Advanced Machine Learning Techniques for Precise Thyroid Disease Classification: A Novel Approach

Abstract

Aiming to address the extended diagnosis and recovery period along with low efficiency in traditional stroke patient rehabilitation, this study introduces a speech recognition-based finger rehabilitation training control system. This system enables patients to perform finger exercises while providing feedback on finger angle, speed, and position. Furthermore, it offers rehabilitation physicians valuable data for evaluation and reference in finger rehabilitation. The system is divided into hardware circuitry, a lower computer control system, and a voice recognition human-computer interaction system, all working in conjunction with the finger movement perception system. By applying the Hidden Markov Model (HMM) algorithm to the voice interaction system for pattern matching, the finger rehabilitation system undergoes simulation testing. The results demonstrate that the proposed rehabilitation training system based on speech recognition meets design requirements, ensuring safety, reliability, and substantial application potential in future finger rehabilitation training.