Using data mining
technique, we have gained higher prediction accuracy to detect PD compared with
the existing methods. We have also successfully compared two different workbenches
with same classifiers to identify the best result produced by them. It has been
found that ensemble method gives 100% accuracy using IBM SPSS Modeller 18
workbench. This paper also shows that the ensemble method shows higher accuracy
than individual classifiers in the case of Parkinson dataset. Not all
classifiers show better accuracy for all datasets. Using the ensemble method,
all single classifiers are used with
eliminating their limitations. It is quite difficult to test each classifier
available in workbench to see their accuracy on a particular dataset. This
problem has been solved successfully with the help of auto classifier node
available in SPSS Modeller 18 workbench. We have used 10-fold cross-validation
for training and testing in both workbenches to compare them with the same used
technique. The difference between their accuracy indicates that the
implementation detail is different in each workbench. Classification model j48
in Weka is similar to C5.0 in IBM SPSS Modeller 18 but C5.0 is an updated
version than j48 which is also known as C4.5. Weka is an open source workbench
whereas IBM SPSS Modeller 18 is a DM modeller
from IBM. So, it is not possible to diagnosis each classifier used in both
workbenches. Thus we can say that the ensemble method gives higher accuracy to
distinguish PD patient and healthy people. However, with the help of feature
selection strategy, those fields which can degrade the performance or
unimportant for modelling can be removed
to generate ensemble method with higher accuracy.

References

1       
IpsitaBhattacharya , M.
P. S. Bhatia, SVM classification to distinguish Parkinson disease patients,
Proceedings of the 1st Amrita ACM-W Celebration on Women in Computing in India,
Coimbatore, India, pp.1-6, 2010.

We Will Write a Custom Essay Specifically
For You For Only $13.90/page!


order now

2       
Parkinson.
Available: http://kidshealth.org/kid/grownup/conditions/parkinson.html.

3       
D. S. V.
G. K. Kaladhar, P. V. NageswaraRao, and N. R.B. L. V. Ramesh, Confusion
matrix analysis for evaluation of speech on Parkinson disease using Weka and
MatLab, International Journal of Engineering Science and Technology, 2(7),
pp. 2734-2737, 2010.

4       
Bakar, Z.A., Tahir, N.M. and Yassin, I.M., Classification
of Parkinson’s disease based on Multilayer Perceptrons Neural Network, 6th
International Colloquium on Signal Processing & Its Applications (CSPA),
pp.1-4, 2010.

5       
Tsanas A.,
Little M.A., McSharry P.E., Ramig L.O., Accurate telemonitoring of
Parkinson’s disease progression by non-invasive speech tests, IEEE Transactions
on Biomedical Engineering, 57(4), pp. 884-893, 2009.

6       
SchragA,
Ben-Shlomo Y, Quinn N., How valid is the clinical diagnosis of Parkinson’s
disease in the community?, Journal of Neurology, Neurosurgery &
Psychiatry, 73(5), pp. 529-534, 2002.

7       
Van Den Eeden, S.K., C. M. Tanner, et al., Incidence
of Parkinson’s disease: Variation by age, gender, and Race/Ethnicity,
American Journal of Epidemiology, 157 (11), 1015-1022, 2003.

