Z-score-normalized euclidean distances

version (2.87 KB) by Wei-Rong Chen
Compute normalized euclidean distance between two arrays [m (points) x n (features)]


Updated 3 Oct 2016

View License

% Z-score-normalized euclidean distances.
% Compute euclidean distance between two arrays [m (points) x n (features)]
% The two input arrays must share the same features but each feature may be
% in different scale (e.g., Time (ms) vs. Freq (kHz) ). In order to compute
% the closeness between two arrays without weighting on the feature with
% larger scale, the two input arrays undergo z-score
% normalization, before computing the distances.
% Input:
% pt1, pt2 : two input arrays: m (points) x n (features)
% pt1 and pt1 must be either in the same dimensions (i.e., dim(pt1) = dim(pt2) ), or
% pt2 = 1 x n (features) and pt1 = m (points) x n (features),
% then the output 'd' will be the distances from pt2 to each elements in pt1.
% Output:
% d : m (points) x 1 vector: zscore normalized distances/closeness between the two input arrays.
% Wr.Ch Jun-15-2016

Cite As

Wei-Rong Chen (2022). Z-score-normalized euclidean distances (https://www.mathworks.com/matlabcentral/fileexchange/59407-z-score-normalized-euclidean-distances), MATLAB Central File Exchange. Retrieved .

MATLAB Release Compatibility
Created with R14
Compatible with any release
Platform Compatibility
Windows macOS Linux

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!