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 15, 2026

Design and Analysis for Fall Detection System Simplification

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

LiteFallNet: A lightweight deep learning model for efficient real-time fall detection.

Emmanuel Owusu^1,2, Isaac Acquah^1,2, Michael Asiedu Asare^1,2

¹Biomedical Engineering Program, Department of Computer Engineering, Kwame Nkrumah University of Science and Technology, Kumasi, Ghana.

|October 14, 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

Evaluation of medical device calibration knowledge, perceived importance, and implementation support among healthcare professionals in Ghana.

Health informatics journal·2026

Same author

Resilient Sinkhorn-Based Optimal Transport Late Fusion Framework for Breast Cancer Diagnosis.

Cancer informatics·2026

Same author

Confidence in Medical Device Calibration Knowledge and Skills Among Healthcare Professionals in Ghana: A Cross-Sectional Analysis.

Health services insights·2025

Same author

Rational design of alternative natural-based coupling media for diagnostic ultrasound imaging: a review.

Biomedical physics & engineering express·2025

Same author

A hybrid long short-term memory-convolutional neural network multi-stream deep learning model with Convolutional Block Attention Module incorporated for monkeypox detection.

Science progress·2025

LiteFallNet is a new deep learning model for accurate, real-time fall detection using inertial sensors. This lightweight, interpretable system prioritizes privacy and efficiency for various applications.

Area of Science:

Biomedical Engineering
Artificial Intelligence
Sensor Technology

Background:

Current fall detection systems often face challenges with high computational demands, latency, and privacy concerns.
There is a need for efficient, accurate, and interpretable fall detection models suitable for real-time applications.

Purpose of the Study:

To introduce LiteFallNet, a lightweight and interpretable deep learning model for real-time fall detection.
To address limitations of existing systems by focusing on computational efficiency and privacy preservation.

Main Methods:

LiteFallNet integrates GRU, TCN, depthwise separable convolutions, and SE blocks for temporal feature extraction from inertial sensor data.
The model utilizes tri-axial accelerometer, gyroscope, and magnetometer signals.

Keywords:

Fall detection deep learning lightweight model explainability privacy-preserving

Related Experiment Videos

Last Updated: Jan 15, 2026

Design and Analysis for Fall Detection System Simplification

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

Interpretability is achieved using 1D Grad-CAM and LIME.

Main Results:

Achieved high performance on the FallAllD dataset: 97.81% accuracy, 98.55% recall, 97.88% F1-score, and 99.33% AUC.
Demonstrated efficiency with a model size of 0.312 MB and inference time of 7.07 ms.
The model's performance is suitable for resource-constrained environments.

Conclusions:

LiteFallNet provides a privacy-preserving, real-time fall detection solution.
Its accuracy, transparency, and lightweight design are ideal for smart homes, eldercare, and wearable health technologies.