c

1. Performance Analysis of Support Vector Machine in
Diabetes Prediction
Vinod Jain
Assistant Professor, Department of Computer Engineering
Applications
GLA University , Mathura, India
Vinod.jain@gla.ac.in
(ORCHID-0000-0003-0260-7319)
Narendra Mohan
Assistant Professor, Department of Computer Engineering
Applications
GLA University , Mathura, India
narendra.mohan@gla.ac.in
(ORCHID- 0000-0002-7037-3318)
Abstract—Lots of people are suffering from diabetes in India.
The disease is very serious and cause many other problems in
human body. Many factors are cause of this disease in human
body. The disease is not curable and can only be controlled. In
this paper Support Vector Machine learning algorithm is applied
in prediction of diabetes. The performance of SVM algorithm is
analyzed for different available kernels. The best kernel is
selected and used for prediction. The proposed work is
implemented in python programming language and its
performance is found good as compared to other algorithms.
Keywords—Machine Learning; Support Vector Machine;
Diabetes Prediction
I. INTRODUCTION
Diabetes is a very common disease in India now a day. The
life of diabetic patient is not easy at all. According to WHO
there were almost 31.7 million diabetic patients in India in the
year 2000 and it may goes to 79.4 million by 2030. Figure 1 is
showing the WHO data of diabetic patients in India. There is a
need to control this disease in India.
Fig. 1. WHO report on diabetes
Machine learning algorithm are mathematical techniques
which are very useful in analyzing large amount of data and
suggesting some actions on the basis of that data. These
algorithms are also very useful in analyzing a data set and
predicting values for a new entry. Many researchers [1][5][6]
are applying machine learning algorithms for prediction and
control of various diseases. The results of machine learning
algorithms found very good in prediction of different diseases.
II. LITERATURE SURVEY
J. Neelaveni and M. S. G. Devasana [1] applied machine
learning for Alzheimer prediction. V. K. Yarasuri et al. [2]
proposed a machine leaning based model for Hepatitis
prediction. M. P. N. M. Wickramasinghe et al. [3] applied
machine learning algorithms for diet prediction. The system
was used for dietary prediction for kidney diseases. A. Maurya
et al. [4] also applied ML for recommending diet plan for
patients suffering from kidney disease prediction. V. Vats et al.
[5] proposed an approach for prediction of liver diseases using
machine learning.
A. Gavhane et al. [6] proposed a system for prediction of
heart diseases. The machine learning algorithms was used for
prediction of heart diseases. The accuracy of machine learning
algorithms was tested on a data set of heart diseases. S. K. J.
and G. S. [7] also applied machine learning based approach for
heart disease prediction.
Support Vector Machine (SVM) is a very popular machine
learning model. It works on supervised machine learning
model. In supervised machine learning model we have a
teacher and the model is trained on the instructions of a
teacher/critic. It is very useful in solving classification
problems.
A lot of other authors [8-17] also applied machine learning
algorithm in prediction and detection of various diseases.
Support Vector Machine is also applied by many researchers to
predict various diseases [14-17]. But there is a scope of
research to optimize the performance of SVM algorithm in
prediction of diabetes patients in Indian context. The next
section discusses the proposed work for diabetes detection
using SVM.

2. III. PROPOSED METHODOLOGY
This paper applied SVM machine learning algorithm in
diabetes prediction. The SVM algorithm is implemented in
python programming language and tested on a data set. The
SVM model is created using python programming language.
The dataset is divided into training set and testing set. Then the
SVM model is trained.
Fig. 2. Proposed Methodology
The model is trained on four different kernels available for
SVM and its prediction accuracies are calculated by testing set.
The SVM is tested on four kernels which are Linear kernel,
Polynomial kernel, Sigmoid Kernel and RBF kernel. The best
SVM kernel is selected and used for diabetes prediction. Figure
2 is showing the flowchart of the proposed model.
The proposed model is implemented in Python
programming language and tested on a data set of 768 patients.
The data set is freely available on Kaggle with the name Pima
Indians Diabetes Database for research. The data set is
available in the form of a CSV file which is best suited for
python programming language.
The accuracy of the SVM model depends on the selection
of a particular model. The available models are Linear model,
Polynomial model, RBF model and Sigmoid model. First the
SVM is trained and tested on different models.
IV. RESULTS ANALYSIS
The Table 1 is showing the accuracy of the SVM for
different available models such as Linear, Polynomial, RBF
and Sigmoidal. The accuracy is found maximum for RBF
model which is 82%.
TABLE I. Accuracy of different SVM kernels
SVM Kernel Accuracy
Linear 0.77
Polynomial 0.80
RBF 0.82
Sigmoid 0.69
Fig. 3. Comparison of prediction accuracy of SVM kernels
Figure 3 is showing the bar chart of the prediction accuracy
of SVM Kernels. It is observed that the prediction accuracy of
RBF kernel is maximum for SVM while predicting diabetes for
Indian patients.

