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

Upsampling

Upsampling

Managing signal sampling rates is essential in digital signal processing to maintain signal integrity. A decimated signal, characterized by a reduced frequency range due to its lower sampling rate, can be upsampled by inserting zeros between each sample. This upsampling process expands the original spectrum and introduces repeated spectral replicas at intervals dictated by the new Nyquist frequency. To refine this zero-inserted sequence, it is passed through a lowpass filter with a cutoff...

You might also read

Related Articles

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

Sort by

Same author

Sub-Low Temperature Preconditioning Induced Cold Signaling and Antiviral Defenses Correlate with Reduced TSWV Accumulation in Tomato.

Plants (Basel, Switzerland)·2026

Same author

An interpretable multimodal framework using compact biomarkers and Kolmogorov-Arnold networks improves the early diagnosis of Alzheimer's disease.

Scientific reports·2026

Same author

Encephalomyocarditis virus impairs the blood-brain barrier by degrading tight junction proteins via AKT3-dependent autophagic and apoptotic pathways.

Virulence·2026

Same author

Prophylactic Cranial Irradiation in MRI-Staged Limited-Stage Small-Cell Lung Cancer: A Systematic Review and Meta-Analysis of Survival and Neurocognitive Outcomes.

Cancers·2026

Same author

Analysis of under-five mortality rate and healthcare utilization equity in Hunan Province, China, 2020-2024.

Preventive medicine reports·2026

Same author

Establishment of the Genetic Transformation System of <i>Trichoderma longibrachiatum</i> 40418 and Its Induced Resistance Against <i>Meloidogyne incognita</i> in Tomato.

Journal of fungi (Basel, Switzerland)·2026

Search research articles

Related Experiment Video

Updated: Sep 13, 2025

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

An improved lightweight tongue segmentation model with self-attention parallel network and progressive upsampling.

Xuan Wang¹, Yifang Cao¹, Yijia Chen²

¹School of Management, Beijing University of Chinese Medicine, Beijing, China.

Scientific Reports

|July 29, 2025

Summary

A new model, PAPU_TonSeg, improves tongue segmentation in Traditional Chinese Medicine (TCM) by enhancing feature extraction and reducing precision loss. This AI tool offers more accurate tongue diagnosis for clinical research.

Keywords:

Multi-level feature aggregation Parallel network Segformer The ECA attention mechanism Tongue semantic segmentation

More Related Videos

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Related Experiment Videos

Last Updated: Sep 13, 2025

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Area of Science:

Artificial Intelligence
Medical Imaging
Traditional Chinese Medicine

Background:

Tongue diagnosis is a key component of Traditional Chinese Medicine (TCM).
Accurate tongue image segmentation is vital for intelligent TCM diagnosis.
Existing methods struggle with blurred tongue edges and inaccurate segmentation.

Purpose of the Study:

To introduce an improved Segformer-based model for precise tongue semantic segmentation.
To address limitations in current tongue edge segmentation accuracy and clarity.
To enhance the intelligentization of TCM tongue diagnosis research.

Main Methods:

Developed Parallel Attention and Progressive Upsampling for Tongue Segmentation (PAPU_TonSeg).
Integrated a Self-Attention Parallel Network for simultaneous local and global feature extraction.
Incorporated Efficient Channel Attention (ECA) and Multi-dimensional Feature Progressive Upsampling.

Main Results:

PAPU_TonSeg demonstrated significant improvements in Mean Pixel Accuracy (MPA), Mean Intersection over Union (MIoU), and Dice coefficient on the BioHit dataset.
Achieved higher accuracy metrics compared to the original Segformer model on a second dataset.
The model exhibits lower parameter count and computational complexity than classical models.

Conclusions:

PAPU_TonSeg offers superior tongue segmentation performance, accurately capturing fine details like tooth marks.
The model effectively balances global and local feature extraction for improved attention distribution.
PAPU_TonSeg is a promising tool for advancing clinical diagnosis and research in TCM tongue diagnosis.