Prediction of Force Reaction, Joint Kinetics and Fatigue Indices Using Artificial Neural Network (ANN) for Plastic Rope

A carbon plastic rope is a lightweight and durable material that is widely used in various applications due to its strength and resistance to damage. This study employed an Artificial Neural Network (ANN) to investigate the ground reaction force, joint kinetics, and fatigue indices associated with the use of carbon plastic rope during the landing phase. The ANN was trained using a diverse range of data samples, extending beyond the scope of experimental data, to generate predictions. The analysis of the ANN's predictions revealed that increasing the magnitude of circular arm motions with the rope and vertical leg movements that initiate body motion led to alterations in the ground reaction force, joint kinetics, and fatigue indices. The measurements were standardized on a scale of 0 to 1, with the highest value of 0.92 indicating more efficient and effective arm movements. Similarly, the highest value of 0.91 on the scale represented superior technique in propelling the body forward through vertical leg movements that initiate body motion. The ground reaction force during the landing phase was measured in Newtons (N), representing the intensity of impact experienced by the body. The highest recorded ground reaction force was 1200 N, indicating a greater force exerted on the body upon landing. Joint kinetics during various techniques were evaluated on a scale of 0 to 1, with higher values indicating increased joint dynamics. These results shed light on the impact of rope jumping techniques on various variables and provide valuable insights for coaches, athletes, and researchers. Additionally, the prediction errors of the ANN were examined using linear regression, demonstrating an acceptable level of error compared to the target results obtained from experimental tests.