Jove
Visualize
Contact Us

Related Experiment Video

Updated: Jan 11, 2026

Design and Analysis for Fall Detection System Simplification
08:05

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

11.1K

Optimized fall detection using hybrid BiLSTM BiGRU additive attention model and BAOA driven feature selection system.

Mithun Singh Ahirwar1, Vaibhav Soni2

  • 1Department of Computer Science and Engineering, Maulana Azad National Institute of Technology Bhopal, Bhopal, 462003, Madhya Pradesh, India. mithunvns@gmail.com.

Scientific Reports
|November 10, 2025
PubMed
Summary

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

Biomarkers.

Alzheimer's & dementia : the journal of the Alzheimer's Associationยท2025
See all related articles
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

This study introduces a novel fall detection system using a hybrid deep learning model (BiLSTM-BiGRU) with attention and optimized feature selection. The system achieves high accuracy, offering a reliable solution for elderly fall prevention.

Area of Science:

  • Biomedical Engineering
  • Artificial Intelligence

Background:

  • The aging population is growing, increasing the incidence of fall-related injuries among the elderly.
  • Accurate and reliable fall detection systems are essential for timely intervention and care.
  • Existing deep learning methods for fall detection face challenges in capturing complex temporal data.

Purpose of the Study:

  • To propose a novel fall detection method combining Bidirectional Long Short-Term Memory (BiLSTM) and Bidirectional Gated Recurrent Unit (BiGRU) networks.
  • To enhance the hybrid model with an additive attention mechanism and optimized feature selection using the Binary Arithmetic Optimization Algorithm (BAOA).
  • To evaluate the proposed model's effectiveness on multiple wearable sensor datasets for real-time fall detection.

Main Methods:

Keywords:
BAOABiGRUBiLSTMDeep learningFall detectionWearable sensors

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

5.2K

Related Experiment Videos

Last Updated: Jan 11, 2026

Design and Analysis for Fall Detection System Simplification
08:05

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

11.1K
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

5.2K
  • Utilized a hybrid deep learning architecture: Bidirectional Long Short-Term Memory (BiLSTM) and Bidirectional Gated Recurrent Unit (BiGRU).
  • Incorporated an additive attention mechanism to focus on relevant temporal features.
  • Employed the Binary Arithmetic Optimization Algorithm (BAOA) for optimized feature selection.
  • Evaluated the model on SisFall, UMAFall, and UP-Fall datasets using wearable sensors.

    • Main Results:

    • The proposed hybrid BiLSTM-BiGRU-Additive Attention Model with BAOA Driven Feature Selection achieved high accuracies.
    • Achieved 99.50% accuracy on the SisFall dataset.
    • Achieved 99.85% accuracy on the UMAFall dataset.
    • Achieved 99.68% accuracy on the UP-Fall dataset.
    • Demonstrated superior performance compared to traditional deep learning architectures and non-optimized models.

    Conclusions:

    • The developed fall detection system significantly outperforms existing methods.
    • The hybrid model effectively captures temporal dependencies crucial for accurate fall detection.
    • The proposed system is suitable for real-time fall detection applications, enhancing elderly safety.