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

Force Classification

Force Classification

Forces play a crucial role in the study of physics and engineering. They are essential in describing the motion, behavior, and equilibrium of objects in the physical world. Forces can be classified based on their origin, type, and direction of action.
Contact and non-contact forces are two of the most widely used categories of forces. As the name suggests, contact forces require physical contact between two objects to act upon each other. Examples of contact forces include frictional,...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Robust data-driven feedback linearization using neural network based sparse identification of nonlinear dynamics.

ISA transactions·2026

Same author

Efficient compression of encoder-decoder models for semantic segmentation using the separation index.

Scientific reports·2025

Same author

Comparative analysis of sandstone microtomographic image segmentation using advanced convolutional neural networks with pixelwise and physical accuracy evaluation.

Scientific reports·2025

Same author

Design of thin, wideband electromagnetic absorbers with polarization and angle insensitivity using deep learning.

Scientific reports·2025

Same author

A geometric approach for accelerating neural networks designed for classification problems.

Scientific reports·2024

Same author

Forward layer-wise learning of convolutional neural networks through separation index maximizing.

Scientific reports·2024

Search research articles

Related Experiment Video

Updated: Aug 12, 2025

One Dimensional Turing-Like Handshake Test for Motor Intelligence

One Dimensional Turing-Like Handshake Test for Motor Intelligence

Published on: December 15, 2010

A hand rubbing classification model based on image sequence enhanced by feature-based confidence metric.

Mohammad Amin Haghpanah¹, Mehdi Tale Masouleh¹, Ahmad Kalhor¹

¹Tehran, Iran Human and Robot Interaction Laboratory, School of Electrical and Computer Engineering, University of Tehran.

Signal, Image and Video Processing

|January 30, 2023

Summary

This study introduces a new computer vision sequence model for evaluating hand hygiene compliance with World Health Organization (WHO) guidelines. The model achieves 98.99% accuracy, outperforming baseline methods and highlighting the need for advanced metrics beyond simple accuracy.

Keywords:

Computer vision Deep learning Feature-based confidence Hand hygiene Image sequence Infection Machine learning Transfer learning

More Related Videos

Experimental Assessment of Mouse Sociability Using an Automated Image Processing Approach

Experimental Assessment of Mouse Sociability Using an Automated Image Processing Approach

Published on: May 15, 2016

Estimation of Contact Regions Between Hands and Objects During Human Multi-Digit Grasping

Estimation of Contact Regions Between Hands and Objects During Human Multi-Digit Grasping

Published on: April 21, 2023

Related Experiment Videos

Last Updated: Aug 12, 2025

One Dimensional Turing-Like Handshake Test for Motor Intelligence

One Dimensional Turing-Like Handshake Test for Motor Intelligence

Published on: December 15, 2010

Experimental Assessment of Mouse Sociability Using an Automated Image Processing Approach

Experimental Assessment of Mouse Sociability Using an Automated Image Processing Approach

Published on: May 15, 2016

Estimation of Contact Regions Between Hands and Objects During Human Multi-Digit Grasping

Estimation of Contact Regions Between Hands and Objects During Human Multi-Digit Grasping

Published on: April 21, 2023

Area of Science:

Computer Vision
Machine Learning
Public Health

Background:

Hand hygiene is crucial for preventing disease transmission, notably during the COVID-19 pandemic.
The World Health Organization (WHO) established a 12-step guideline for effective hand rubbing.
Current computer vision methods for assessing hand hygiene compliance primarily use single images, limiting temporal analysis.

Purpose of the Study:

To develop and evaluate a novel sequence model for assessing hand hygiene compliance using consecutive images.
To improve upon existing computer vision-based hand hygiene monitoring systems.
To introduce and utilize a Feature-Based Confidence Metric for more robust model comparison and hyperparameter optimization.

Main Methods:

A sequence model integrating Inception-ResNet for spatial feature extraction and Long Short-Term Memory (LSTM) for time-series analysis was proposed.
The model was trained on a comprehensive dataset of hand hygiene procedures.
Model performance was evaluated using accuracy and a novel Feature-Based Confidence Metric.

Main Results:

The proposed sequence model achieved a high accuracy of 98.99% on the test set.
Compared to baseline models, the sequence model demonstrated approximately 1% higher accuracy and 4% higher confidence.
The inference time for the sequence model was found to be three times slower than baseline models.

Conclusions:

The sequence model offers a more accurate and confident assessment of hand hygiene compliance compared to single-image baseline models.
The Feature-Based Confidence Metric provides a more nuanced evaluation than accuracy alone, aiding in model selection and optimization.
While computationally more intensive, the sequence model's enhanced performance justifies its use for critical applications like public health monitoring.