ANALISIS PERBANDINGAN PREDIKSI PENYAKIT DIABETES MENGGUNAKAN ALGORITMA LOGISTIC REGRESSION DAN K-NEAREST NEIGHBOR

MUHAMMAD FAJAR ISLAM IMAN MUJAHID, . (2025) ANALISIS PERBANDINGAN PREDIKSI PENYAKIT DIABETES MENGGUNAKAN ALGORITMA LOGISTIC REGRESSION DAN K-NEAREST NEIGHBOR. Sarjana thesis, UNIVERSITAS NEGERI JAKARTA.

	Text Cover.pdf Download (2MB)
	Text Bab 1.pdf Download (858kB)
	Text Bab 2.pdf Restricted to Registered users only Download (1MB) | Request a copy
	Text Bab 3.pdf Restricted to Registered users only Download (1MB) | Request a copy
	Text Bab 4.pdf Restricted to Registered users only Download (2MB) | Request a copy
	Text Bab 5.pdf Restricted to Registered users only Download (841kB) | Request a copy
	Text Daftar Pustaka.pdf Download (484kB)
	Text Lampiran & Riwayat Hidup.pdf Restricted to Registered users only Download (2MB) | Request a copy

Abstract

Penyakit diabetes merupakan salah satu penyakit kronis yang prevalensinya terus meningkat setiap tahun, baik secara global maupun nasional. Dalam upaya mendeteksi diabetes secara dini, pemanfaatan teknologi machine learning menjadi salah satu alternatif yang menjanjikan. Penelitian ini bertujuan untuk menganalisis dan membandingkan performa algoritma Logistic Regression dan K-Nearest Neighbor (KNN) dalam klasifikasi data diabetes. Dataset yang digunakan diperoleh dari National Institute of Diabetes and Digestive and Kidney Diseases melalui platform Kaggle, yang terdiri dari delapan atribut gejala pasien dan satu atribut target (outcome). Proses penelitian dimulai dengan tahap preprocessing data, dilanjutkan dengan penerapan masing-masing algoritma baik sebelum maupun sesudah dilakukan hyperparameter tuning. Pada Logistic Regression, parameter yang dituning mencakup lambda, solver, dan maximum iteration, sedangkan pada KNN, parameter yang diujikan meliputi jumlah tetangga (k), uniform, dan parameter jarak. Evaluasi performa model dilakukan dengan menggunakan metrik akurasi, precision, recall. Hasil penelitian menunjukkan bahwa setelah dilakukan hyperparameter tuning, algoritma Logistic Regression menghasilkan akurasi sebesar 84% sedangkan KNN mencapai akurasi sebesar 81,43%. Temuan ini mengindikasikan bahwa pilihan parameter berpengaruh signifikan terhadap performa model. Oleh karena itu, pemilihan dan pengujian berbagai kombinasi parameter sangat penting dalam proses perancangan sistem klasifikasi penyakit berbasis machine learning.****Diabetes is one of the chronic diseases whose prevalence continues to increase every year, both globally and nationally. In an effort to detect diabetes early, the use of machine learning technology has become a promising alternative. This study aims to analyze and compare the performance of the Logistic Regression and K-Nearest Neighbor (KNN) algorithms in classifying diabetes data. The dataset used was obtained from the National Institute of Diabetes and Digestive and Kidney Diseases via the Kaggle platform, consisting of eight patient symptom attributes and one target attribute (outcome). The research process began with the data preprocessing stage, followed by the application of each algorithm both before and after hyperparameter tuning. In Logistic Regression, the parameters tuned included lambda, solver, and maximum iteration, while in KNN, the parameters tested included the number of neighbors (k), uniformity, and distance parameters. Model performance was evaluated using accuracy, precision, and recall metrics. The results show that after hyperparameter tuning, the Logistic Regression algorithm produced an accuracy of 84%, while KNN achieved an accuracy of 81.43%. These findings indicate that parameter selection has a significant effect on model performance. Therefore, selecting and testing various parameter combinations is very important in the process of designing a machine learning-based disease classification system.

Item Type:	Thesis (Sarjana)
Additional Information:	1). Ali Idrus, M.Kom. ; 2). Lipur Sugiyanta, Ph.D.
Subjects:	Sains > Matematika > Ilmu Komputer Sains > Matematika > Software, Sistem Informasi Komputer Teknologi dan Ilmu Terapan > Teknik Komputer
Divisions:	FT > S1 Sistem dan Teknologi Informasi
Depositing User:	Users 28306 not found.
Date Deposited:	04 Aug 2025 03:17
Last Modified:	04 Aug 2025 03:17
URI:	http://repository.unj.ac.id/id/eprint/57123

Actions (login required)

View Item