Parkinson’s Diseases Detection By

Using Voice Recording Replication

MACHINE LEARNING PROJECT

Problem statement

 Parkinson’s disease is a progressive nervous system disorder that effects movement

leading to shaking ,stiffness and difficulty with walking ,balance and coordination.
Parkinson’s symptoms usually begin gradually and get worse over time.
 Work Flow

Train test split

Parkinson’s data Data pre processing

Support vector Machine

Classifier
 Parkinson’s
(or)
Healthy

Prediction
New Data Trained Support Vector Machine
Classifier
ABSTRACT

 A clinical expert system has been developed for detection of Parkinson’s Disease (PD).
The system extracts features from voice recordings and considers an advanced
statistical approach for pattern recognition. The significance of the work lies on the
development and use of a novel subject-based Bayesian approach to account for the
dependent nature of the data in a replicated measure-based design. The ideas under this
approach are conceptually simple and easy-to-implement by using Gibbs sampling.
Available information could be included in the model through the prior distribution. In
order to assess the performance of the proposed system, a voice recording replication-
based experiment has been specifically conducted to discriminate healthy people from
people suffering PD. The experiment involved 80 subjects, half of them affected by PD.
The proposed system is able to discriminate acceptably well healthy people from people
with PD in spite that the experiment has a reduced number of subjects.
 OBJECTIVES

Aim of the Project:

 To develop a model that is useful to detect the Parkinson’s disease through the
voice samples collected from the patients.
Scope of the Project:
 The scope of the project is to develop a model which is used to detect whether
the subject is affected with Parkinson’s disease or not.
 INTRODUCTION

 Parkinson’s disease (PD) is the second most common neurodegenerative disorder

after Alzheimer’s disease, affecting one in every 100 persons above the age of 65
years in Europe(Solana- Lavalle, G.,.(2020).
 According to the Parkinson’s Disease Foundation, an estimated 7 to 10 million
people worldwide are living with this medical condition(Patra, R. K., Gupta.(2020)
 Voice and speech, as dependent on movement of the articulators, are not spared.
 Introduction

 Voice and speech, as dependent on movement of the articulators, are not spared.
 The process starts with taking the speech samples from the subject.
 Each subject is advised to speak for 5 seconds and from each subject 3 voice
samples are taken
 After that the voice samples are pre-processed and the feature extraction is to be
done .
 During the pre-processing stage , noise in the voice which is collected from the
subject is removed by using high pass filter
 INTRODUCTION

 After the completion of pre-processing and feature extraction , it will enter

into the next stage called feature selection
 And finally the classification that whether the subject is affected with the
Parkinson’s disease or not will be declared based on the data set collected.
 If the output from the data set is 0 then the subject is declared as not affected
from the Parkinson’s disease
 If the output is 1 then the subjected is affected with Parkinson’s disease.
 DESIGN AND METHOLOGIES

 MODULE 1:
Data Collection and training using Machine Learning Algorithms

 MODULE 2:
Real Time data gathering and prognostics GUI design
 Data set Information

 Attribute Information:
 Matrix column entries (attributes):
name - ASCII subject name and recording number
MDVP:Fo(Hz) - Average vocal fundamental frequency
MDVP:Fhi(Hz) - Maximum vocal fundamental frequency
MDVP:Flo(Hz) - Minimum vocal fundamental frequency
MDVP:Jitter(%),MDVP:Jitter(Abs),MDVP:RAP,MDVP:PPQ,Jitter:DDP - Several
measures of variation in fundamental frequency
MDVP:Shimmer,MDVP:Shimmer(dB),Shimmer:APQ3,Shimmer:APQ5,MDVP:APQ,Shimmer:DDA - Several
measures of variation in amplitude
NHR,HNR - Two measures of ratio of noise to tonal components in the voice
status - Health status of the subject (one) - Parkinson's, (zero) - healthy
RPDE,D2 - Two nonlinear dynamical complexity measures
DFA - Signal fractal scaling exponent
spread1,spread2,PPE - Three nonlinear measures of fundamental frequency variation
MODULE:1
Data Collection and training using Machine Learning Algorithms
Step:1 Collection of data
Step 2: Processing of data
ARCHITECTURE DIAGRAM
DATA FLOW DIAGRAM
 1. Input and Output
1. Input Design
 
Model input for the data set named Parkinson.
1.Output Design

The data has been taken from the data set named pd speech features and after all pre-processing the
output has been recorded successfully
 1. Types of Testing

1. Unit testing

In the project the aim of the unit testing is to check the missing values in each column and in each row by using the function called parkinsons data.isnull().sum()
Test result
CONCLUSION

 This study focuses on the classification of a person

whether he/she affected with Parkinson’s disease or not
by taking the voice samples of the respective person
 The data was collected and trained using machine
learning algorithm and the predicted data has been tested
THANK YOU

R.Gowtham Reddy
V.Nirmal kumar varma