstrasse, Germany)·2026
Same author

Immune-pathological response induced by Saprolegnia parasitica in Pangasianodon hypophthalmus and assessment of clinical efficacy of clotrimazole.

Brazilian journal of microbiology : [publication of the Brazilian Society for Microbiology]·2026
Same author

Composite Liquid Marble Templated Millimetric Capsule With Tunable Rigidity, Porosity, and Thermal Reconfigurability Toward 3D Cell Culture.

Advanced materials (Deerfield Beach, Fla.)·2026
Same author

Peripheral arterial disease classification using machine learning and multi-point photoplethysmography.

Computers in biology and medicine·2026
Same author

Multi-level biomarker responses to potentially toxic elements (PTEs) contamination in a coastal bivalve from the Maharashtra coast, India.

Marine pollution bulletin·2026
Same author

From Physical to Digital: Hoarding Phenomena in Obsessive-Compulsive Disorder.

The primary care companion for CNS disorders·2026

Related Experiment Video

Updated: Sep 18, 2025

A Vibrotactile Feedback Device for Seated Balance Assessment and Training
09:13

A Vibrotactile Feedback Device for Seated Balance Assessment and Training

Published on: January 20, 2019

6.5K

Smart seat cushion mobile application with on-device posture prediction using TensorFlow lite.

Saurav Kumar1, Pranav Kashyap Gujja1, Snehith Kongara1

  • 1University of Texas at Arlington Research Institute, Arlington, TX, USA.

Disability and Rehabilitation. Assistive Technology
|June 21, 2025
PubMed
Summary

This study developed a smart seat cushion system with an Android app and machine learning to help wheelchair users prevent pressure injuries. The system provides real-time feedback and posture monitoring to improve adherence to pressure redistribution guidelines.

Keywords:
Smart seat cushionmobile applicationposture predictionpressure injurieswheelchair users

More Related Videos

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

1.6K
A Human-machine-interface Integrating Low-cost Sensors with a Neuromuscular Electrical Stimulation System for Post-stroke Balance Rehabilitation
11:06

A Human-machine-interface Integrating Low-cost Sensors with a Neuromuscular Electrical Stimulation System for Post-stroke Balance Rehabilitation

Published on: April 12, 2016

10.5K

Related Experiment Videos

Last Updated: Sep 18, 2025

A Vibrotactile Feedback Device for Seated Balance Assessment and Training
09:13

A Vibrotactile Feedback Device for Seated Balance Assessment and Training

Published on: January 20, 2019

6.5K
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

1.6K
A Human-machine-interface Integrating Low-cost Sensors with a Neuromuscular Electrical Stimulation System for Post-stroke Balance Rehabilitation
11:06

A Human-machine-interface Integrating Low-cost Sensors with a Neuromuscular Electrical Stimulation System for Post-stroke Balance Rehabilitation

Published on: April 12, 2016

10.5K

Area of Science:

  • Biomedical Engineering
  • Rehabilitation Technology
  • Machine Learning in Healthcare

Background:

  • Pressure injuries (PI) are a significant risk for individuals with spinal cord injuries (SCI).
  • Low adherence to clinical guidelines for periodic pressure redistribution (PR) is a major challenge in PI prevention.
  • Existing monitoring systems lack real-time feedback, hindering consistent PR practice.

Purpose of the Study:

  • To develop and evaluate a smart seat cushion (SSC) system with an integrated Android application for real-time monitoring and feedback.
  • To enhance adherence to pressure redistribution protocols for wheelchair users.
  • To leverage machine learning for accurate posture prediction and user behavior analysis.

Main Methods:

  • Collected seating posture data from 12 healthy participants across nine postures.
  • Trained and compared five deep learning architectures (MLP, CNN, LSTM, CNN-LSTM, Multi-Headed Attention) for posture prediction.
  • Developed an Android application using Flutter and integrated the best-performing LSTM model (92% accuracy) via TensorFlow Lite for on-device deployment.

Main Results:

  • The LSTM model achieved 92% accuracy in posture prediction, outperforming other deep learning architectures.
  • The Android application successfully controlled the SSC wirelessly, identified seating postures, visualized pressure maps, and generated user statistics.
  • The system provided real-time feedback and guidance, addressing low adherence to weight shift protocols.

Conclusions:

  • The developed SSC system with an AI-powered Android application offers a viable solution for improving adherence to PR protocols.
  • Real-time monitoring, posture prediction, and user feedback are crucial for effective pressure injury prevention in wheelchair users.
  • This innovation represents a significant advancement in PI prevention and supports user compliance with clinical guidelines.