An improved quantum particle swarm optimisation and its application on hand kinematics tracking

Abstract

The evolutional motivated particle swarm optimisation (PSO) has been widely employed in various scientific areas, and there has been plenty of contribution on the modification and improvement of PSO. Recently, a quantum behaviour inspired optimisation algorithm (QPSO) was developed by modelling a Delta potential well in quantum space, which shows better performance in global search ability and convergence precision compared with the original PSO algorithm. In this paper, based on the principle of QPSO, we proposed a dynamic search strategy fused with chaos map to strengthen the ability of escaping from local optima, and replaced the attractor with beta distribution for faster convergence speed. We first compared this improved algorithm (DCQPSO) with PSO and QPSO on general optimisation benchmark functions. Then, from the point view of application, we also achieved a simplicity-oriented human hand kinematics tracking system by leveraging DCQPSO, which can be further served in human computer interaction (HCI). Indicated by the experiments result, DCQPSO outperforms either traditional PSO or QPSO algorithm, and it can be well qualified with optimisation task in hand kinematics tracking.