Klasifikasi Kadar Kolesterol Menggunakan Ekstraksi Ciri Moment Invariant dan Algoritma K-Nearest Neighbor (KNN)

  • Sekar Arum Nurhusni Universitas Singaperbangsa Karawang
  • Riza Ibnu Adam Universitas Singaperbangsa Karawang
  • Carudin Carudin Universitas Singaperbangsa Karawang
Keywords: Classification, Cholesterol, KNN

Abstract

Cholesterol is a fat that is mostly formed by the body itself, especially in the liver. Cholesterol is very useful for the body but will be very dangerous if it has excessive levels. The impact of excessive cholesterol is the emergence of deadly diseases such as heart disease, stroke and poor blood circulation. In this study, one of the medical sciences that can be used to detect cholesterol levels is Iridology. This iridology itself can be applied in computer science which is often referred to as Digital Image Processing. In this case, the feature recognition method will be used using Moment Invariant feature extraction and the K-Nearest Neighbor Algorithm. Where the data used is the Dataset from Ubiris V1. With the resulting accuracy of 84,8485%.

Downloads

Download data is not yet available.

References

Murray, Robert K. 2009. Biokimia Harper. Jakarta : EGC.

Lyli, S. Sulistyawati. (2017). Penyakit Tidak Menular. Profil Penyakit Tidak Menular 2016. Jakarta : Kementerian Kesehatan RI.

Rani, H. A. D., Supriyati, E., & Khotimah, T. (2014). Deteksi Iris Mata untuk Menentukan Kelebihan Kolesterol menggunakan Ekstraksi Ciri Moment Invariant dengan K-Means Clustering. Prosiding SNATIF, 287-292.

Kurniawan, C. T. (2017). SISTEM PENDUKUNG KEPUTUSAN PENGELOMPOKAN STATUS KADAR KOLESTEROL MENGGUNAKAN ALGORITMA K-NEAREST NEIGHBOR (K-NN) DI PUSKESMAS ARJUNO. JATI (Jurnal Mahasiswa Teknik Informatika), 1(1), 135-143.

Waluya, D. P., Suhartono, E., & Safitri, I. Deteksi Kolesterol Menggunakan Citra Mata Berbasis Local Binary Pattern (LBP) Dan Support Vector Machine (SVM) Detection Of Cholesterol Using Eye Picture Based Local Binary Pattern (LBP) And Support Vector Machine (SVM).

Enjelica, R. (2019). Deteksi Kelebihan Kolesterol melalui Citra Iris Mata dengan Metoda Discrete Wavelet Transform dan Klasifikasi K-Nearest Neighbor. Universitas Telkom, Bandung.

Sari, Y. A., & Arwan, A. (2018). Seleksi Fitur Information Gain untuk Klasifikas i Penyakit Jantung Menggunakan Kombinasi Metode K-Nearest Neighbor dan Naïve Bayes Human Detection and Tracking View project Smart Nutritio n Box View project. Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer e-ISSN, 2548, 964X.

Kusumadewi, S. (2003). Artificial Intelligence (Teknik dan Aplikasinya). Yogyakarta: Graha Ilmu.

Andono, Pulung Nurtantio, Konsep Pengolahan Citra Digital, Ed. 1. Yogyakarta: Andi, (2015).

Whidhiasih, Retno Nugroho et al. 2013. Klasifikasi Buah Belimbing Berdasarkan Citra Red-Green-Blue Menggunakan KNN dan LDA. Jurnal Penelitian Ilmu Komputer Universitas Pakuan Bogor : 29-35.

Fahma ST MSc, 2007, Perancangan Algoritma Pengolahan Citra Mata Menjadi Citra Polar Iris Sebagai Bentuk Antara Sistem Biometrik, Universitas Sumatra Utara, Medan.

Farida Sachran, 2005, Iridology: A Complete Guide To Diagnosing Through the Iris And To Related Forms of Treatment, New York, USA.

Published
2021-12-10
How to Cite
[1]
S. Nurhusni, R. Adam, and C. Carudin, “Klasifikasi Kadar Kolesterol Menggunakan Ekstraksi Ciri Moment Invariant dan Algoritma K-Nearest Neighbor (KNN)”, JAIC, vol. 5, no. 2, pp. 169-175, Dec. 2021.
Section
Articles