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

Simultaneous classification and feature clustering using discriminant vector quantization with applications to

Jia Li1, Hongyuan Zha

  • 1Statistics Department, Penn State Univ, PA 16802, USA. jiali@stat.psu.edu

Proceedings. IEEE Computer Society Bioinformatics Conference
|April 20, 2005
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

Learning Roles With Emergent Social Value Orientations.

IEEE transactions on pattern analysis and machine intelligence·2025
Same author

Learning Temporal Features With Alternated Similarity and Proximity Attention for Time-Series Prediction.

IEEE transactions on neural networks and learning systems·2025
Same author

A Transformative Topological Representation for Link Modeling, Prediction and Cross-Domain Network Analysis.

IEEE transactions on pattern analysis and machine intelligence·2024
Same author

Learning Fair Representations via Distance Correlation Minimization.

IEEE transactions on neural networks and learning systems·2022
Same author

Structured Cooperative Reinforcement Learning With Time-Varying Composite Action Space.

IEEE transactions on pattern analysis and machine intelligence·2021
Same author

Interpretable Anomaly Detection in Event Sequences via Sequence Matching and Visual Comparison.

IEEE transactions on visualization and computer graphics·2021
Same journal

Epitope prediction algorithms for peptide-based vaccine design.

Proceedings. IEEE Computer Society Bioinformatics Conference·2006
Same journal

Keynote address: the role of algorithmic research in computational genomics.

Proceedings. IEEE Computer Society Bioinformatics Conference·2006
Same journal

Stepping up the pace of discovery: the genomes to life program.

Proceedings. IEEE Computer Society Bioinformatics Conference·2006
Same journal

Prokaryote phylogeny without sequence alignment: from avoidance signature to composition distance.

Proceedings. IEEE Computer Society Bioinformatics Conference·2006
Same journal

Efficient reconstruction of phylogenetic networks with constrained recombination.

Proceedings. IEEE Computer Society Bioinformatics Conference·2006
Same journal

A new approach for gene annotation using unambiguous sequence joining.

Proceedings. IEEE Computer Society Bioinformatics Conference·2006
See all related articles

This study introduces a new method for simultaneous classification and feature clustering, improving accuracy and reducing complexity in high-dimensional data. Applied to lymphoma classification, it identified biologically relevant gene expression patterns.

Area of Science:

  • Machine Learning
  • Bioinformatics
  • Computational Biology

Background:

  • Supervised learning benefits from automatic feature clustering for understanding feature interactions and class relationships.
  • Feature clustering can enhance classification accuracy and reduce computational load in high-dimensional datasets.

Purpose of the Study:

  • To develop a method for simultaneous classification and feature clustering.
  • To improve upon existing prototype classification methods like discriminant vector quantization (DVQ).

Main Methods:

  • Extending discriminant vector quantization (DVQ) using minimum description length principles.
  • Integrating feature clustering with classification by fusing features within identified clusters.

Main Results:

Related Experiment Videos

  • The developed method was applied to human lymphoma microarray gene expression data.
  • Incorporating feature clustering led to improved classification accuracy.
  • Generated clusters corresponded well with biologically significant gene expression signatures.

Conclusions:

  • The novel method effectively performs simultaneous classification and feature clustering.
  • Feature clustering enhances both classification performance and biological interpretation of high-dimensional data.
  • The approach shows promise for applications in areas like cancer subtyping.