Related Experiment Video
Updated: Apr 11, 2026

Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision
Published on: March 28, 2025
Recurrence quantification analysis and support vector machines for golf handicap and low back pain EMG classification
Luís Silva1, João Rocha Vaz1, Maria António Castro2
1Faculdade de Motricidade Humana, Universidade de Lisboa, Portugal.
This study used electromyography (EMG) and machine learning to differentiate golf handicap and low back pain (LBP) levels. Findings reveal distinct neuromuscular strategies in golfers with LBP, aiding injury prevention.
Area of Science:
- Biomechanics
- Motor Control
- Sports Medicine
Background:
- Electromyography (EMG) analysis is crucial for understanding neuromuscular strategies in dynamic movements.
- Limited research exists on muscle coordination under motor constraints during dynamic contractions, particularly in golf.
- Golfers' handicap (Hc) and low back pain (LBP) are significant factors in injury occurrence.
Purpose of the Study:
- To assess the accuracy of Support Vector Machines (SVM) in classifying golfers based on handicap and LBP status using EMG data.
- To discriminate between low and high handicap golfers and between golfers with and without LBP during the golf swing.
- To identify specific neuromuscular coordination patterns associated with handicap and LBP in golfers.
Main Methods:
- Recurrence Quantification Analysis (RQA) features were extracted from trunk and lower limb muscle EMG signals.
- RQA features, including recurrence rate (RR) and determinism/RR ratio, were used to train an SVM classifier.
- Classification accuracy was evaluated for different phases of the golf swing (swing, backswing, downswing).
Main Results:
- SVM achieved high accuracy in discriminating Hc (94.4-97.1%) and LBP (96.9-99.7%) across swing phases.
- Recurrence rate (RR) and determinism/RR ratio demonstrated significant discriminant power.
- Specific muscles like external oblique (EO), biceps femoris (BF), semitendinosus (ST), and rectus femoris (RF) showed high accuracy in classification, varying by laterality and phase.
- Low back pain golfers exhibited distinct neuromuscular coordination strategies compared to asymptomatic golfers.
Conclusions:
- RQA features combined with SVM provide a robust method for classifying golfers by handicap and LBP status.
- The study highlights the capacity of EMG-based analysis to reveal differences in neuromuscular coordination related to golf performance and injury risk.
- Findings suggest that LBP influences neuromuscular strategies during the golf swing, offering insights for targeted interventions and injury prevention.
More Related Videos
08:27Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines
Published on: January 5, 2024
06:28Biomechanical Changes Related to Low Back Pain: An Innovative Tool for Movement Pattern Assessment and Treatment Evaluation in Rehabilitation
Published on: December 13, 2024