Related Experiment Video
Updated: Aug 20, 2025

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances
Published on: October 11, 2018
Fast prototype selection algorithm based on adjacent neighbourhood and boundary approximation
1College of Distance Education, Shaanxi Normal University, Xi'an, 710062, Shaanxi, China.
This study introduces a new prototype selection algorithm for large datasets. It efficiently creates a smaller, high-quality reference set for incremental learning without sacrificing accuracy.
Area of Science:
- Machine Learning
- Data Mining
- Computer Science
Background:
- Increasing data volumes challenge traditional classification algorithms.
- Existing methods struggle with execution time and memory constraints in incremental environments.
Purpose of the Study:
- To develop a novel prototype selection algorithm for efficient incremental learning.
- To address the need for fast, adaptive reference set generation in large datasets.
Main Methods:
- Integrates condensing and editing strategies for prototype selection.
- Extends neighbor reference from single to k-nearest neighborhood.
- Uses neighbor relationships and classification boundaries to identify prototypes.
- Periodically updates prototypes in non-boundary or unlearned zones.
Main Results:
- Achieves a smaller reference set with higher boundary prototypes.
- Maintains classification accuracy and reduction rate compared to existing algorithms.
- Demonstrates effectiveness in handling incremental data environments and large datasets.
Conclusions:
- The proposed algorithm offers an efficient solution for large-scale incremental learning.
- It effectively balances reference set size, accuracy, and adaptability.
- Provides a valuable tool for applications requiring dynamic data processing.
Related Concept Videos
Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
Woodward–Hoffmann Selection Rules and Microscopic Reversibility
Area Computation by the Alternative Coordinate Method
Areas Within Irregular Boundaries
Linear Approximation in Time Domain
For a simple pendulum with a mass evenly distributed along its length and the center of mass located at half the pendulum's length,...
Fast Decoupled and DC Powerflow

