Flexible multi-objective particle swarm optimization clustering with game theory to address human activity discovery fully unsupervised

Download PDF
Open Webpage

Parham Hadikhani, Daphne Teck Ching Lai, Wee-Hong Ong

Published: 2024, Last Modified: 21 Nov 2025Image Vis. Comput. 2024EveryoneRevisionsBibTeXCC BY-SA 4.0
Abstract: Highlights•Novel unsupervised method for discovering human activity from skeleton-based data.•Introducing a flexible multi-objective PSO clustering based on game theory.•Adopting Incremental techniques to estimate the number of activities automatically.•Proposing smart grid-based swarm initialization to generate diverse solutions.•Updating particle velocity based on mean shift to find nonlinear clusters.