CD Skripsi

Perancangan Aplikasi Berbasis Machine Learning Metode Artificial Neural Network (Ann) Dan K-Nearest Neighbour (Knn) Untuk Mendeteksi Diabetes Menggunakan Resonator Mikrostrip

---

Globally, the number of diabetes sufferers is estimated to continue to increase. To measure glucose, blood needs to be drawn from the body. Invasive methods carry the risk of infection. Developing devices with non-invasive methods can reduce the risks of invasive methods. One way is to use machine learning. In this study, a comparison of the Artificial Neural Network (ANN) and K-Nearest Neighbor (KNN) methods was carried out to classify a person's type of diabetes by adding additional features from the resonator microstrip. The data used is 1000 data with 10 features and 1 output with 2 labels. The 10 features are gender, age, smoking habits, family history of diabetes, height, weight, Body Mass Index (BMI), frequency, return loss, and bandwidth. In the output there are 2 labels used, namely diabetes and non-diabetes. ANN and KNN both produced accuracies of 99% and 100% on their respective models. Using 20 classification data and 20 diabetes prediction data, ANN and KNN were able to validate the 40 data correctly.

Keywords: Diabetes, Non-invasive, Artificial Neural Network, K-Nearest
Neighbour, Resonator Mikrostrip.

---

Ketersediaan

Informasi Detail

Judul Seri

-

No. Panggil

2007113989

Penerbit

Pekanbaru : Universitas Riau - F. Teknik - Teknik Elektro., 2024

Deskripsi Fisik

-

Bahasa

Indonesia

ISBN/ISSN

-

Klasifikasi

2007113989

Tipe Isi

-

Tipe Media

-

Tipe Pembawa

-

Edisi

-

Subjek

TEKNIK ELEKTRO

Info Detail Spesifik

-

Pernyataan Tanggungjawab

Vina

Versi lain/terkait

Lampiran Berkas

Komentar

---

Anda harus masuk sebelum memberikan komentar