Date of Graduation
8-2014
Document Type
Thesis
Degree Name
Master of Science in Electrical Engineering (MSEE)
Degree Level
Graduate
Department
Electrical Engineering
Advisor/Mentor
Jingxian Wu
Committee Member
Baohua Li
Second Committee Member
Shengfan Zhang
Keywords
Coherence, EEG, Golf, SVM
Abstract
In this thesis, a machine learning based method is proposed to predict the putt outcomes of golfers based on their electroencephalogram (EEG) data. The method can be used as a core building block of a brain-computer interface, which is designed to provide guidance to golf players based on their EEG patterns. The proposed method includes three steps. First, multi-channel 1-second EEG trials were extracted during golfers' preparation of putting. Second, different features are calculated such as correlation coefficient, power spectrum density and coherence, which are used as features for the classification algorithm. To predict golfers' performance, the support vector machine algorithm is used to classify the EEG patterns into two categories corresponding to successful and non-successful putts. The proposed approach utilizes a large number of features extracted from the EEG signals, and it is capable of providing adequate prediction that could help golfers to improve their performances.
Citation
Guo, Q. (2014). Improving Golf Putt Performance with Statistical Learning of EEG Signals. Graduate Theses and Dissertations Retrieved from https://scholarworks.uark.edu/etd/2166