Parkinson'S Brain Disease Prediction Using Descriptive Analysis

PARKINSON’S BRAIN DISEASE PREDICTION USING
DESCRIPTIVE ANALYSIS
A PROJECT REPORT
Submitted by
AISHWARYA S (211614104005)
ANUSHA S (211614104019)
in partial fulfillment for the award of the degree

of
BACHELOR OF ENGINEERING
IN
COMPUTER SCIENCE AND ENGINEERING
RAJALAKSHMI ENGINEERING COLLEGE

ANNA UNIVERSITY: CHENNAI 600 025
April 2018
BONAFIDE CERTIFICATE
Certified that this project report“PARKINSON’S BRAIN DISEASE

PREDICTION USING DESCRIPTIVE ANALYSIS” is the bonafidework of
AISHWARYA S (211614104005) and ANUSHA S (211614104019) who carried
out the project work under my supervision.
SIGNATURE SIGNATURE
Dr. P. KUMAR Mr.B.BHUVANESWARAN
Professor and Head Supervisor
Assistant Professor (SG)
Department of Computer Science and Department of Computer Science and
Engineering Engineering
Rajalakshmi Engineering College Rajalakshmi Engineering College
Chennai – 602 105 Chennai – 602 105
Submitted to Project and Viva Examination held on __________.
Internal Examiner External Examiner

ACKNOWLEDGEMENT
I extend my gratitude to my Chairman Mr.S.MEGANATHAN, B.E.,F.I.E.,

and Chairperson Dr.(Mrs.).THANGAM MEGANATHAN, M.Phil.,Ph.D., for
providing me with all the necessary resources and other facilities towards
completion of this project. I am extremely grateful to my principal
Dr.S.N.MURUGESAN, M.E.,Ph.D., for giving me a valuable support and
encouragement throughout the duration of this course.
I wish to thank Dr.P.KUMAR, M.E.,Ph.D., Head of the Department,
Department of Computer Science and Engineering, Rajalakshmi Engineering
College, for extending all facilities to me to work on this project. I take this
opportunity to thank our coordinator Dr.S.UDHAYAKUMAR, M.E.,Ph.D.,
Associate Professor, Department of Computer Science and Engineering,
Rajalakshmi Engineering College for his kind direction.
I would like to express my sincere appreciation and gratitude to my guide
Mr.B.BHUVANESWARAN,M.E.,Assistant Professor (SG), Department of
Computer Science and Engineering, Rajalakshmi Engineering College for his
guidance, constant encouragement, and support. His meticulous attention and
creative thinking have been a source of inspiration for me throughout this project.
I also extend my sincere thanks to all faculty members and supporting staffs
for their direct and indirect involvement in successful completion of the project. All
endeavors over a long period can be successful only with the advice and support of
many well-wishers. I take this opportunity to express my gratitude and appreciation
to all of them. Above all, I express my heartfelt thanks to my parents and family
members who have dedicated their life to my well-being.
ABSTRACT
Big data is a term that describes the large volume of data, both structured and
unstructured, that flows into a business on a regular basis. In health care domain,
the medical data of numerous patients collected, forms Big Data. This Big Data can
be analyzed to build better health profiles and better predictive models around
individual patients so that efficient diagnosis and treatment can be provided.
Previously the analysis was difficult due to the manual collection of patient records
but due to digitization of records this process is made simple.
Existing technologies, do not take into consideration large dataset for
prediction of Parkinson’s Disease (PD). This leads to shortcomings in terms of
accuracy and execution time. The idea of the proposed system is to generate Big
Data on PD by taking into parameters that fall within specified ranges which is
used as input. The data is preprocessed to eliminate records with missing values
and outliers. This preprocessed data is given as an input to the classifier consisting
of DecisionTree (DT), Artificial Neural Network (ANN) and Support Vector
Machine (SVM) which compares the accuracy and execution time.
iii
TABLE OF CONTENTS
ABSTRACT ................................................................................................................................... iii
LIST OF TABLES ...................................................................................................................... vi
LIST OF FIGURES ................................................................................................................... 4ii
1 INTRODUCTION .................................................................. Error! Bookmark not defined.

