Abstract | ||
---|---|---|
To analyze golf player’s individual golf swing and improve their skills using computerized methods, recognizing the golf player’s personal swing is essential. In this study, the golf swing signal is acquired using high-precision strain gage sensor integrated into the golf club. We use four different types of classifiers to classify the golf players’ swing signals i.e. decision tree algorithms, discriminant analysis algorithms, support vector machine algorithms, and k-nearest neighbor classifiers. The best result is achieved by linear support vector machine with 100% testing accuracy and minimum time-cost. The classification results demonstrate that using machine learning algorithms is effective in recognizing golf player’s swing signature, and that the chosen strain gage sensor works well. This work presents the foundation for our future research in classifying different types of golf swings of the same golf player. |
Year | DOI | Venue |
---|---|---|
2017 | 10.1016/j.procs.2018.03.061 | Procedia Computer Science |
Keywords | Field | DocType |
strain gage sensor,golf swing signal,machine learning,classification,golf swing analysis | Decision tree,Computer science,Support vector machine,Algorithm,Artificial intelligence,Strain gauge,Linear discriminant analysis,Machine learning,Swing | Conference |
Volume | ISSN | Citations |
129 | 1877-0509 | 0 |
PageRank | References | Authors |
0.34 | 5 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Zhichao Zhang | 1 | 6 | 4.88 |
Yuan Zhang | 2 | 160 | 16.82 |
Anton Kos | 3 | 80 | 17.96 |
Anton Umek | 4 | 48 | 10.66 |