Related Experiment Video
Updated: Jun 13, 2026

ExCYT: A Graphical User Interface for Streamlining Analysis of High-Dimensional Cytometry Data
Published on: January 16, 2019
Fast construction of k-nearest neighbor graphs for point clouds
1Department of Computer Science, Florida State University, Tallahassee, FL 32306, USA. miconnor@cs.fsu.edu
This study introduces a faster parallel algorithm for k-nearest neighbor graph construction using Morton ordering. The method improves efficiency, reduces space usage, and handles large datasets effectively on multicore machines.
Area of Science:
- Computer Science
- Data Science
- Algorithm Design
Background:
- K-nearest neighbor (KNN) graph construction is fundamental in machine learning and data analysis.
- Existing parallel algorithms face challenges with efficiency, scalability, and resource utilization.
Purpose of the Study:
- To develop a novel parallel algorithm for efficient k-nearest neighbor graph construction.
- To leverage Morton ordering for improved performance on multicore architectures.
Main Methods:
- Implementation of a parallel algorithm utilizing Morton ordering for point set representation.
- Experimental evaluation on multicore machines comparing performance against existing methods.
Main Results:
- Demonstrated faster k-nearest neighbor graph construction compared to existing approaches.
- Achieved reduced space usage and enhanced cache efficiency.
- Showcased scalability for large datasets and ease of parallel implementation.
Conclusions:
- The proposed Morton ordering-based parallel algorithm offers significant advantages for k-nearest neighbor graph construction.
- This method provides a practical and efficient solution for handling large-scale data on modern multicore systems.
Related Concept Videos
Design Example: Measuring Distance Between Two Points with Obstructions
Vector Algebra: Graphical Method
We use the laws of geometry to construct resultant vectors, followed by trigonometry to find vector magnitudes and directions. For a geometric construction of the sum of two vectors in a plane, we follow the parallelogram rule. Suppose two vectors are at arbitrary positions. Translate either one of...
Cluster Sampling Method
To choose a cluster sample, divide the population into clusters (groups) and then randomly select some of the clusters. All the members from these clusters are in the cluster sample. For example, if you randomly sample four departments from your...
Distance Problem
Graphs of Two-Variable Functions
Vectors in 2D: Problem Solving