8       
Elbaz A, Bower JH, Maraganore DM, McDonnell SK,
Peterson BJ, Ahlskog JE, Schaid DJ, Rocca WA, Risk tables for parkinsonism
and Parkinson’s disease, Journal of Clinical Epidemiology, 55(1), pp.25-31,
2002.1       
 2       
Motor and Non-motor symptoms. Available: http://www.pdf.org/symptoms_primary.3       
Parkinson disease. Available: https://en.wikipedia.org/wiki/Parkinsons_disease.4       
Symptoms of autonomic dysfunction. Available: http://www.healthline.com/health/autonomic-dysfunction#Symptoms2.5       
 NIH:
National Institute of Neurological Disorders and Stroke. Available: http://www.ninds.nih.gov/disorders/parkinsons_disease/parkinsons_disease.htm.6       
King J. B., Ramig L.O., Lemke J.H. and Horii Y,
Parkinson’s disease: Longitudinal changes in acoustic parameters of
phonation, Journal of Medical Speech-Language Pathology, 2, pp. 29– 42,
1994.7       
Little M.A., McSharry P.E., Hunter E.J.,
Spielman, J., Ramig L.O., Suitability of dysphonia measurements for
telemonitoring of Parkinson’s disease, IEEE Transactions on Biomedical
Engineering, 2008.8       
Han and Kamber, Data mining concepts and
techniques, 2nd ed, Springer Verlag, 2006.9       
Alaa M. Elsayad,
Diagnosis of Erythemato-Squamous
Diseases using Ensemble of Data Mining Methods, ICGST-BIME Journal, 10(1),
pp. 13-23, 2010.10   
NorsariniSalim, Medical Diagnosis Using
Neural Networks, Available: http://www.generation5.org/content/2004/MedicalDiagnosis.asp.11   
Shelly Gupta, Dharminder Kumar, Anand Sharma, Data
Mining Classification Techniques Applied For Breast Cancer Diagnosis And Prognosis,
Indian Journal Of Computer Science And Engineering 2(2), pp. 188-195, 2011.12   
UCI: Machine Learning Repository. Available: http://archive.ics.uci.edu/ml.13   
Ozisikyilmaz, B., Narayanan, R., Zambreno, J., Memik, G. and Choudhary, A., An
architectural characterization study of data mining and bioinformatics
workloads, IEEE International Symposium on Workload Characterization
(IISWC), pp. 61-70, 2006.14   
Md. Inzamam-Ul-Hossain, Lachlan MacKinnon and Md. Rafiqul Islam, Parkinson Disease
Detection Using Ensemble Method in PASW Modeler, Presented at 2015 IEEE
International Advance Computing Conference, Bangalore, India, 12-13 June, 2015.15   
IBM SPSS PASW 18 Modeler. Available: http://www-01.ibm.com/software/analytics/spss/products/modeler/.16   
K-fold cross-validation in IBM SPSS Modeler.
Available at: https://developer.ibm.com/predictiveanalytics/2016/03/02/k-fold-cross-validation-ibm-spss-modeler.17   
Alaa M. Elsayad,
Diagnosis of Breast Tumor using Boosted Decision Trees, ICGST-AIML
Journal, 10(1), pp. 01-11 , 2010.18   
Islam, M.S., Parvez, I.,Hai Deng and Goswami, P., Performance Comparison of
Heterogeneous Classifiers for Detection of Parkinson’s Disease Using Voice
Disorder (Dysphonia), 3rd International Conference on
Informatics, Electronics and Vision, pp. 1-7, 2014.19   
A. David Gill and B. Magnus Johnson, Diagnosing
Parkinson by using Artificial Neural Network and Support Vector Machines,
Global Journal of Computer Science and technology, vol. 9, pp. 63- 71, 2009.20   
Tarigoppula V.S Sriram, M. VenkateswaraRao, G V SatyaNarayana , DSVGK Kaladhar, T PanduRanga
Vital, Intelligent Parkinson Disease Prediction Using Machine Learning
Algorithms, International Journal of Engineering and Innovative Technology
(IJEIT), 3(3), 2013.21   
Indira Rustempasic, Mehmet Can, Diagnosis of
Parkinson’s Disease using Principal Component Analysis and Boosting Committee
Machines,  Southeast Europe Journal
of Soft Computing, 2(1), pp. 102-109, 2013.22   
Breiman L, Friedman JH, Olshen RA, Stone CJ., Classification
and Regression Trees, Wadsworth Statistics/Probability Series. Wadsworth
Advanced Books and Software, Belmont, CA, 1984.23   
Rick L. Lawrence and Andrea Wright, Rule-Based
Classification Systems Using Classification and Regression Tree (CART) analysis,
Photogrammetric Engineering & Remote Sensing, 67(10), pp. 1137-1142, 2001.24   
Statsoft:
Popular Decision Tree: Classification and Regression Trees. Available: http://www.statsoft.com/textbook/classification-and-regression-trees/?button=1.25   
Witten, I. H., Frank, E. and Hall M. A., Implementations:
Real Machine Learning Schemes, in Data Mining: Practical Machine Learning Tools
and Techniques, 3rd ed, Morgan Kaufmann, USA, pp.-261-272, 2011.26   
Comparison between C5.0 and C4.5. Available: http://rulequest.com/see5-comparison.html.27   
L. Rokach, Ensemble-based classifiers,
Artificial Intelligence Review, 33(1-2), pp. 1-39, 2010.28   
Ida Moghimipour & Malihe Ebrahimpour, Comparing
Decision Tree Method Over Three Data Mining Software, International Journal
of Statistics and Probability, 3(3), 2014.29   
Weka 3: Data Mining Software in Java.
Available: http://www.cs.waikato.ac.nz/ml/weka/.30   
Frank E, Hall M, Trigg L, Holmes G, Witten IH, Data
mining in bioinformatics using Weka, Bioinformatics, 20(15): pp. 2479–2481,
2004.31   
Christine M. Bronikowski, Angela Weng, Jacob D.
Furst, Daniela S. Raicu, Prediction of chronic fatigue syndrome using
decision tree-based ensemble methods, Presented at International Conference
on Artificial Intelligence, Las Vegas, NV, 2011.32   
Voice Acoustics. Available: http://newt.phys.unsw.edu.au/jw/voice.html.33   
Selwyn Piramuthu, Evaluating feature
selection methods for learning in data mining applications, European
journal of operational research, 156(2), pp. 483-494, 2004.34   
Sunita Beniwal, Jitender Arora, Classification
and Feature Selection Techniques in Data Mining, International Journal of
Engineering Research and Technology (IJERT), 1(6), pp. 1-6, 2012.35   
M. Ramaswami and R. Bhaskaran, A Study on
Feature Selection Techniques in Educational Data Mining, Journal of
Computing, 1(1), pp.7-11, 2009.

36   
H. Liu, H. Motoda, R. Setiono and Z. Zhao, Feature Selection: An ever evolving frontier in data mining,
Journal of Machine Learning Research, 10, pp. 4-13, 2010.

Categories: Articles

x

Hi!
I'm Garrett!

Would you like to get a custom essay? How about receiving a customized one?

Check it out