A Hybrid Method for Knee Injury Detection Systems Using Petri Net and LSTM

Knee injuries impact mobility and quality of life, making them a common problem in both sports and general healthcare. Machine learning and mathematical models are being used more creatively as a result of the demand for precise, automated, and effective detection systems. A innovative hybrid approach that combines Petri Nets and Long Short-Term Memory (LSTM) networks to develop a reliable knee injury detection system is examined in this study. The combination of Petri Nets with LSTM networks creates a potent tool for detecting knee injuries, combining the benefits of mathematical modeling and machine learning. This hybrid approach not only improves diagnostic accuracy but also promotes preventative healthcare, opening the way for smarter, more responsive medical systems. The results of the trial show that the Injury Detection System outperforms previous studies and other classifier techniques, achieving a high classification accuracy of 99.71%.