Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Jan 17, 2026

Design and Analysis for Fall Detection System Simplification

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

Real-time activity and fall detection using transformer-based deep learning models for elderly care applications.

Raja Omman Zafar¹, Farhan Zafar²

¹Dalarna University-Campus Borlange, Borlänge, Sweden roz@du.se.

BMJ Health & Care Informatics

|September 18, 2025

Summary

This summary is machine-generated.

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

Ex Vivo Hydrodynamic Assessment of Expanded Polytetrafluoroethylene Trileaflet Pulmonary Valves.

ASAIO journal (American Society for Artificial Internal Organs : 1992)·2025

Same author

Stabilizing the Unstable: An Analysis of The Society of Thoracic Surgeons Congenital Heart Surgery Database of Children Supported With Extracorporeal Membrane Oxygenation Before Cardiac Surgery.

The Annals of thoracic surgery·2025

Same author

Machine Learning Driven Synthesis of Cobalt Oxide Entrapped Heteroatom-Doped Graphitic Carbon Nitride for Enhanced Oxygen Evolution Reaction.

PloS one·2025

Same author

Machine-Learning-Assisted Synthesis of Bimetallic Metal-Organic Frameworks for the Optimized Oxygen Evolution Reaction.

ACS applied materials & interfaces·2025

Same author

Clinical Outcomes With Normothermic Pulsatile Organ Perfusion in Heart Transplantation: A Report From the OCS Heart Perfusion Registry.

Circulation·2025

Same author

Letter in reference to "Association of Procurement Technique with Organ Yield and Cost Following Donation After Circulatory Death".

American journal of transplantation : official journal of the American Society of Transplantation and the American Society of Transplant Surgeons·2025

Same journal

Ambient AI in primary care: an exploratory mixed methods survey of UK general practitioners.

BMJ health & care informatics·2026

Same journal

Clarifying the relationship between biomedical and health informatics and digital health: expert perspectives.

BMJ health & care informatics·2026

Same journal

Measuring performance trajectories in lung cancer surgery: a longitudinal study using the French national hospital database from 2020 to 2024.

BMJ health & care informatics·2026

Same journal

Mapping of mental health indicators in the WHO European region: a scoping review.

BMJ health & care informatics·2026

Same journal

Automated monitoring in clinical and operational workflows.

BMJ health & care informatics·2026

Same journal

Characterising 'Watch and Wait' prescribing patterns in paediatric otitis media using large language models and pharmacy dispense data.

BMJ health & care informatics·2026

See all related articles

A new transformer-based deep learning model achieves over 98% accuracy in real-time activity recognition and fall detection. This advanced system outperforms traditional models, offering improved reliability for elderly care and fall prevention applications.

Area of Science:

Artificial Intelligence
Biomedical Engineering
Computer Science

Background:

Existing activity recognition and fall detection methods struggle with accuracy and real-time performance.
Wearable sensor data analysis is crucial for monitoring daily living activities and detecting falls.

Purpose of the Study:

To develop a transformer-based deep learning model for accurate and real-time activity recognition and fall detection.
To address the limitations of current systems in terms of accuracy and real-time applicability.

Main Methods:

Utilized a transformer encoder with a self-attention mechanism to process wearable sensor data (accelerometer, gyroscope, orientation) via sliding window segmentation.
Trained and evaluated the model on the extensive MobiAct dataset, comprising over 14 million records from 66 participants across 16 activities, including various fall types.

Keywords:

Artificial intelligence BMJ Health Informatics Data Science Deep Learning Delivery of Health Care

More Related Videos

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

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

Published on: December 15, 2023

Related Experiment Videos

Last Updated: Jan 17, 2026

Design and Analysis for Fall Detection System Simplification

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

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

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

Published on: December 15, 2023

Main Results:

Achieved over 98% accuracy, with excellent precision and recall for complex fall categories like forward-lying and sideward-lying.
Demonstrated superior performance compared to Convolutional Neural Networks-Long Short-Term Memory (CNN-LSTM) and Temporal Convolutional Networks across classification metrics and training stability.

Conclusions:

Transformer models effectively capture complex temporal dependencies, mitigating misclassification and false positives in activity recognition and fall detection.
The developed transformer-based system offers efficient real-time deployment and reliable solutions for elderly care and fall prevention.