<![CDATA[Physical fitness assessment is crucial for evaluating an individual's physical performance and endurance. However, traditional methods often rely on manual observation, which can lead to subjectivity and inconsistent results. This study proposes a machine learning-based approach for physical fitness evaluation through motion detection using pose estimation and exercise classification models. A quantitative method was employed to train and evaluate models for four exercise types: push-ups, sit-ups, pull-ups, and chinning. Each model was trained separately and assessed using accuracy, precision, recall, and F1-score metrics, achieving accuracies of 97.50% for push-ups, 97.67% for sit-ups, 97.00% for pull-ups, and 98.50% for chinning. The maximum error margin compared to manual counting was 2.48%. System-generated outputs were validated against manual observations using standard evaluation matrices. These findings indicate that machine learning can offer a reliable, consistent, and automated solution for physical fitness assessment, with the potential to enhance training programs, support remote fitness monitoring, and reduce human error in performance evaluation.]]>
Copyrights © 2025
