Prediksi Infesi Saluran Pernafasan Akut (ISPA) Pada Anak Dibawah Lima Tahun Menggunakan Stacking Support Vector Machine (SVN)

Damayanti, Reynata Tri (2023) Prediksi Infesi Saluran Pernafasan Akut (ISPA) Pada Anak Dibawah Lima Tahun Menggunakan Stacking Support Vector Machine (SVN). Masters thesis, Institut Teknologi Sepuluh Nopember.

Text 6026211017-Master_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 April 2025. Download (1MB) | Request a copy

Abstract

Kesehatan anak pada usia awal kehidupan sangat rentan terhadap penyakit. Terdapat penyakit yang mengancam kematian pada anak yaitu Infeksi Saluran Pernafasan Akut (ISPA). ISPA merupakan infeksi akut pada saluran pernafasan bagian atas. Infeksi ini menyerang komponen saluran pernafasan bagian atas seperti hidung, sinus, faring, dan laring. Menurut World Health Organization (WHO), kematian anak akibat penyakit ini cukup tinggi. ISPA menyebabkan kematian hampir 20% kematian anak balita di seluruh dunia. Terdapat berbagai faktor yang mengakibatkan anak sakit, salah satunya berkaitan dengan masalah gizi anak. Oleh karena itu, penelitian ini akan membuat model prediksi berdasarkan data kebutuhan gizi anak untuk mencegah anak mengidap ISPA. Penelitian ini mengembangkan model untuk memprediksi penyakit ISPA pada anak dibawah umur lima tahun menggunakan pendekatan machine learning. Metode yang digunakan yaitu Support Vector Machine (SVM) dan stacking SVM. Sementara data yang digunakan berasal dari Clinical, Anthropometric & Bio-Chemical (CAB). Data yang tersedia pada dataset CAB antara lain berkaitan dengan data antropometri seperti berat badan dan tinggi badan; data klinis seperti tekanan darah, hasil tes gula darah; data biokimia seperti tingkat Hb; dan konsumsi saat anak dibawah umur 3 tahun seperti waktu konsumsi ASI, waktu awal konsumsi air, susu hewan, makanan pendamping semisolid dan solid, serta sayuran. Hasil dari percobaan menggunakan SVM saja menghasilkan akurasi terbaik sebesar 67%. Model SVM ini menggunakan parameter kernel Poly, Cost = 10, dan gamma = 0.1. Sementara pada model stacking SVM menghasilkan akurasi yang sama yaitu 67% dengan model sebagai berikut: model SVM dengan kernel linear, C=100, gamma=1; SVM dengan kernel poly; dan SVM dengan kernel poly, C=10, gamma=0.1
=====================================================================================================================================
Children's health at an early age of life is very vulnerable to disease. There is a disease that threatens death in children, namely Acute Respiratory Infection (ARI). ISPA is an acute infection of the upper respiratory tract. This infection attacks the components of the upper respiratory tract such as the nose, sinuses, pharynx and larynx. According to the World Health Organization (WHO), child mortality due to this disease is quite high. ISPA causes the death of nearly 20% of under-five deaths worldwide. There are various factors that cause children to get sick, one of which is related to child nutrition problems. Therefore, this study will create a predictive model based on data on children's nutritional needs to prevent children from contracting ARI. This research develops a model to predict ARI in children under the age of five using a machine learning approach. The method used is Support Vector Machine (SVM) and SVM stacking. While the data used comes from Clinical, Anthropometric & Bio-Chemical (CAB). The data available in the CAB dataset relates to anthropometric data such as body weight and height; clinical data such as blood pressure, blood sugar test results; biochemical data such as Hb level; and consumption when children are under 3 years old such as when consuming breast milk, when starting to consume water, animal milk, semisolid and solid complementary foods, and vegetables. The results of the experiment using SVM alone produce the best accuracy of 67%. This SVM model uses kernel parameters Poly, Cost = 10, and gamma = 0.1. While the SVM stacking model produces the same accuracy of 67% with the following models: SVM model with a linear kernel, C=100, gamma=1; SVM with poly kernels; and SVM with poly kernel, C=10, gamma=0.1

Item Type:	Thesis (Masters)
Uncontrolled Keywords:	Prediksi, Infeksi Saluran Pernafasan Akut (ISPA), Support Vector Machine (SVM), Machine Learning, Stacking Prediction, Acute Respiratory Infection (ARI), Support Vector Machine (SVM), Machine Learning, Stacking
Subjects:	T Technology > T Technology (General) T Technology > T Technology (General) > T57.8 Nonlinear programming. Support vector machine. Wavelets. Hidden Markov models.
Divisions:	Faculty of Intelligent Electrical and Informatics Technology (ELECTICS) > Information System > 59101-(S2) Master Thesis
Depositing User:	Reynata Tri Damayanti
Date Deposited:	15 Feb 2023 01:05
Last Modified:	15 Feb 2023 01:05
URI:	http://repository.its.ac.id/id/eprint/96341

Actions (login required)

View Item