Analysing the Accuracy of Elite Amateur Golf Players during a Pre-tournament Wedge Test

Background: Previous studies identified a medium/strong relationship between the accuracy of wedge play and performance of professional golf players. However, there is a lack of research studies investigating which distance in wedge play has the strongest relationship to performance. Objective: The aim of the study was to determine the accuracy with wedges of elite amateur golfers and find out the relationship between accuracy from different distances and short and long-term performance. Methods: Ten elite golf players assessed accuracy across distances (45 – 85 m) with Trackman in a pre-tournament wedge test and afterward attended a three-round tournament. Results: Percentage error rate decreases (19.0% to 8.4%) with increasing distance, in addition, a significant difference in percentage error rate between 45 m distance and 85 m distance (p = 0.02) significant relation between percentage error rate and short term/long term performance indicators at 45 and 55 m. Conclusion: Distance control was significantly more difficult (more variable) than direction control with wedges. Significant difference between distances indicates greater difficulty in controlling distance over shorter distances played with wedges. Results show higher importance of accuracy with wedges on performance in shorter (45 and 55 m) versus longer (65, 75 and 85 m) distances. Players performed the stroke more consistently in terms of controlling key impact factors at longer distances, especially in regards to the club head speed, which, together with the ball speed, is the main determinant of the carry distance.

Download Full-text

Multiday EMG-Based Classification of Hand Motions with Deep Learning Techniques

Sensors ◽

10.3390/s18082497 ◽

2018 ◽

Vol 18 (8) ◽

pp. 2497 ◽

Cited By ~ 47

Author(s):

Muhammad Zia ur Rehman ◽

Asim Waris ◽

Syed Gilani ◽

Mads Jochumsen ◽

Imran Niazi ◽

...

Keyword(s):

Myoelectric Control ◽

Classification Error ◽

Linear Discriminant ◽

Upper Limb Prostheses ◽

Learning Techniques ◽

Significant Difference ◽

Improved Performance ◽

Long Term Performance ◽

Term Performance

Pattern recognition of electromyography (EMG) signals can potentially improve the performance of myoelectric control for upper limb prostheses with respect to current clinical approaches based on direct control. However, the choice of features for classification is challenging and impacts long-term performance. Here, we propose the use of EMG raw signals as direct inputs to deep networks with intrinsic feature extraction capabilities recorded over multiple days. Seven able-bodied subjects performed six active motions (plus rest), and EMG signals were recorded for 15 consecutive days with two sessions per day using the MYO armband (MYB, a wearable EMG sensor). The classification was performed by a convolutional neural network (CNN) with raw bipolar EMG samples as the inputs, and the performance was compared with linear discriminant analysis (LDA) and stacked sparse autoencoders with features (SSAE-f) and raw samples (SSAE-r) as inputs. CNN outperformed (lower classification error) both LDA and SSAE-r in the within-session, between sessions on same day, between the pair of days, and leave-out one-day evaluation (p < 0.001) analyses. However, no significant difference was found between CNN and SSAE-f. These results demonstrated that CNN significantly improved performance and increased robustness over time compared with standard LDA with associated handcrafted features. This data-driven features extraction approach may overcome the problem of the feature calibration and selection in myoelectric control.

Download Full-text