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

Classification of Signals

Classification of Signals

In signal processing, signals are classified based on various characteristics: continuous-time versus discrete-time, periodic versus aperiodic, analog versus digital, and causal versus noncausal. Each category highlights distinct properties crucial for understanding and manipulating signals.
A continuous-time signal holds a value at every instant in time, representing information seamlessly. In contrast, a discrete-time signal holds values only at specific moments, often denoted as x(n), where...

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...

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...

Aggregates Classification

Aggregates Classification

Aggregate classification is generally based on its size, petrographic characteristics, weight, and source. Size classification ranges from coarse to fine aggregates, defined by the size of the particles. Coarse aggregates are particles that do not pass through ASTM sieve No. 4, and aggregates that pass through the sieve are fine aggregates.
Petrographic classification groups aggregates based on common mineralogical characteristics. Some of the common mineral groups found in aggregates are...

Classification of Systems-II

Classification of Systems-II

Continuous-time systems have continuous input and output signals, with time measured continuously. These systems are generally defined by differential or algebraic equations. For instance, in an RC circuit, the relationship between input and output voltage is expressed through a differential equation derived from Ohm's law and the capacitor relation,

Classification of Systems-I

Classification of Systems-I

Linearity is a system property characterized by a direct input-output relationship, combining homogeneity and additivity.
Homogeneity dictates that if an input x(t) is multiplied by a constant c, the output y(t) is multiplied by the same constant. Mathematically, this is expressed as:

You might also read

Related Articles

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

Sort by

Same author

Bacteriophage P2-71: a promising therapeutic against multidrug-resistant <i>Proteus mirabilis</i> in urinary tract infections.

Frontiers in veterinary science·2024

Same author

GraKerformer: A Transformer With Graph Kernel for Unsupervised Graph Representation Learning.

IEEE transactions on cybernetics·2024

Same author

Three-dimensional printed titanium chest wall reconstruction for tumor removal in the sternal region.

Journal of cardiothoracic surgery·2024

Same author

Canine mesenchymal stem cell-derived exosomes attenuate renal ischemia-reperfusion injury through miR-146a-regulated macrophage polarization.

Frontiers in veterinary science·2024

Same author

Cytoplasmic FBXO38 mediates PD-1 degradation.

EMBO reports·2024

Same author

CD24-Targeted NIR-II Fluorescence Imaging Enables Early Detection of Colorectal Neoplasia.

Cancer research·2024

Search research articles

Related Experiment Video

Updated: Jul 1, 2026

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

A diffusion-inspired noise augmentation framework for robust multilingual text classification.

Ming Gao¹, Yuanfa Cen², Haifeng Liu¹

¹Guangzhou City Institute of Technology, Guangzhou, 510800, Guangdong, China.

Scientific Reports

|June 29, 2026

Summary

This summary is machine-generated.

NoiseDiffuser (ND) enhances text classifiers against errors and ambiguity. This task-oriented framework improves model robustness and accuracy in noisy environments.

Keywords:

Data augmentation Diffusion-inspired noise modeling Feature manifold Overfitting mitigation Text classification

Related Experiment Videos

Last Updated: Jul 1, 2026

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

Area of Science:

Natural Language Processing
Machine Learning
Artificial Intelligence

Background:

Text classifiers struggle with spelling errors and semantic ambiguity, impacting real-world performance.
Existing augmentation methods may not adequately address diverse noise types or preserve original semantics.

Purpose of the Study:

To introduce NoiseDiffuser (ND), a novel text augmentation framework designed to enhance the robustness of text classifiers.
To address challenges posed by spelling errors and semantic ambiguity in text classification tasks.

Main Methods:

Developed a task-oriented text augmentation framework (ND) inspired by diffusion principles.
Implemented a length-aware dynamic noise schedule to adapt perturbation intensity based on text length.
Integrated a multilingual semantic recovery strategy using HIT-CIR Tongyici Cilin (Chinese) and WordNet (English) for synonym-based perturbation and lexical filtering.

Main Results:

Reduced the generalization gap by 41.7% and increased feature cosine similarity by up to 33.33%.
Decreased FGSM-induced accuracy degradation by approximately 40% and improved accuracy under TextFooler attacks.
Enhanced short-text F1 scores for baseline classifiers and BERT by approximately 38.63%.

Conclusions:

NoiseDiffuser (ND) provides an efficient and compatible strategy for text classification in noisy environments.
The framework effectively improves model robustness and performance while largely preserving original semantics.
ND demonstrates significant improvements in handling spelling errors and semantic ambiguity across various datasets.