Analisis Perbedaan Ekg Pasien Diabetes Melitus Tipe 2 Dengan Orang Normal Menggunakan Metode Support Vector Machine (SVM)

Hidayat, Tsaabitah Rizqiina Putri (2025) Analisis Perbedaan Ekg Pasien Diabetes Melitus Tipe 2 Dengan Orang Normal Menggunakan Metode Support Vector Machine (SVM). Other thesis, Institut Teknologi Sepuluh Nopember.

Text 5026211124-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only Download (3MB) | Request a copy

Abstract

Penelitian ini bertujuan untuk menganalisis perbedaan sinyal Elektrokardiogram (EKG) antara pasien Diabetes Melitus Tipe 2 (T2DM) dan individu normal menggunakan metode Support Vector Machine (SVM). Data EKG yang digunakan diambil dari dataset Cerebral Perfusion and Cognitive Decline in Type 2 Diabetes, yang mencakup informasi dari dua kelompok, yaitu pasien diabetes dan individu sehat. Metode SVM digunakan untuk mengklasifikasikan perbedaan gelombang EKG pada kedua kelompok, dengan tiga jenis kernel yang diuji: Radial Basis Function (RBF), Polynomial, dan Linear. Hasil penelitian menunjukkan bahwa SVM dengan kernel Polynomial memberikan tingkat akurasi tertinggi, yaitu 95% pada perbandingan data 60:40 untuk leads V1, dan 91% untuk leads V5. Selain itu, teknik SMOTE diterapkan untuk menangani ketidakseimbangan data, sehingga model dapat lebih efektif dalam mengklasifikasikan kedua kelompok. Penelitian ini membuktikan bahwa metode SVM dapat diandalkan dalam membedakan EKG pasien T2DM dengan individu normal dan dapat diterapkan untuk deteksi dini diabetes serta pengelolaan kesehatan pasien secara lebih baik.
=======================================================================================================================
=============
This research aims to analyze the differences in Electrocardiogram (ECG) signals between Type 2 Diabetes Mellitus (T2DM) patients and normal individuals using the Support Vector Machine (SVM) method. The ECG data used were obtained from the Cerebral Perfusion and Cognitive Decline in Type 2 Diabetes dataset, which includes information from two groups: diabetic patients and healthy individuals. The SVM method was employed to classify the differences in ECG waves between the two groups, with three types of kernels tested: Radial Basis Function (RBF), Polynomial, and Linear. The results show that the SVM model with the Polynomial kernel achieved the highest accuracy, 95% for the 60:40 data split in leads V1, and 91% for leads V5. Additionally, the SMOTE technique was applied to address class imbalance, making the model more effective in classifying both groups. This study demonstrates that the SVM method is reliable in differentiating ECGs of T2DM patients from normal individuals and can be applied for early diabetes detection and better health management of patients.

Item Type:	Thesis (Other)
Uncontrolled Keywords:	Diabetes Mellitus Tipe 2, SVM , EKG, Diabetes Mellitus Type 2
Subjects:	T Technology > T Technology (General) > T57.8 Nonlinear programming. Support vector machine. Wavelets. Hidden Markov models.
Divisions:	Faculty of Intelligent Electrical and Informatics Technology (ELECTICS) > Information System > 57201-(S1) Undergraduate Thesis
Depositing User:	TsabitaRizqina Putri
Date Deposited:	25 Jul 2025 06:55
Last Modified:	25 Jul 2025 06:55
URI:	http://repository.its.ac.id/id/eprint/121698

Actions (login required)

View Item