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 Concept Videos

Transformers01:26

Transformers

1.7K
A device that transforms voltages from one value to another using induction is called a transformer. A transformer consists of two separate coils, or windings, wrapped around the same soft iron core. However, they are electrically insulated from each other.
The iron core has a substantial relative permeability. Therefore, the magnetic field lines generated due to the current in one winding are almost entirely confined within the core, such that the same magnetic flux permeates each turn of both...
1.7K
Types Of Transformers01:16

Types Of Transformers

1.4K
Transformers can provide desired voltages to a circuit by modifying the number of turns in the secondary windings.
If the ratio of the number of turns in the secondary winding to that of the primary winding is greater than one, then the transformer is said to be a step-up transformer. In a step-up transformer, the voltage at the secondary winding is greater than the voltage applied at the primary winding.
However, if this ratio is less than one, the transformer is said to be a step-down...
1.4K

You might also read

Related Articles

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

Sort by
Same author

Correction: Determinants of Sustainable Return to Work After Burnout or Depression: A Longitudinal Cohort Study.

Journal of occupational rehabilitationยท2026
Same author

Associations of Exposure to Common Plasticizers and Organophosphate Pesticides during Pregnancy and in Childhood with Cognitive Performance in Adolescents: A Population-Based Study.

Environmental science & technologyยท2026
Same author

Understanding burnout and engagement during medical residency: a multifactorial and longitudinal approach.

BMC medical educationยท2026
Same author

Metabolic changes in human plasma samples among workers exposed to diisocyanate products.

Food and chemical toxicology : an international journal published for the British Industrial Biological Research Associationยท2026
Same author

Exposure of Farmers and Spouses to Glyphosate in Morocco: Urinary Levels and Predictors of Exposure.

Toxicsยท2026
Same author

Biomonitoring of Occupational Exposure to Mercury Among Dental Health Workers in LMICs: A Systematic Review.

International dental journalยท2026

Related Experiment Video

Updated: Jan 10, 2026

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

2.3K

Implementing generative pretrained transformer models for text recognition tasks in safety data sheets.

Floris Pekel1, Gino Kalkman1, Erik Lemcke1

  • 1TNO, Department of Risk Assessment, Prevention, Innovation and Development, Netherlands Organization for Applied Scientific Research, Princetonlaan 6, 3584CB Utrecht, The Netherlands.

Annals of Work Exposures and Health
|November 24, 2025
PubMed
Summary
This summary is machine-generated.

Automating safety data sheet (SDS) data extraction with large language models (LLMs) improves chemical inventory management. This enhances the accuracy and timeliness of workplace risk assessments, boosting occupational safety.

Keywords:
large language modelsoccupational safetysafety data sheetstext extraction

Related Experiment Videos

Last Updated: Jan 10, 2026

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

2.3K

Area of Science:

  • Occupational Health and Safety
  • Artificial Intelligence in Chemistry
  • Information Management

Background:

  • Chemical handling workplaces require robust risk assessments.
  • Manual data import from safety data sheets (SDSs) to inventories is inefficient.
  • Incomplete or delayed risk assessments pose significant occupational hazards.

Purpose of the Study:

  • To develop an automated pipeline for extracting data from SDSs using LLMs.
  • To streamline the management of chemical inventories in online systems.
  • To improve the efficiency and accuracy of workplace risk assessments.

Main Methods:

  • Implementation of a pipeline leveraging large language models (LLMs).
  • Automated extraction of key variables (company name, product name, hazard statements) from SDSs.
  • Comparison of LLM-extracted data accuracy against manual extraction.

Main Results:

  • The LLM pipeline achieved an average accuracy of 0.83 in data extraction.
  • Successful automation of critical data points from SDSs.
  • Demonstrated efficiency gains over manual data import processes.

Conclusions:

  • LLM-powered pipelines can effectively automate SDS inventory management.
  • Automated data extraction supports timely and comprehensive risk assessments.
  • This technology significantly contributes to enhancing occupational safety in chemical handling environments.