Title :
Neural networks for golf swing analysis from weight-shift
Author :
Yoon, Ho Sub ; Bae, Chang Seok ; Min, Byung Woo
Author_Institution :
Syst. Eng. Res. Inst., Korea Inst. of Sci. & Technol., Taejon, South Korea
fDate :
27 Jun-2 Jul 1994
Abstract :
Weight-shift of human body motion means the continuous change of weights loaded on the left and right foot respectively. In this study a neural network method is employed to identify the golf swing from a continuous weight-shift waveform. We defined eight input features which can classify various shapes of swing pattern. The adopted network is a three-layered error backpropagation model consisting of eight input, ten hidden and two output nodes. According to experimental results, the identifying success rate is 97.75% using 10 hidden nodes and 5000 epochs
Keywords :
backpropagation; neural nets; pattern classification; sport; golf swing analysis; human body motion; neural network; sport; swing pattern classification; three-layered error backpropagation model; weight-shift; Artificial intelligence; Feature extraction; Hardware; Humans; Image motion analysis; Motion analysis; Neural networks; Pattern analysis; Shape; Signal analysis;
Conference_Titel :
Neural Networks, 1994. IEEE World Congress on Computational Intelligence., 1994 IEEE International Conference on
Conference_Location :
Orlando, FL
Print_ISBN :
0-7803-1901-X
DOI :
10.1109/ICNN.1994.374725
