Parkinson’s Disease Identification using KNN and ANN

Algorithms based on Voice Disorder

INTRODUCTION :

Brief on Topic Neurodegenerative disease has human, social and financial impacts, on a personal,
professional and social level. It is a progressive pathology that affects the brain and the nervous
system, leading to the death of nerve cells. The most known and frequent ones are Alzheimer's and
Parkinson's diseases. Parkinson’s disease, is particularly linked to the loss of dopamineproducing
neurons in the basic ganglia. In fact, medication fees for Parkinson's disease are very expensive. At
the moment, no cure has been found. Medication is limited to treatments, at an early stage, to improve
the patient's quality of life. Several methods have been used to detect the symptoms of Parkinson's
disease, but most of them require motor actions that appear only in an advanced state of the disease.
Most used traditional methods for the determination of the disease, are costly invasive methods
namely SPECT and CT tomography’s which are effective, essentially, in the mature stage of the
disease. Besides classic methods, practitioners adopt several diagnostic paths. Some of them were
based on handwriting by considering the relationship between handwriting and nervous system
problems. Others have relied on peripheral biomarkers for early detection of PD. The detection of
Parkinson's disease is based on the use of different classifiers. The distinction between them is based
on measurement criteria, namely classification accuracy, Matthews’s correlation coefficient (MCC),
Spearman correlation coefficient, specificity, sensitivity, Fscore (Fmeasure) ... etc. Each of these
measurement criteria has formulas to calculate it and conclude which is the most qualitatively
adequate classifier for the study. Before defining these criteria, we must focus on the confusion
matrix. Called a contingency table, it is a tool for measuring the performance of a learning model,
checking how far its predictions are correct, compared to reality in classification problems

Problem Statement Of The Project:

Parkinson’s Disease Identification using KNN and ANN Algorithms based on Voice
Disorder.

Objectives Of The Project:

• By using Artificial Neural Networks (ANN) and K nearest neighbors (KNN) one can detect
PD patients from healthy ones.

• To analysis the patient data who has been diagnosed with PD Disease.

• Here we led a comparative analysis for efficient detection of Parkinson’s disease.

Goals of the Project:

In this project, by using speech signal processing we will lead a comparative analysis for efficient
detection of Parkinson’s disease applied to machine learning classifiers from voice disorder known as
dysphonia. we aimed to compare between machine learning classifiers, Artificial Neural
Networks (ANN) and K nearest neighbors (KNN). We used them to detect PD patients from
healthy ones and compute the accuracy of the both ANN and KNN Algorithm.

Existing system:

Several methods have been used to detect the symptoms of Parkinson's disease, but most of
them require motor actions that appear only in an advanced state of the disease. Most used
traditional methods for the determination of the disease, are costly invasive methods namely
SPECT and CT tomography’s which are effective, essentially, in the mature stage of the
disease. Besides classic methods, practitioners adopt several diagnostic paths. Some of them
were based on handwriting by considering the relationship between handwriting and nervous
system problems. Others have relied on peripheral biomarkers for early detection of PD.

Proposed system:

Here the evaluation of a classifier is based on the confusion matrix.

• The detection of Parkinson's disease is based on the use of different classifiers.

• The distinction between them is based on measurement criteria, namely

• Classification accuracy,

• Matthews’s correlation coefficient (MCC),

• specificity,

• sensitivity,

• F-score.
 LITRATURE SURVEY:

Sl.No TITLE AUTHOR PUBLSHED TOPIC DISCUSSED

YEAR

1 Early detection Junho Lee , 2020 A deep learning model proposed

of parkinson’s Fouzi Harrou to automatically discriminate
disease using and Ying sun. normal individual and PD patient
deep learning
and machine
learning.
2 Improving EJunho Lee , 2019 The classification methods in
Parkinson’s Fouzi Harrou machine learning for the
disease and Ying sun. prediction of Parkinsons disease
diagnosis with for better classification accuracy.
machine
learning method
3 Parkinson’s David C, Dong 2018 Prediction and diagnosis is
disease SI, Reiza Hossien possible using non-invasive
diagnosis using voice biomarkers as features,
machine also provides comparison of
learning and various ML classifiers with noisy
voice. and high dimensional data.

Methodology:

1. Data set:

The database consists of 195 sustained vocal phonations of 31 male and female subjects,
of which 23 were diagnosed with Parkinson's disease. The age of the patients varies
Speech between 46 and 85 years.

2. Recordings:

For each of the subjects, averages of six phonations, lasting from 1 to 36 s, were recorded.
 3. Feature Extraction / Selection :

Each method produces a unique number for each of the 195 signals.

4. Classifiers baselines:
1. ANN Classification.
2. KNN Classification.

Hardware Requirement:

• System : core i3 Processors.

• Hard Disk : 500 GB
• Ram : 8 GB/ 12 GB
• Any Desktop/Laptop system with this above configuration or higher level
Software Requirement:

Operating system : windows 8/ 10(64 bit OS)

IDE : Matlab

Architecture:

• The database consists of 195 sustained vocal phonations of 31 male and female
subjects, of which 23 were diagnosed with Parkinson's disease. The age of the
patients varies Speech between 46 and 85 years.
• For each of the subjects, averages of six phonations, lasting from 1 to 36 s, were
recorded.
• Each method produces a unique number for each of the 195 signals.
. Attribute Details For Diagnosis Of PD Patient
 • the machine learning algorithms used are Artificial Neural Networks (ANN) and K-
nearest neighbors (KNN). They are some of the most popular classifiers.
1. ANN Classifier.
2. KNN Classifier.

ANN Classifier View

Possible Outcome Of the Project:

In this study, we aimed to compare between machine learning classifiers, Artificial Neural
Networks (ANN) and K nearest neighbors (KNN). We used them to detect PD patients from
healthy ones.

By using ANN, 96.7% correct classification rate was obtained. And for the KNN, the
accuracy achieved was 79.31%. Thus, the classifier result that was produced by the ANN is
the best score to our knowledges.
REFERENCES :

[1] R. Prashanth and S. D. Roy, ‘‘Early detection of Parkinson’s disease through patient
questionnaire and predictive modelling,’’ Int. J. Med. Informat., vol. 119, pp. 75–87, Nov.
2018.

[2] H. Gunduz, ‘‘Deep learning-based Parkinson’s disease classification using vocal feature
sets,’’ IEEE Access, vol. 7, pp. 115540–115551, 2019.

[3] S. Lahmiri and A. Shmuel, ‘‘Detection of Parkinson’s disease based on voice patterns
ranking and optimized support vector machine,’’ Biomed. Signal Process. Control, vol. 49,
pp. 427–433, Mar. 2019.

[4] D. Braga, A. M. Madureira, L. Coelho, and R. Ajith, ‘‘Automatic detection of Parkinson’s

disease based on acoustic analysis of speech,’’ Eng. Appl. Artif. Intell., vol. 77, pp. 148–158,
Jan. 2019.

[5] V. Illner, P. Sovka, and J. Rusz, ‘‘Validation of freely-available pitch detection

algorithms across various noise levels in assessing speech captured by smartphone in
Parkinson’s disease,’’ Biomed. Signal Process. Control, vol. 58, Apr. 2020, Art. no. 101831