Klasifikasi Balita Terkait Kasus Stunting Di Kota Surabaya Menggunakan Classification And Regression Trees (CART) dengan Adaptive Synthetic Nominal (ADASYN-N) dan Adaptive Synthetic K-Nearest Neighbor (ADASYN-kNN)

Insyroh, Winantri Nurbuwah (2020) Klasifikasi Balita Terkait Kasus Stunting Di Kota Surabaya Menggunakan Classification And Regression Trees (CART) dengan Adaptive Synthetic Nominal (ADASYN-N) dan Adaptive Synthetic K-Nearest Neighbor (ADASYN-kNN). Other thesis, Institut Teknologi Sepuluh Nopember.

[thumbnail of 06211640000034-Undergraduate_Thesis.pdf]
Preview
Text
06211640000034-Undergraduate_Thesis.pdf

Download (1MB) | Preview

Abstract

Stunting merupakan masalah gizi kronis yang disebabkan oleh defisiensi nutrien selama seribu hari pertama kehidupan yang menyebabkan penurunan kemampuan kognitif dan motorik serta penurunan performa kinerja fisik. Jumlah balita stunting di Indonesia kini mencapai 27,67 persen. Kemudian di Jawa Timur, pada tahun 2019, terdapat 32,8 persen kasus balita stunting. Sedangkan di Surabaya, angka stunting hampir mendekati 30 persen. Untuk mengurangi angka stunting, perlu diketahui faktor apa saja yang dapat mengindikasikan terjadinya stunting pada balita. Pada penelitian ini dilakukan klasifikasi terhadap faktor-faktor yang diduga menyebabkan kasus stunting pada balita di Kota Surabaya menggunakan metode klasifikasi CART. Data merupakan data sekunder yang diperoleh dari Dinas Kesehatan Kota Surabaya. Data pada penelitian ini merupakan data imbalance sehingga dilakukan penanganan data imbalance dengan ADASYN-N dan ADASYN-kNN. Kesimpulan yang dihasilkan pada penelitian ini adalah metode ADASYN-N memiliki nilai AUC lebih baik dibanding metode ADASYN-kNN, sehingga hasil dari klasifikasi faktor-faktor yang mengindikasikan terjadinya stunting pada balita di Kota Surabaya berdasarkan metode terbaik adalah tinggi badan balita dibandingkan umur, ketersediaan jamban, dan tidak adanya anggota keluarga yang merokok di dalam rumah.
====================================================================================================================
Stunting is a chronic nutritional problem caused by nutrient deficiency during the first thousand days after birth which causes a decrease in cognitive and motoric skills and decreased physical performance. The number of toddlers who suffer from stunting in Indonesia has now reached 27,67%. Then in East Java, in 2019, there were 32,8% of the similar cases. Whereas in Surabaya, the stunting rate come near to 30%. To reduce those type of cases, it is necessary to know what kind factors that can be used to predict stunting in toddlers. In this study the classification of the factors suspected to predict stunting cases in toddlers in Surabaya was carried out using the CART classification method. Data that used in this study are the secondary data obtained from the Surabaya City Health Office. The data in this study are imbalance data so that the handling of imbalance data is carried out with ADASYN-N and ADASYN-kNN. The conclusion generated in this study is the ADASYN-N method has a better AUC value than the ADASYN-kNN method, so the result of the classification of factors that indicate stunting in toddlers in Surabaya based on the best method are the height compared to age, availability of latrines, and absence of family members who smoke inside the house.

Item Type: Thesis (Other)
Uncontrolled Keywords: ADASYN-kNN, ADASYN-N, CART, Stunting, Toddler, ADASYN-kNN, ADASYN-N, Balita, CART, Stunting
Subjects: H Social Sciences > HD Industries. Land use. Labor > HD108 Classification (Theory. Method. Relation to other subjects )
Divisions: Faculty of Science and Data Analytics (SCIENTICS) > Statistics > 49201-(S1) Undergraduate Thesis
Depositing User: Winantri Nurbuwah Insyroh
Date Deposited: 25 Aug 2020 05:31
Last Modified: 26 Dec 2023 15:25
URI: http://repository.its.ac.id/id/eprint/81099

Actions (login required)

View Item View Item