Shape and Centroid Independent Clustring Algorithm for Crowd Management Applications

TL;DR

This paper introduces a robust, low-complexity clustering algorithm tailored for crowd management that is independent of shape and centroid, enhancing real-time data processing capabilities.

Contribution

The paper presents a novel clustering algorithm that is shape and centroid independent, with a new technique for efficient matrix power computation, suitable for real-time crowd applications.

Findings

Effective on real and synthetic data

Low complexity due to novel matrix power technique

Robust performance in crowd management scenarios

Abstract

Clustering techniques play an important role in data mining and its related applications. Among the challenging applications that require robust and real-time processing are crowd management and group trajectory applications. In this paper, a robust and low-complexity clustering algorithm is proposed. It is capable of processing data in a manner that is shape and centroid independent. The algorithm is of low complexity due to the novel technique to compute the matrix power. The algorithm was tested on real and synthetic data and test results are reported.