DIABETES DIAGNOSIS BASED ON KNN

Authors

DOI:

https://doi.org/10.31436/iiumej.v21i1.1206

Keywords:

Diabetes, KNN, Classification and Machine learning

Abstract

Diabetes is a life-threatening syndrome occurring around the world; it can have huge complications and is documented by large amounts of medical data. Therefore, attempts at early detection of this disease took a large area of research and many methods were used to deal with diabetes. In this paper, different types of KNN algorithm have been used to classify diabetes disease using Matlab. The dataset was generated by the criteria of the American diabetes association. For the training stage, 4900 samples have been used by the classifier learner tool to observe the results. Then, 100 of the data samples were used for the test. The results show that the KNN types (Fine, Weighted, Medium and Cubic) give high accuracy over the Coarse and the Cosine methods. Fine KNN is considered the most suitable according to its accuracy of classified samples.

ABSTRAK: Penyakit kencing manis adalah sindrom penyakit ancaman nyawa yang berlaku di seluruh dunia dan ia mempunyai data perubatan yang besar serta komplikasi tinggi. Oleh itu, cubaan dalam mengesan awal penyakit ini mempunyai potensi luas dalam kajian dan banyak kaedah telah digunakan bagi mengkaji penyakit kencing manis. Dalam kajian ini, pelbagai jenis algoritma KNN telah digunakan bagi mengelas penyakit kencing manis menggunakan Matlab. Setdata dihasilkan berdasarkan kriteria Kesatuan Kencing Manis Amerika. Pada peringkat latihan, sebanyak 4900 sampel telah digunakan oleh pelatih alat pengelasan bagi memantau dapatan kajian. Kemudian, 100 daripada sampel data telah digunakan bagi ujian. Keputusan menunjukkan jenis KNN (Halus, Berat, Sederhana dan Kubik) lebih tepat berbanding kaedah Kasar dan Kosinus. KNN Halus di dapati lebih sesuai berdasarkan ketepatan sampel pengelasan.

Downloads

Download data is not yet available.

References

T.Karthikeyan, K.Vembandadsamy. (2015). An Analytical Study on Early Diagnosis and Classification of Diabetes Mellitus. International Journal of Computer Application,7:2250-1797.

Catherine C. Cowie, Keith F. Rust,Danita D. Byrd-Holt, Edward W. Gregg, Earl S. Ford, Linda S. Geiss, Kathleen E. Bainbridge, Judith E. Fradkin. (2010). Prevalence of diabetes and high risk for diabetes using A1C criteria in the US population in 1988–2006. Diabetes care, 33: 562-568.

V. Anuja Kumari, R.Chitra. (2013). Classification Of Diabetes Disease Using Support Vector Machine. International Journal of Engineering Research and Applications,3:1797-1801.

Longfei Han, Beijing, Senlin Luo, Jianmin Yu, Limin Pan, Songjing Chen. (2013) Rule Extraction from Support Vector Machines Using Ensemble Learning Approach: An Application for Diagnosis of Diabetes. IEEE,19:2168-2194.

Nahla H. Barakat, Andrew P. Bradley, Mohamed Nabil H. Barakat (2010). Intelligible Support Vector Machines for Diagnosis of Diabetes Mellitus. IEEE,40:2168-2194.

Subhankar Manna, Malathi G. (2017). Performance Analysis Of Classification Algorithm On Diabetes Healthcare Dataset. International Journal of Research - Granthaalayah,5:260-266.

Aiswarya Iyer, S. Jeyalatha, Ronak Sumbaly (2015). Diagnosis Of Diabetes Using Classification Mining Techniques. International Journal of Data Mining & Knowledge Management Process (IJDKP),5:1-14.

Theodora S. Brisimi, Tingting Xu, Taiyao Wang, Wuyang Dai, William G. Adams , Ioannis Ch. Pasc halidis(2018). Predicting Chronic Disease Hospitalizations from Electronic Health Records: An Interpretable Classification Approach. IEEE,106:1-18.

Bum Ju Lee, Boncho Ku, Jiho Nam, Duong Duc Pham, Jong Yeol Kim (2014). Prediction of Fasting Plasma Glucose Status Using Anthropometric Measures for Diagnosing Type 2 Diabetes. IEEE,18:555-561.

Chang-Shing Lee, Senior Member, Mei-Hui Wang (2011) A Fuzzy Expert System for Diabetes Decision Support Application. IEEE,41:139-153.

Yuliang Liu, Quan Zhang, Geng Zhao, Zhigang Qu, Guohua Liu, Zhiang Liu, Yang An (2018). Detecting Diseases by Human-Physiological- Parameter-Based Deep Learning. IEEE,7: 2169-3536

Shichao Zhang, Xuelong Li,Ming Zong, Xiaofeng Zhu, Ruili Wang (2017). Efficient kNN Classification With Different Numbers of Nearest Neighbors. IEEE,29:1-12.

Mehdi Zekriyapanah gashti (2018). A Modified Model Based on Flower Pollination Algorithm and K-Nearest Neighbor for Diagnosing Diseases. IIUM Engineering Journal, 19:144-157.

Jenifer Mariam Johnson and Anamika Yadav(2016). Fault detection and classification technique for HVDC transmission lines using KNN, Second International Conference on ICT for Sustainable Development, Goa, 1-2 July 2016.

Jaime Vitola , Francesc Pozo, Diego A. Tibaduiza, Maribel Anaya (2017). A Sensor Data Fusion System Based on k-Nearest Neighbor Pattern Classification for Structural Health Monitoring Applications. Sensors, 17.

Asad Hussain, Sajjad Ahmed Ghauri, M. Farhan Sohail,Sheraz A. Khan, Ijaz Mansoor Qureshi. (2016). KNN BASED CLASSIFICATION OF DIGITAL MODULATED SIGNALS. IIUM Engineering Journal, 17: 71-82.

American Diabetes Association (2014). Standards of Medical Care in Diabetes 2014 ,Diabetes Care 37: S14-S80.

Downloads

Published

2020-01-20

How to Cite

Ali, A., Alrubei, M. A. T. ., Hassan, . L. F. M., Al-Ja’afari, M. A. M., & Abdulwahed, . S. H. . (2020). DIABETES DIAGNOSIS BASED ON KNN. IIUM Engineering Journal, 21(1), 175 - 181. https://doi.org/10.31436/iiumej.v21i1.1206

Issue

Section

Engineering Mathematics and Applied Science