Search for collections on Repository Universitas Sulawesi Barat

IMPLEMENTASI ALGORITMA IMPROVED K-NEAREST NEIGHBOUR UNTUK KLASIFIKASI PENYAKIT KARDIOVASKULER IMPLEMENTATION OF THE IMPROVED K-NEAREST NEIGHBOUR ALGORITHM FOR CARDIOVASCULER DISEASES CLASSIFICATION

MUH TASLIM, MUH TASLIM (2025) IMPLEMENTASI ALGORITMA IMPROVED K-NEAREST NEIGHBOUR UNTUK KLASIFIKASI PENYAKIT KARDIOVASKULER IMPLEMENTATION OF THE IMPROVED K-NEAREST NEIGHBOUR ALGORITHM FOR CARDIOVASCULER DISEASES CLASSIFICATION. Diploma thesis, UNIVERSITAS SULAWESI BARAT.

[thumbnail of SKRIPSI_MUH TASLIM D0220021. .pdf] Text
SKRIPSI_MUH TASLIM D0220021. .pdf
Restricted to Repository staff only

Download (6MB)
[thumbnail of SKRIPSI_MUH TASLIM D0220021. (pdf.io).pdf] Text
SKRIPSI_MUH TASLIM D0220021. (pdf.io).pdf

Download (2MB)

Abstract

Penyakit jantung merupakan penyebab utama kematian di dunia, dengan tingkat privalensi yang terus meningkat setiap tahunnya. Deteksi dini menjadi salah satu langkah krusial dalam upaya pencegahan dan penanganan penyakit ini. Penelitian ini bertujuan untuk mengimplementasikan Improved K-Nearest Neingbour dalam sistem klasifikasi kardiovaskuler dengan memanfaatkan 17 fitur yang mempengaruhi kesehatan jantung. Data yang digunakan berasal dari center for disease control and prevention (CDC) tahun 2022, dengan total 10.000 data rekam medis yang dibagi rata antara antara pasien dengan penyakit jantung dengan tanpa penyakit jantung. Proses klasifikasi dilakukan dengan pembagian
data training dan testing dalam tiga skenario rasio, yakni 70:30, 80:20 dan 90:10. Evaluasi model dilakukan menggunakan metric, confusion matrix, mencakup akurasi, presisi, recall, dan f1-score. Hasil pengujian menunjukkan bahwa algoritma Improved K-Nearest Neighbour mampu memberikan performa klasifikasi yang tinggi, dengan akurasi tertinggi mencapai 93%. Temuan ini mengidentifikasikan bahwa pendekatan yang digunakan efektif dalam mendeteksi penyakit jantung berdasarkan data yang tersedia. Penelitian ini diharapkan dapat berkontribusi dalam pengembangan sistem pendukung keputusan medis berbasis data dan teknologi kecerdasan buatan.
Cardiovascular disease is a leading couse of death worldeide, with a steadily increasing prevalence each year. Early detectionis acrucial step in the prevention and management of thiscondition. Thisstudy aims to implement the Improved Knn algorithm for the classification of cardiovascular disease using 17 health-related features. The dataset used was obtained from the 2022 annual survey conducted bye the Center for Disease Control and Prevention (CDC), constingting of 10.000 medical records split between individuals diagnosed with heart disease and those without. The classification process was evaluated using three training-testing data rations : 70:30, 80:20, and 90:10. Model performance was assessed through confusion matrix metrics including accuracy, precision, recall, and f1-score. Experimental result demonstrated that the Improved KNearest Neighbour algorithm achieved excellent classification performance, with the highest accuracy reaching 93%. these findings indicate the effectiveness of the proposed approach in detecting cardiovascular disease based on the given
dataset. The research is expected to contributed to the development of data-diven decision support system in the medical domain, particulary for heart disease detection.

Item Type: Thesis (Diploma)
Uncontrolled Keywords: klasifikasi, penyakit jantung, algoritma Improved K- Nearest Neighbour, data mining, mechine learning. classification, heart disease, Improved K-Nearest Neighbour algorithm, data mining, machine learning.
Subjects: FAKULTAS TEKNIK > Informatika
Divisions: Fakultas Teknik
Depositing User: Unnamed user with email aryatiunsulbar@gmail.com
Date Deposited: 28 Jul 2025 02:26
Last Modified: 28 Jul 2025 02:26
URI: https://repository.unsulbar.ac.id/id/eprint/2179

Actions (login required)

View Item
View Item