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

Pattern representation in feature extraction and classifier design: matrix versus vector.

Zhe Wang1, Songcan Chen, Jun Liu

  • 1Department of Computer Science and Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, PRChina.

IEEE Transactions on Neural Networks
|May 10, 2008
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

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

Sort by
Same author

Foundation Model-Based Zero-Shot Tissue Segmentation of Pathological Images via the Mixture of Local-to-Global Experts.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same author

EfficientCovNet: Modeling the Pairwise Voxel Dependency for Brain ROI Segmentation.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same author

MoHD: Multi-mOdal survival prediction through Hierarchical Decoupling of whole-slide image pyramids and genomics.

Medical image analysis·2026
Same author

Functional system-specific brain aging across the Alzheimer's disease continuum.

Translational psychiatry·2026
Same author

Direct PET-to-CT Generation for Attenuation Correction: A Slice-to-Slice Continual Transformer Segmentation-Aware Network.

IEEE journal of biomedical and health informatics·2026
Same author

Shared genetic architecture between the topology of brain white matter structural connectome and fluid intelligence.

Communications biology·2026
Same journal

Universal perceptron and DNA-like learning algorithm for binary neural networks: LSBF and PBF implementations.

IEEE transactions on neural networks·2013
Same journal

Guest editorial: special section on white box nonlinear prediction models.

IEEE transactions on neural networks·2011
Same journal

Data-based fault-tolerant control of high-speed trains with traction/braking notch nonlinearities and actuator failures.

IEEE transactions on neural networks·2011
Same journal

Guest editorial: special section on data-based control, modeling, and optimization.

IEEE transactions on neural networks·2011
Same journal

Neural network-based multiple robot simultaneous localization and mapping.

IEEE transactions on neural networks·2011
Same journal

Data-driven model-free adaptive control for a class of MIMO nonlinear discrete-time systems.

IEEE transactions on neural networks·2011
See all related articles

This study introduces a fully matrixized approach for pattern recognition, integrating matrix patterns in both feature extraction and classifier design. This novel method demonstrates effective and efficient performance, particularly for data with inherent structure like images.

Area of Science:

  • Pattern Recognition
  • Machine Learning
  • Computer Vision

Background:

  • Matrix patterns offer advanced feature extraction beyond traditional vectors.
  • Current methods often combine matrix feature extraction with vector classifiers, limiting potential.
  • The effectiveness of matrix patterns in classification remains underexplored.

Purpose of the Study:

  • To investigate the application of matrix pattern representation in both feature extraction and classifier design.
  • To propose and validate a fully matrixized approach (MatFE + MatCD).
  • To compare the fully matrixized approach against various combinations of matrix and vector representations for feature extraction and classification.

Main Methods:

  • Developed a fully matrixized approach (MatFE + MatCD) for pattern recognition.

Related Experiment Videos

  • Systematically evaluated all combinations of matrix and vector feature extraction (FE) and classifier design (CD).
  • Tested approaches including MatFE + MatCD, MatFE + VecCD, MatCD, VecFE + MatCD, VecFE + VecCD, and VecCD.

    • Main Results:

    • The proposed fully matrixized approach (MatFE + MatCD) achieved effective and efficient performance.
    • Demonstrated strong results for patterns with prior structural knowledge, such as images.
    • Validated the matrix as a feasible alternative pattern representation for both feature extraction and classifier design.

    Conclusions:

    • The fully matrixized approach (MatFE + MatCD) is a viable and high-performing method for pattern recognition tasks.
    • Matrix pattern representation offers a powerful alternative to vector representations in machine learning.
    • Findings support the utility of matrix patterns and provide insights into generalization theorems in machine learning.