1.1 Motivation ................................................................................................................................. 4
1.2 Hardware and Software Requirements ...................... Error! Bookmark not defined.
1.2.1 Software Requirements ................................................. Error! Bookmark not defined.
1.2.2 Hardware Requirements ............................................... Error! Bookmark not defined.
1.3 Organization of the Report .............................................. Error! Bookmark not defined.
2 LITERATURE SURVEY ................................................... Error! Bookmark not defined.
3 SYSTEM DESIGN ................................................................................................................ 14
4 MODULES FOR CPPD ...................................................................................................... 16
4.1 Data Generator ...................................................................................................................... 16

4.2 Data Preprocessor ................................................................................................................ 16
4.3 Predictive Analytics Engine using Python ............................................................... 16
4.3.1 Artificial Neural Network ............................................................................................ 17
4.3.2 Decision Tree ..................................................................................................................... 17
4.3.3 Support Vector Machine ............................................................................................... 18
5 IMPLEMENTATION .......................................................................................................... 19
5.1 Data Generator ...................................................................................................................... 19

5.2 Data Preprocessor ................................................................................................................ 24
5.3 Predictive Analytics Engine using Python ............................................................... 26
5.3.1 Installation of Virtual Machine of Ubuntu……………………………….27
5.3.2 Decision Tree ..................................................................................................................... 33
5.3.3 Artificial Neural Networks .......................................................................................... 36
5.3.4 Support Vector Machine ............................................................................................... 40
2
6 PERFORMANCE ANALYSIS ....................................................................................... 45
6.1 Impact of Preprocessing.................................................................................................... 45

7 CONCLUSIONS .................................................................................................................... 51
REFERENCES ……………………………………………………………...52
APPENDIX 1…………………………………………………………………………………….53
APPENDIX 2…………………………………………………………………………………….59
LIST OF TABLES
5.1 Values in each of the attribute that decides the range for populating
the dataset. ............................. 21
5.2 Conditions of combinations of the attributes that help in populating
the dataset. ............................. 22
6.1 Comparison of accuracy and execution time of ANN algorithm. . 47
6.2 Comparison of accuracy and execution time of DT algorithm. . . . 48
6.3 Comparison of accuracy and execution time of SVM algorithm. . 50
4
LIST OF FIGURES
3.1 Competent Predictor of Parkinson’s Disease(CPPD) . . . . . . . . 15
5.1 The Generated Dataset ....................... 24
5.2 Dataset with Outliers . . . . . . . . . . . . . . . . . . . . . . . . 25
5.3 Dataset without Outliers ...................... 26
5.4 Execution Time and Accuracy of Decision Tree . . . . . . . . . . 36
5.5 Execution Time and Accuracy of ANN . . . . . . . . . . . . . . . 40
5.6 Execution Time and Accuracy of SVM . . . . . . . . . . . . . . . 44
6.1 Accuracy and execution time before Preprocessing for
ANN Algorithm ………………………………………………. 46
6.2 Accuracy and execution time after Preprocessing for ANN 46
Algorithm…………………………………………………….
6.3 Accuracy and execution time before Preprocessing for DT 47
Algorithm………………………………………………………..
6.4 Accuracy and execution time after Preprocessing for DT 48
algorithm ……………………………………………………….
6.5 Accuracy and execution time before Preprocessing for SVM 49
Algorithm……………………………………………………….
6.6 Accuracy and execution time after Preprocessing for SVM 49
Algorithm………………………………………………………

Parkinson'S Brain Disease Prediction Using Descriptive Analysis

Uploaded by

Copyright:

Available Formats

Parkinson'S Brain Disease Prediction Using Descriptive Analysis

Uploaded by

Document Information

Original Description:

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Parkinson'S Brain Disease Prediction Using Descriptive Analysis

Uploaded by

Copyright:

Available Formats

PARKINSON’S BRAIN DISEASE PREDICTION USING

in partial fulfillment for the award of the degree

RAJALAKSHMI ENGINEERING COLLEGE

Certified that this project report“PARKINSON’S BRAIN DISEASE

Submitted to Project and Viva Examination held on __________.

Internal Examiner External Examiner

I extend my gratitude to my Chairman Mr.S.MEGANATHAN, B.E.,F.I.E.,

LIST OF FIGURES ................................................................................................................... 4ii

1 INTRODUCTION .................................................................. Error! Bookmark not defined.

4 MODULES FOR CPPD ...................................................................................................... 16

4.1 Data Generator ...................................................................................................................... 16

5.1 Data Generator ...................................................................................................................... 19

6 PERFORMANCE ANALYSIS ....................................................................................... 45

6.1 Impact of Preprocessing.................................................................................................... 45

You might also like