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

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving

Mechanistic models play a crucial role in algorithms for numerical problem-solving, particularly in nonlinear mixed effects modeling (NMEM). These models aim to minimize specific objective functions by evaluating various parameter estimates, leading to the development of systematic algorithms. In some cases, linearization techniques approximate the model using linear equations.
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...

You might also read

Related Articles

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

Sort by

Same author

Asymmetric Zn─N<sub>2</sub>O-Coordinated Hydrogen-Bonded Organic Frameworks for Electrochemical Hydrogen Peroxide Production and Wastewater Purification.

Angewandte Chemie (International ed. in English)·2026

Same author

Atrophy of specific amygdala subregion precedes the conversion from mild cognitive impairment with neuropsychiatric symptoms to dementia.

International psychogeriatrics·2026

Same author

Creation and Verification of a Machine Learning-Based Model for Predicting Breast Cancer Risk in Patients with BI-RADS 4 Breast Lesions.

Current medical imaging·2026

Same author

Simulation of homogeneous electrochemical proton-coupled electron transfer using the hybrid-bath hierarchical equations of motion.

The Journal of chemical physics·2026

Same author

Synergistic effects of Ultrasound-Assisted Ultra-High pressure on quality attributes and flavor profile of lactic acid Bacteria-Fermented fresh jujube juice.

Ultrasonics sonochemistry·2026

Same author

Solution-Processed Organic UV-Sensitive Neuromorphic Sensors for Healthy Protection Application.

ACS applied materials & interfaces·2026

Same journal

Design Principles for Fluid Molecular Ferroelectrics.

Advanced materials (Deerfield Beach, Fla.)·2026

Same journal

Generating Unconventional Spin-Orbit Torques With Patterned Phase Gradients in Tungsten Thin Films.

Advanced materials (Deerfield Beach, Fla.)·2026

Same journal

An In Situ H<sub>2</sub>S-Activated Plasmonic Nanozyme for Near-Infrared II Photo-Thermoelectric Catalytic Therapy.

Advanced materials (Deerfield Beach, Fla.)·2026

Same journal

A Recyclable and Sustainable Hydroxypropyl Methylcellulose Electrolyte for Electrochromic Devices.

Advanced materials (Deerfield Beach, Fla.)·2026

Same journal

Perovskite Heterostructures for Optoelectronic Applications.

Advanced materials (Deerfield Beach, Fla.)·2026

Same journal

Light-Written Nonvolatile Polarization via Defect-Engineered Charge Trapping.

Advanced materials (Deerfield Beach, Fla.)·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Jun 25, 2025

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

Large-Language-Model-Based AI Agent for Organic Semiconductor Device Research.

Qian Zhang^1,2, Yongxu Hu¹, Jiaxin Yan^1,2

¹Key Laboratory of Organic Integrated Circuits, Ministry of Education and Tianjin Key Laboratory of Molecular Optoelectronic Sciences, Department of Chemistry, School of Science, Tianjin University, Tianjin, 300072, China.

Advanced Materials (Deerfield Beach, Fla.)

|May 30, 2024

Summary

This summary is machine-generated.

An AI agent integrating GPT-4 and machine learning extracts organic field-effect transistor (OFET) data from literature, achieving over 92% accuracy. This enables optimized device design, tripling charge transport properties in specific OFETs.

Keywords:

accelerated design large language models machine learning organic field‐effect transistors

More Related Videos

Author Spotlight: Enhancing Understanding and Treatment Strategies with the NEC-on-a-Chip Model

Author Spotlight: Enhancing Understanding and Treatment Strategies with the NEC-on-a-Chip Model

Published on: July 28, 2023

Probing C84-embedded Si Substrate Using Scanning Probe Microscopy and Molecular Dynamics

Probing C84-embedded Si Substrate Using Scanning Probe Microscopy and Molecular Dynamics

Published on: September 28, 2016

Related Experiment Videos

Last Updated: Jun 25, 2025

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

Author Spotlight: Enhancing Understanding and Treatment Strategies with the NEC-on-a-Chip Model

Author Spotlight: Enhancing Understanding and Treatment Strategies with the NEC-on-a-Chip Model

Published on: July 28, 2023

Probing C84-embedded Si Substrate Using Scanning Probe Microscopy and Molecular Dynamics

Probing C84-embedded Si Substrate Using Scanning Probe Microscopy and Molecular Dynamics

Published on: September 28, 2016

Area of Science:

Organic electronics
Materials science
Artificial intelligence in science

Background:

Large language models (LLMs) show promise but require adaptation for specialized scientific fields.
Extracting and structuring experimental data from scientific literature is a significant challenge.

Purpose of the Study:

To develop an AI agent for extracting and organizing organic field-effect transistor (OFET) experimental data.
To leverage this data for guiding and optimizing OFET device design.
To demonstrate the application of LLMs in the field of organic optoelectronics.

Main Methods:

Integration of the generative pre-trained transformer 4 (GPT-4) model with machine learning (ML) algorithms.
Development of prompt engineering and human-in-loop strategies for data extraction.
Creation of a standardized database of OFET parameters from scientific literature.
Training an Extreme Gradient Boosting ML model for device performance prediction.

Main Results:

The AI agent achieved precision and recall rates exceeding 92% in extracting OFET experimental parameters.
A database containing information on 709 OFETs from 277 articles was compiled.
The AI agent provided an optimization scheme that tripled the charge transport properties of a specific OFET.
High-precision model interpretation facilitated feasible optimization strategies.

Conclusions:

The developed AI agent effectively applies LLMs to organic optoelectronic device research.
This approach expands research paradigms for organic optoelectronic materials and devices.
The AI agent demonstrates a powerful tool for accelerating scientific discovery in specialized fields.