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 Experiment Video

Updated: Jul 8, 2025

Design and Analysis for Fall Detection System Simplification
08:05

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

10.7K

Deep transfer learning-based anomaly detection for cycling safety.

Shumayla Yaqoob1, Salvatore Cafiso2, Giacomo Morabito1

  • 1Department of Electrical, Electronic, Computer and Telecommunication Engineering, University of Catania, Italy.

Journal of Safety Research
|December 11, 2023
PubMed
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

Non-invasive assistive framework for sign language recognition using software-defined radio sensing and deep learning.

Disability and rehabilitation. Assistive technology·2026
Same author

Real-World Application of Non-Destructive Pavement Health Monitoring Sensors.

Sensors (Basel, Switzerland)·2026
Same author

Multi-filter stacking in inception V3 for enhanced Alzheimer's severity classification.

Neuroscience·2025
Same author

AI-Driven Adaptive Communications for Energy-Efficient Underwater Acoustic Sensor Networks.

Sensors (Basel, Switzerland)·2025
Same author

Transferability of safety inspection procedures for network-wide safety assessment of two-lane rural roads - an Italian-Hungarian experiment.

Traffic injury prevention·2025
Same author

Synthetic molecular communication through microfluidic oscillating droplets for intrabody physiological data transmission.

Lab on a chip·2025

This study introduces DTL AD, a deep transfer learning model for identifying unsafe cycling behavior and high-risk areas. It uses Global Navigation Satellite System (GNSS) data to proactively prevent bicycle crashes.

Area of Science:

  • Transportation Safety
  • Data Science
  • Machine Learning

Background:

  • Cycling fatalities are increasing in EU cities, highlighting a critical road safety challenge.
  • Traditional crash statistics are reactive and limited by data availability for effective bicycle safety analysis.
  • Smart city data collection offers proactive solutions for identifying and mitigating cycling hazards.

Purpose of the Study:

  • To develop a proactive approach for identifying critical locations for bicycle safety interventions.
  • To detect anomalies in cycling behavior indicative of potential traffic conflicts or near-miss incidents.
  • To leverage advanced machine learning for enhanced road safety analysis.

Main Methods:

  • Applied a deep transfer learning model, specifically a convolutional autoencoder (CAE), for anomaly detection.
Keywords:
Anomaly detectionDeep transfer learningRoad safety

More Related Videos

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

558
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

3.8K

Related Experiment Videos

Last Updated: Jul 8, 2025

Design and Analysis for Fall Detection System Simplification
08:05

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

10.7K
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

558
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

3.8K
  • Utilized Global Navigation Satellite System (GNSS) data recorded in National Marine Electronics Association (NMEA) strings from instrumented bicycles.
  • Developed a user-tailored riding model named DTL AD.

    • Main Results:

    • The DTL AD model successfully detects and localizes riding anomalies using GNSS data.
    • Transfer learning with CAE reduced the effort required for data labeling and model training.
    • Anomaly detection effectively identified high-risk areas when visualized on Geographic Information Systems (GIS) maps.

    Conclusions:

    • The DTL AD model offers a proactive and effective method for improving cycling safety.
    • Anomaly detection in cycling behavior can be accurately mapped to identify hazardous locations.
    • This approach enhances road transport safety by enabling targeted interventions.