CLASSIFICATION OF NUTRITIONAL STATUS USING K-NEAREST NEIGHBOR (KNN) METHOD

Authors

  • Lina Fauziah Universitas Sains Al-Qur’an
  • Hidayatus Sibyan Universitas Sains Al-Qur'an
  • Nur Hasanah Universitas Sains Al-Qur'an
  • Iman Ahmad Ihsannudin Universitas Sains Al-Qur'an
  • Nulngafan Universitas Sains Al-Qur'an

DOI:

https://doi.org/10.58641/cest.v1i2.38

Keywords:

Classification, K-Nearest Neighbor (KNN), Stunting, Toddler Nutrition

Abstract

According to a statement from the chairman of the Ngadimulyo village cadres, the prevalence of stunting in five-year-old babies (toddlers) in Ngadimulyo village in 2022 is 20%, which means there are 32 stunted toddlers out of 160 toddlers in Ngadimulyo village. The first 1000 days are the golden age for babies, but many toddlers aged 0-59 months still experience nutritional problems. In interviews with several mothers in Ngadimulyo village who have toddlers, many mothers still do not understand the calculation of nutritional status; they only rely on calculations from posyandu cadres recorded in the MCH book (Maternal and Child Health). Data recording is still conventional and produces physical data in the form of books, so data storage also has many risks, such as damage and loss. To reduce the risk of stunting, a system is needed that facilitates the calculation of under-five nutrition so that parents can independently calculate the nutritional status of their under-fives. Currently, many parents are still assisted in determining stunting criteria. Currently, parents only get stunting knowledge from counseling, so parents who have toddlers do not understand to analyze stunting symptoms independently. They are unaware if stunting occurs; therefore, with a system that can assist parents in calculating stunting rates, it is hoped that parents can provide maximum nutritional intake so that stunting cases decrease. Parents can also prevent stunting from occurring. One of the systems used to calculate the nutritional status classification of toddlers is the K-Nearest Neighbor Method (KNN). The reason for choosing the KNN method is because this method can meet other variables in determining the nutritional status of toddlers and is one of the most basic and simple grouping techniques.

References

Hidayat, M. S., & Pinatih, G. N. I. (2017). Prevalensi stunting pada balita di wilayah kerja Puskesmas Sidemen Karangasem. E-Jurnal Medika, 6(7), 1-5.

La Ode Alifariki, S. K. (2020). Gizi Anak dan Stunting. Penerbit LeutikaPrio.

Liantoni, F. (2016). Klasifikasi Daun Dengan Perbaikan Fitur Citra Menggunakan Metode K-Nearest Neighbor. Jurnal ULTIMATICS, 7(2), 98–104. https://doi.org/10.31937/ti.v7i2.356

Sibyan, H., & Hasanah, N. (2022). ANALISIS SENTIMEN ULASAN PADA WISATA DIENG DENGAN ALGORITMA K-NEAREST NEIGHBOR (K-NN). Jurnal Penelitian dan Pengabdian Kepada Masyarakat UNSIQ, 9(1), 38-47.

Sidik, A. D. W. M., Kusumah, I. H., Suryana, A., Artiyasa, M., & Junfithrana, A. P. (2020). Gambaran Umum Metode Klasifikasi Data Mining. FIDELITY: Jurnal Teknik Elektro, 2(2), 34-38.

Downloads

Published

2023-04-29

Issue

Section

Articles