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 Experiment Videos

An Adaptive Multi-Scale Manifold Embedding Preprocessing Framework for High-Dimensional Data Visualization.

Tianhao Ni, Bingjie Li, Zhigang Yao

    IEEE Transactions on Visualization and Computer Graphics
    |June 17, 2026
    PubMed
    Summary
    This summary is machine-generated.

    Related Concept Videos

    Introduction to Scalers01:21

    Introduction to Scalers

    Many familiar physical quantities can be specified completely by giving a single number and the appropriate unit. For example, "a class period lasts 50 min," or "the gas tank in my car holds 65 L," or "the distance between the two posts is 100 m." A physical quantity that can be specified completely in this manner is called a scalar quantity. The word "scalar" is a synonym for "number." Time, mass, distance, length, volume, temperature, and energy are some examples of scalar quantities.
    Scalar...

    You might also read

    Related Articles

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

    Sort by
    Same author

    Improved CenterNet-Based Multimodal Object Detection for Low-Light and Complex Environments.

    Sensors (Basel, Switzerland)·2026
    Same author

    Current treatment landscape and translational priorities in malignant rhabdoid tumor of the kidney.

    Frontiers in pediatrics·2026
    Same author

    A novel glioma prognosis marker CAMK2A is related to immune microenvironment and may be involved in Ras/Raf/MEK/ERK signaling.

    Scientific reports·2026
    Same author

    Interpretable scRNA-seq Analysis with Intelligent Gene Selection.

    Applied biochemistry and biotechnology·2026
    Same author

    Survival prediction in stage II/III rectal cancer: Role of immune-inflammatory biomarkers post neoadjuvant chemoradiotherapy.

    Oncology letters·2026
    Same author

    Phenotypic and genomic study of digital dermatitis in UK Holstein heifers.

    BMC genomics·2026
    Same journal

    GLLA: A Unified Force-Directed Graph Layout Framework Supporting Local Adjustments.

    IEEE transactions on visualization and computer graphics·2026
    Same journal

    Multi-Perception Crowd: Learning to combine entity and implicit perception for diverse crowd simulation.

    IEEE transactions on visualization and computer graphics·2026
    Same journal

    Hiding in Plain Sight: Camouflaging Real-world Objects.

    IEEE transactions on visualization and computer graphics·2026
    Same journal

    RTF2Mesh: Restricted Tangent Face Based Mesh Compression With Neural Displacement Fields.

    IEEE transactions on visualization and computer graphics·2026
    Same journal

    Practical Occluder Generation for Mobile Games.

    IEEE transactions on visualization and computer graphics·2026
    Same journal

    Spatial-temporal Relation guided Motion Transfer via Diffusion Model.

    IEEE transactions on visualization and computer graphics·2026
    See all related articles

    Adaptive Multi-Scale Manifold Embedding (AMSME) enhances high-dimensional data visualization by using ordinal distances for better neighborhood construction and cluster separation. This method improves both intra-cluster structure preservation and inter-cluster separability in complex datasets.

    Area of Science:

    • Data Science
    • Computational Biology
    • Machine Learning

    Background:

    • High-dimensional data visualization faces challenges in neighborhood construction and cluster separation.
    • Traditional methods using Euclidean distances suffer from distance concentration in high dimensions.
    • Existing manifold embedding algorithms can be sensitive to noise and data structure variations.

    Purpose of the Study:

    • To propose Adaptive Multi-Scale Manifold Embedding (AMSME), a novel preprocessing framework for manifold embedding algorithms.
    • To enhance the robustness of neighborhood construction and improve the separation of intra-cluster and inter-cluster structures in high-dimensional data.
    • To optimize the performance of dimensionality reduction techniques like t-SNE, UMAP, and PaCMAP.

    Main Methods:

    Related Experiment Videos

  • Introduced ordinal distance as a replacement for Euclidean distances to improve neighborhood ordering stability.
  • Developed an adaptive neighborhood adjustment strategy to create similarity graphs optimizing intra-cluster compactness and inter-cluster separability.
  • Transformed similarity graphs into structure-enhanced distance matrices as optimized inputs for manifold embedding algorithms.

    • Main Results:

    • AMSME significantly improves inter-cluster separation while effectively preserving intra-cluster topological structures across various datasets.
    • Ordinal distance mitigates the adverse effects of distance concentration in high-dimensional settings.
    • In a scRNA-seq dataset, AMSME identified potential neuronal subtypes with preliminary evidence of transcriptional differences.

    Conclusions:

    • AMSME provides a robust framework for improving high-dimensional data visualization and analysis.
    • The ordinal distance approach and adaptive neighborhood strategy enhance the performance of existing manifold embedding techniques.
    • AMSME shows promise in biological data analysis, particularly in identifying novel cell subtypes from single-cell RNA sequencing data.