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

Passive Diffusion: Overview and Kinetics

Passive Diffusion: Overview and Kinetics

Passive diffusion is a critical process that allows small lipophilic drugs to cross the cell membrane along a concentration gradient. This mechanism's efficiency depends on four primary factors: the membrane's surface area, the drug's lipid-water partition coefficient, the concentration gradient, and the membrane's thickness.
When administered orally, drugs establish a substantial concentration gradient between the gastrointestinal (GI) lumen and the bloodstream, expediting...

You might also read

Related Articles

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

Sort by

Same author

A Behavioral and fNIRS Comparative Study of Gender and Task Differences in Mental Rotation Among Primary Students.

Brain and behavior·2025

Same author

Word concreteness modulates bilingual language control during reading comprehension.

Journal of experimental psychology. Learning, memory, and cognition·2024

Same author

Effect of short-term intensive design-based STEM learning on executive function: an fNIRS study of the left-behind children.

Cerebral cortex (New York, N.Y. : 1991)·2024

Same author

The Effects of Digital Addiction on Brain Function and Structure of Children and Adolescents: A Scoping Review.

Healthcare (Basel, Switzerland)·2024

Same author

Self-Supervised Spatiotemporal Clustering of Vehicle Emissions With Graph Convolutional Network.

IEEE transactions on neural networks and learning systems·2023

Same author

Effect of Etoricoxib on miR-214 and inflammatory reaction in knee osteoarthritis patients.

American journal of translational research·2021

Search research articles

Related Experiment Video

Updated: May 24, 2025

Trajectory Data Analyses for Pedestrian Space-time Activity Study

Trajectory Data Analyses for Pedestrian Space-time Activity Study

Published on: February 25, 2013

Spatiotemporal Imputation of Traffic Emissions With Self-Supervised Diffusion Model.

Lihong Pei, Yang Cao, Yu Kang

IEEE Transactions on Neural Networks and Learning Systems

|March 3, 2025

Summary

Traffic emission data often has missing blocks, impacting models. A new diffusion model framework (STI-dm) improves imputation for these complex, incomplete datasets, outperforming existing methods.

More Related Videos

Single-Molecule Tracking Microscopy - A Tool for Determining the Diffusive States of Cytosolic Molecules

Single-Molecule Tracking Microscopy - A Tool for Determining the Diffusive States of Cytosolic Molecules

Published on: September 5, 2019

An Inverse Analysis Approach to the Characterization of Chemical Transport in Paints

An Inverse Analysis Approach to the Characterization of Chemical Transport in Paints

Published on: August 29, 2014

Related Experiment Videos

Last Updated: May 24, 2025

Trajectory Data Analyses for Pedestrian Space-time Activity Study

Trajectory Data Analyses for Pedestrian Space-time Activity Study

Published on: February 25, 2013

Single-Molecule Tracking Microscopy - A Tool for Determining the Diffusive States of Cytosolic Molecules

Single-Molecule Tracking Microscopy - A Tool for Determining the Diffusive States of Cytosolic Molecules

Published on: September 5, 2019

An Inverse Analysis Approach to the Characterization of Chemical Transport in Paints

An Inverse Analysis Approach to the Characterization of Chemical Transport in Paints

Published on: August 29, 2014

Area of Science:

Environmental Science
Data Science
Traffic Engineering

Background:

Traffic emission monitoring faces challenges with missing not-at-random (MNAR) data, particularly long-term block missing in road segments due to sparse monitoring.
This missing data disrupts spatiotemporal correlations, leading to significant biases in incomplete data modeling.
Existing diffusion models struggle with the dynamics and spatiotemporal heterogeneity of traffic emissions in unknown missing scenarios.

Purpose of the Study:

To propose a novel progressive Diffusion Model-based framework for SpatioTemporal Imputation of traffic emissions (STI-dm).
To address biases and improve the accuracy of traffic emission modeling with MNAR data.
To enhance the applicability of diffusion models for complex spatiotemporal missing data patterns.

Main Methods:

Developed a self-supervised masked training strategy to establish nonlocal similarity priors for traffic emission data.
Incorporated the MNAR missing mechanism directly into the diffusion process.
Employed an enhanced noise injection and supervised denoising approach to correct nonlocal alignment misconceptions and reduce modeling biases.
Implemented a progressive imputation and prior modeling process for stable, mutually beneficial results.

Main Results:

The proposed STI-dm framework effectively handles intricate spatiotemporal patterns and varying missing data rates.
STI-dm demonstrates superior performance compared to current state-of-the-art algorithms in traffic emission imputation.
The progressive approach ensures stable results and enhances the accuracy of the imputation process.

Conclusions:

STI-dm offers a robust solution for spatiotemporal imputation of traffic emissions, particularly under MNAR conditions.
The framework significantly reduces modeling biases associated with incomplete traffic emission data.
This work advances the application of diffusion models in environmental data science for improved traffic emission analysis.