Search research articles

Search research articles

Related Experiment Videos

Condensed nearest neighbor data domain description.

Fabrizio Angiulli¹

¹Dipartimento di Elettronica Informatica e Sistemistica, Università della Calabria, Italy. f.angiulli@deis.unical.it

IEEE Transactions on Pattern Analysis and Machine Intelligence

|August 19, 2007

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

Mining sponge phenomena in RNA expression data.

Journal of bioinformatics and computational biology·2021

Same author

Prototype-based Domain Description for one-class classification.

IEEE transactions on pattern analysis and machine intelligence·2012

Same author

Scaling up support vector machines using nearest neighbor condensation.

IEEE transactions on neural networks·2010

Same journal

A Comprehensive Survey on Multimodal Recommender Systems: Taxonomy, Evaluation, and Future Directions.

IEEE transactions on pattern analysis and machine intelligence·2026

Same journal

Benchmarking the Robustness of Autonomous Driving to Environmental Illusions: A Lane Perception Perspective.

IEEE transactions on pattern analysis and machine intelligence·2026

Same journal

Learning Topology-Aware Representations via Test-Time Adaptation for Anomaly Segmentation.

IEEE transactions on pattern analysis and machine intelligence·2026

Same journal

TraGraph-GS: Trajectory Graph-based Gaussian Splatting for Arbitrary Large-Scale Scene Rendering.

IEEE transactions on pattern analysis and machine intelligence·2026

Same journal

SWIFT: A Small-World Interaction Framework for Flow-Aware Trajectory Prediction in Autonomous Driving.

IEEE transactions on pattern analysis and machine intelligence·2026

Same journal

HardFlow: Hard-Constrained Sampling for Flow-Matching Models Via Trajectory Optimization.

IEEE transactions on pattern analysis and machine intelligence·2026

See all related 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

This study introduces a new algorithm (CNNDD) for unsupervised data classification. It effectively identifies abnormal data by using a condensed reference set, improving nearest neighbor classification accuracy.

Area of Science:

Data Science
Machine Learning
Pattern Recognition

Background:

Unsupervised classification discriminates normal from abnormal data using nearest neighbor distances.
The effectiveness of the reference dataset's size and composition is crucial for classifier performance.

Purpose of the Study:

To investigate the impact of using a data subset as the reference set for classification.
To introduce and address the computational challenge of finding a minimum cardinality reference consistent subset.
To present the CNNDD algorithm for efficient computation of a reference consistent subset.

Main Methods:

Introduced the concept of a reference consistent subset.
Developed the CNNDD algorithm for computing a reference consistent subset with two passes.

Related Experiment Videos

Conducted experimental evaluations to assess the algorithm's performance.

Main Results:

Using a condensed data set as the reference set offers significant advantages.
The CNNDD algorithm effectively computes a reference consistent subset.
Experimental results confirm the proposed approach's effectiveness in data classification.

Conclusions:

Data condensation is beneficial for nearest neighbor-based classification.
The CNNDD algorithm provides an effective and efficient method for creating reference consistent subsets.
The study highlights the strengths and weaknesses of one-class nearest-neighbor methods for training set condensation.