This project implements clustering algorithms for in Euclidian space Rd and polygonal curves in Euclidian space R2 using using the 8 combinations of the following variants. The Manhattan metric (L1) is used for vectors and the pseudo Dynamic Time Warping (DTW) for the curves.
Initialization
- Random selection of K points/curves (simplest)
- K-means++
Assignment
- Lloyd's assignment (simplest approach)
- Assignment by Range Search using LSH for vectors/curves (inverse assignment)
Update
- Partitioning around medoids (PAM) `a la Lloyds
- Calculating Mean Vector/DTW Centroid Curve
Download source code by typing:
https://github.com/PanPapag/Clustering-for-vectors-and-polygonal-curves.git
This project is licensed under the MIT License - see the LICENSE file for details