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

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

Identifying reactivation zones in the kotrupi landslide through UAV, satellite image and slope stability analysis.

Scientific reports·2026

Same author

In vitro and in silico studies provide evidence of competitive binding displacement of Agaricus bisporus laccase mediated by lignin-derived monomers.

Enzyme and microbial technology·2026

Same author

Quantifying Crop Health Through Soil Moisture and Soil Quality Dynamics.

Recent advances in food, nutrition & agriculture·2026

Same author

TTP protects against 6-OHDA-induced dopaminergic neurodegeneration via astrocytic Nrf2/HO-1 activation in cellular and rat models of Parkinson's disease.

Metabolic brain disease·2026

Same author

Subject-independent emotion recognition with EEG bispectral quadratic phase coupling features and explainable machine learning.

Biomedical physics & engineering express·2026

Same author

Mesenchymal Stem cell therapy with GHRH receptor analog resolves post-stroke vasogenic edema via modulating AQP4 and mitochondria-ER crosstalk.

Journal of translational medicine·2026

Search research articles

Related Experiment Video

Updated: May 15, 2025

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

Assessment of Driver Inattention State Using Multimodal Wearable Signals and Cross-Attention-Driven Hierarchical

Kaveti Pavan¹, Ankit Singh², Digvijay S Pawar²

¹Department of Biomedical Engineering, Indian institute of technology, Hyderabad, Telangana, India.

Studies in Health Technology and Informatics

|April 9, 2025

Summary

This study introduces a novel method using wearable sensors and a 1D Convolutional Neural Network (CNN) with Cross Hierarchical Attention Fusion to detect driver inattention. The approach effectively identifies inattentive driving states using physiological signals from smart shirts.

Keywords:

Cross Hierarchical Attention Fusion Driver Inattention Detection Driver well-being Multimodal Physiological Signals Road safety Wearable Smart Shirts

More Related Videos

A Methodology for Capturing Joint Visual Attention Using Mobile Eye-Trackers

A Methodology for Capturing Joint Visual Attention Using Mobile Eye-Trackers

Published on: January 18, 2020

Tactile Vibrating Toolkit and Driving Simulation Platform for Driving-Related Research

Tactile Vibrating Toolkit and Driving Simulation Platform for Driving-Related Research

Published on: December 18, 2020

Related Experiment Videos

Last Updated: May 15, 2025

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

A Methodology for Capturing Joint Visual Attention Using Mobile Eye-Trackers

A Methodology for Capturing Joint Visual Attention Using Mobile Eye-Trackers

Published on: January 18, 2020

Tactile Vibrating Toolkit and Driving Simulation Platform for Driving-Related Research

Tactile Vibrating Toolkit and Driving Simulation Platform for Driving-Related Research

Published on: December 18, 2020

Area of Science:

Biomedical Engineering
Transportation Safety
Machine Learning

Background:

Driver inattention poses significant risks to road safety and well-being.
Effective fusion of multimodal physiological signals for inattention detection remains a challenge, especially with intermediate fusion techniques.
Wearable sensors offer a non-intrusive method for continuous physiological monitoring during driving.

Purpose of the Study:

To develop and evaluate a novel approach for identifying driver inattention using multimodal physiological signals.
To address the challenges of data fusion in multimodal driver monitoring systems.
To assess the efficacy of a 1D CNN with Cross Hierarchical Attention Fusion for classifying driver inattention states.

Main Methods:

Acquisition of electrocardiogram (ECG) and respiration (RESP) signals from 10 subjects using textile electrodes during normal and calling driving scenarios.
Preprocessing and hierarchical fusion of multimodal physiological data.
Application of a 1D Convolutional Neural Network (CNN) with Cross Hierarchical Attention Fusion for inattention classification.
Validation using Leave-One-Subject-Out Cross-Validation (LOSOCV).

Main Results:

The proposed Cross Hierarchical Attention Fusion approach successfully classified driver inattention states.
Shorter data segments demonstrated higher classification accuracy compared to longer segments.
Multimodal physiological data acquired via textile electrodes effectively discriminated between different driver inattention states.
The system demonstrated non-intrusive monitoring capabilities in real-world driving scenarios.

Conclusions:

The developed method utilizing a 1D CNN with Cross Hierarchical Attention Fusion is effective for identifying driver inattention.
Wearable smart shirts with textile electrodes provide a viable platform for non-intrusive, real-time driver monitoring.
Optimizing data segment length is crucial for maximizing classification accuracy in driver inattention detection.