3. V. CONCLUSION AND FUTURE SCOPE
This paper proposed a machine learning based model for
diabetes prediction. Support Vector Machine model is used in
diabetes prediction. The four kernels of the SVM are used for
prediction and their prediction accuracy is measured. It is
found that the RBF kernel best performs for the diabetes
prediction of Indian patients as its prediction accuracy is found
best among the four kernels. In future the RBF SVM kernel can
be tested in prediction of other diseases such as Cancer,
Thyroid etc.
REFERENCES
[1] J. Neelaveni and M. S. G. Devasana, "Alzheimer Disease Prediction
using Machine Learning Algorithms," 2020 6th International Conference
on Advanced Computing and Communication Systems (ICACCS),
Coimbatore, India, 2020, pp. 101-104.doi:
10.1109/ICACCS48705.2020.9074248
[2] V. K. Yarasuri, G. K. Indukuri and A. K. Nair, "Prediction of Hepatitis
Disease Using Machine Learning Technique," 2019 Third International
conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-
SMAC), Palladam, India, 2019, pp. 265-269.doi: 10.1109/I-
SMAC47947.2019.9032585
[3] M. P. N. M. Wickramasinghe, D. M. Perera and K. A. D. C. P.
Kahandawaarachchi, "Dietary prediction for patients with Chronic
Kidney Disease (CKD) by considering blood potassium level using
machine learning algorithms," 2017 IEEE Life Sciences Conference
(LSC), Sydney, NSW, 2017, pp. 300-303.doi:
10.1109/LSC.2017.8268202
[4] Maurya, R. Wable, R. Shinde, S. John, R. Jadhav and R. Dakshayani,
"Chronic Kidney Disease Prediction and Recommendation of Suitable
Diet Plan by using Machine Learning," 2019 International Conference
on Nascent Technologies in Engineering (ICNTE), Navi Mumbai, India,
2019, pp. 1-4. doi: 10.1109/ICNTE44896.2019.8946029
[5] V. Vats, L. Zhang, S. Chatterjee, S. Ahmed, E. Enziama and K. Tepe,
"A Comparative Analysis of Unsupervised Machine Techniques for
Liver Disease Prediction," 2018 IEEE International Symposium on
Signal Processing and Information Technology (ISSPIT), Louisville,
KY, USA, 2018, pp. 486-489.doi: 10.1109/ISSPIT.2018.8642735
[6] Gavhane, G. Kokkula, I. Pandya and K. Devadkar, "Prediction of Heart
Disease Using Machine Learning," 2018 Second International
Conference on Electronics, Communication and Aerospace Technology
(ICECA), Coimbatore, 2018, pp. 1275-1278.doi:
10.1109/ICECA.2018.8474922
[7] S. K. J. and G. S., "Prediction of Heart Disease Using Machine Learning
Algorithms.," 2019 1st International Conference on Innovations in
Information and Communication Technology (ICIICT), CHENNAI,
India, 2019, pp. 1-5.doi: 10.1109/ICIICT1.2019.8741465
[8] R. J. P. Princy, S. Parthasarathy, P. S. Hency Jose, A. Raj
Lakshminarayanan and S. Jeganathan, "Prediction of Cardiac Disease
using Supervised Machine Learning Algorithms," 2020 4th International
Conference on Intelligent Computing and Control Systems (ICICCS),
Madurai, India, 2020, pp. 570-575.doi:
10.1109/ICICCS48265.2020.9121169
[9] R. Atallah and A. Al-Mousa, "Heart Disease Detection Using Machine
Learning Majority Voting Ensemble Method," 2019 2nd International
Conference on new Trends in Computing Sciences (ICTCS), Amman,
Jordan, 2019, pp. 1-6. doi: 10.1109/ICTCS.2019.8923053
[10] S. Mohan, C. Thirumalai and G. Srivastava, "Effective Heart Disease
Prediction Using Hybrid Machine Learning Techniques," in IEEE
Access, vol. 7, pp. 81542-81554, 2019.doi:
10.1109/ACCESS.2019.2923707
[11] M. A. Alim, S. Habib, Y. Farooq and A. Rafay, "Robust Heart Disease
Prediction: A Novel Approach based on Significant Feature and
Ensemble learning Model," 2020 3rd International Conference on
Computing, Mathematics and Engineering Technologies (iCoMET),
Sukkur, Pakistan, 2020, pp. 1-5. doi:
10.1109/iCoMET48670.2020.9074135
[12] Pouriyeh, S. Vahid, G. Sannino, G. De Pietro, H. Arabnia and J.
Gutierrez, "A comprehensive investigation and comparison of Machine
Learning Techniques in the domain of heart disease," 2017 IEEE
Symposium on Computers and Communications (ISCC), Heraklion,
2017, pp. 204-207. doi: 10.1109/ISCC.2017.8024530
[13] Mir and S. N. Dhage, "Diabetes Disease Prediction Using Machine
Learning on Big Data of Healthcare," 2018 Fourth International
Conference on Computing Communication Control and Automation
(ICCUBEA), Pune, India, 2018, pp. 1-6.doi:
10.1109/ICCUBEA.2018.8697439
[14] M. Patil, V. B. Lobo, P. Puranik, A. Pawaskar, A. Pai and R. Mishra, "A
Proposed Model for Lifestyle Disease Prediction Using Support Vector
Machine," 2018 9th International Conference on Computing,
Communication and Networking Technologies (ICCCNT), angalore,
2018, pp. 1-6.doi: 10.1109/ICCCNT.2018.8493897
[15] S. R. Alty, S. C. Millasseau, P. J. Chowienczyc and A. Jakobsson,
"Cardiovascular disease prediction using support vector
machines," 2003 46th Midwest Symposium on Circuits and Systems,
Cairo, 2003, pp. 376-379 Vol. 1.doi: 10.1109/MWSCAS.2003.1562297
[16] S. Kaur and S. Kalra, "Disease prediction using hybrid K-means and
support vector machine," 2016 1st India International Conference on
Information Processing (IICIP), Delhi, 2016, pp. 1-6.doi:
10.1109/IICIP.2016.7975367
[17] R. S. Raj, D. S. Sanjay, M. Kusuma and S. Sampath, "Comparison of
Support Vector Machine and Naïve Bayes Classifiers for Predicting
Diabetes," 2019 1st International Conference on Advanced Technologies
in Intelligent Control, Environment, Computing & Communication
Engineering (ICATIECE), Bangalore, India, 2019, pp. 41-45.doi:
10.1109/ICATIECE45860.2019.9063792