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

Improving Translational Accuracy

Improving Translational Accuracy

Improving Translational Accuracy

Improving Translational Accuracy

Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...

You might also read

Related Articles

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

Sort by

Same author

A Modularized Higher-Order Diagnostic Classification Model for Clustered Attribute Hierarchies.

Multivariate behavioral research·2026

Same author

Uncovering Hierarchical Asymmetries in Artificial Intelligence Transformation: Navigating the Bright and Dark Sides Across Organizational Levels.

Journal of visualized experiments : JoVE·2026

Same author

Effects of divalent cations on diffusion dynamics of biological water confined between lipid membranes.

The Journal of chemical physics·2026

Same author

Neural Network Copulas for Generating Synthetic Test Data Preserving Psychometric Properties.

Journal of Intelligence·2026

Same author

Composite marginal likelihood estimation of higher-order diagnostic classification models under high dimensionality.

The British journal of mathematical and statistical psychology·2026

Same author

A Landmark-Guided Dual-Stream Synergistic Framework for Automated Intracranial Aneurysm Detection in Magnetic Resonance Angiography.

Journal of imaging informatics in medicine·2026

Search research articles

Related Experiment Video

Updated: Oct 27, 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

Low-shot transfer with attention for highly imbalanced cursive character recognition.

Amin Jalali¹, Swathi Kavuri¹, Minho Lee²

¹School of Electronics and Electrical Engineering, Kyungpook National University, Daegu, 41566, South Korea.

Neural Networks : the Official Journal of the International Neural Network Society

|July 19, 2021

Summary

Recognizing ancient Hanja characters is difficult due to data scarcity and class imbalance. The proposed RELATIN framework effectively addresses these challenges using novel low-shot regularization and attention mechanisms for improved ancient character recognition.

Keywords:

Attention transfer learning Decoupled -normalized classifier Highly imbalanced data samples Low-shot regularizer Traditional cursive character recognition

Related Experiment Videos

Last Updated: Oct 27, 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

Area of Science:

* Computer Vision and Pattern Recognition
* Historical Document Analysis
* Machine Learning for Cultural Heritage

Background:

* Ancient Korean-Chinese cursive character (Hanja) recognition faces significant hurdles, including numerous classes, character degradation, diverse handwriting, and visual similarity.
* Limited training data and severe class imbalance exacerbate recognition difficulties, hindering model performance.

Purpose of the Study:

* To introduce a unified framework, RELATIN, designed to overcome the challenges in ancient Hanja character recognition.
* To enhance recognition accuracy for instance-poor classes and mitigate the impact of extreme class imbalance.

Main Methods:

* Development of a novel low-shot regularizer to align weight vector norms for classes with few samples.
* Integration of a decoupled classifier with weight-scaling to address class imbalance by rectifying decision boundaries.
* Implementation of Jensen-Shannon divergence-based data augmentation and an attention module for feature alignment and selection.

Main Results:

* Extreme class imbalance significantly degrades classification performance.
* The low-shot regularizer successfully aligns classifier norms, favoring classes with fewer samples.
* Weight-scaling of the decoupled classifier proved dominant in improving performance across baseline conditions.
* The attention module enhanced feature representation by selecting more pertinent feature maps.
* The RELATIN framework demonstrated superior performance in handling extreme class imbalance.

Conclusions:

* The RELATIN framework offers a robust solution for recognizing ancient Hanja characters, particularly under conditions of extreme class imbalance and data scarcity.
* The combined approach of low-shot regularization, decoupled classification with weight-scaling, and attention mechanisms significantly improves recognition accuracy and feature representation.