Abstract

Parkinson’s disease Slowly progressive degeneration of nervous system i.e destruction of brain cells which produce dopamine. It significantly impacts the quality of life for those who have it. Timely and accurate diagnosis is crucial to ensure management and intervention. In years learning techniques have become increasingly popular, for analyzing complex data offering promising possibilities for improving PD diagnosis and tracking its progression. This study focuses on exploring how deep learning techniques can be applied to aspects of Parkinson’s Disease such as detection, assessing symptom severity and predicting disease progression. Various Algorithms are used in this project for detecting the illness using both features Hand Drawing and Speech. Additionally, a customized model is developed to determine whether an individual has Parkinson’s Disease by utilizing Hand written Images. The process of utilizing learning models for PD diagnosis includes gathering data from sources, preprocessing it, extracting relevant features, training models, conducting testing and evaluating their performance. Transfer learning and domain adaptation techniques are employed to enhance the models effectiveness.