Rishab Shankar

Can a neural network determine whether or not a person has Parkinson's Syndrome?

Started May 3, 2024

Abstract or project description

In this project, we are developing a neural network model using Python to predict whether a person has Parkinson's disease by analyzing audio recordings. We are utilizing a dataset from the UC Irvine Machine Learning Repository, which is well-known for its diverse range of datasets used in machine learning research. By employing advanced techniques in PyTorch and various Python libraries, we can train our model to recognize patterns and features within the audio data that may indicate the presence of Parkinson's disease. This involves preprocessing the audio recordings to extract meaningful features such as fundamental frequency, intensity, and Mel-frequency cepstral coefficients, which capture essential characteristics of the voice. The ultimate goal is to create a reliable and efficient model that can assess an individual’s risk of having Parkinson's disease based solely on their voice, paving the way for innovative approaches to early diagnosis and monitoring in healthcare.