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

Social marginalization risk and its negative association with socialising preferences in Japanese gamers.

PloS one·2026
Same author

HybridSphere: Enhancing Hybrid Meetings with Avatar-Based VR Environments.

IEEE transactions on visualization and computer graphics·2026
Same author

Mask Balancing: Perception-Driven Dynamic Visibility Enhancement for Occlusion-Capable Optical See-Through Head-Mounted Displays.

IEEE transactions on visualization and computer graphics·2026
Same author

Tag-Along Virtual Windows Increase Perceived Resistance and Task Load in Augmented Reality.

IEEE transactions on visualization and computer graphics·2026
Same author

Electrooculography-Based Detection of Refractive Vision Problems.

IEEE journal of biomedical and health informatics·2026
Same author

Visual and Somatosensory Integration With Higher Sitting Posture Enhances the Sense of Standing and Self-Motion in Seated VR.

IEEE transactions on visualization and computer graphics·2025

Related Experiment Video

Updated: Jan 19, 2026

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

5.3K

Recurrent Neural Network for Inertial Gait User Recognition in Smartphones.

Pablo Fernandez-Lopez1, Judith Liu-Jimenez2, Kiyoshi Kiyokawa3

  • 1University Group for ID Technologies (GUTI), University Carlos III of Madrid (UC3M), Av. de la Universidad 30, 28911 Leganes, Madrid, Spain. pablofer@ing.uc3m.es.

Sensors (Basel, Switzerland)
|September 25, 2019
PubMed
Summary

This study introduces a smartphone-based gait recognition algorithm using inertial sensors and Recurrent Neural Networks (RNNs). The optimized algorithm achieves high accuracy, outperforming existing methods for user identification.

Keywords:
Recurrent Neural Networkbiometricsgait recognitionpattern recognitionsmartphone

More Related Videos

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

9.3K
Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding
11:25

Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding

Published on: July 26, 2013

44.0K

Related Experiment Videos

Last Updated: Jan 19, 2026

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

5.3K
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

9.3K
Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding
11:25

Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding

Published on: July 26, 2013

44.0K

Area of Science:

  • Biometrics
  • Computer Science
  • Signal Processing

Background:

  • Gait recognition is a biometric technique for identifying individuals based on their walking patterns.
  • Inertial sensors in smartphones offer a convenient platform for unobtrusive gait analysis.
  • Developing accurate and efficient gait recognition algorithms is crucial for security and personalized applications.

Purpose of the Study:

  • To develop and optimize a novel gait recognition algorithm using smartphone inertial sensor data.
  • To evaluate the algorithm's performance against state-of-the-art methods using a public dataset.
  • To investigate the impact of training data size on algorithm accuracy.

Main Methods:

  • Utilized accelerometers and gyroscopes from smartphones to capture gait signals.
  • Extracted gait cycles and processed them using a Recurrent Neural Network (RNN).
  • Employed random grid hyperparameter search and manual tuning for optimization.

Main Results:

  • Achieved an Equal Error Rate (EER) of 11.48% with 20% user training data.
  • Reduced EER to 7.55% when training with 70% of users.
  • Demonstrated superior performance compared to existing gait recognition algorithms on a public database.

Conclusions:

  • The proposed smartphone-based gait recognition algorithm shows significant potential and outperforms current state-of-the-art methods.
  • Algorithm performance is highly dependent on the quantity of training data, with more user visits leading to substantial improvements.
  • Further enhancements are expected with larger datasets featuring multiple visits per user.