Parkinson's disease (PD) is a long-term degenerative disorder of the central nervous system that mainly affects the motor system. Early in the disease, the most common symptoms are voice impairment, shaking, rigidity, slowness of movement, and difficulty with walking. In this project, we proposed Neural Networks based two modules i.e. VGER Spectrogram Detector and Voice Impairment Classifier, which aim to help doctors and people in diagnosing Parkinson Disease at an early stage based on the two decisive features i.e. walking patterns along with its recorded spectrogram and speech impairment, with the accuracies 71% and 74.36% respectively. The dataset has been taken from Physio Net Database bank & UCI Machine Repository. We have implemented an extensive empirical evaluation of CNNs (Convolutional Neural Networks) on large-scale image classification of grait signals converted to spectrogram images and deep dense ANNs (Artificial Neural Networks) on the voice recordings to predict whether a patient is suffering from Parkinson disease or not.
AnubhavJohri/Parkinson-Detection
We have implemented an extensive empirical evaluation of CNNs (Convolutional Neural Networks) on large-scale image classification of grait signals converted to spectrogram images and deep dense ANNs (Artificial Neural Networks) on the voice recordings to predict whether a patient is suffering from Parkinson disease or not.
Jupyter Notebook