Simplified Swarm Optimization with Sorted Local Search for golf data classification

摘要: Golf Swing is one of the most difficult techniques in sports to perfect, and a smooth swing can't be achieved without correct process bodyweight transfer between feet during motion, which known as weight shift golf. As pointed out by various professional players coaches, proper critical hitting shot with good accuracy range, therefore it would beneficial for golfers obtain data corresponding their motions, so that analysis improvement on pose can made. Weight collected through common methods such using electronic scales may contain noise due factors pre-swing movements, order useful, necessary distinguish actual motion from noise. In this paper mining approach named Simplified Swarm Optimization Sorted Local Search (SSO-SLS), based variant Particle (PSO), has been proposed classify golf data. novel strategy introduced remedy issue premature convergence facing PSO allowing particles information nearest neighbors improve swarm diversity. Experiments UCI datasets show SSO-SLS competitive classification techniques, an ideal classifying shift.