Klasifikasi Status Gizi Bayi Posyandu Kecamatan Bangun Purba Menggunakan Algoritma Support Vector Machine (Svm)

Abstract

This research was conducted to apply the Support Vector Machine algorithm in the process of classifying the nutritional status of infants under five. The nutritional status of early childhood can determine what kind of human resources as successors of a nation in the future. Good nutritional status plays an important role in determining the success or failure of efforts to increase human resources, so that data on the nutritional status of toddlers such as at the Posyandu, Bangun Purba District can be classified using Data Mining techniques using the Support Vector Machine algorithm. The results of this study using 80% of the data as training data and 20% of the data as training data are f1 score 0.865, accuracy 0.876, precision score 0.871, and recall score 0.876. The results showed that from a total of 347 data on the nutritional status of infants, there were 284 infants with good nutrition, 15 infants with poor nutrition, 23 infants with less nutrition, 8 infants with excess nutrition, 6 infants with obesity, and 11 infants at risk of overnutrition. Based on these results, there were 304 baby nutrition data that were classified correctly from a total of 347 baby data that were used as testing data. From this research, it can be concluded that the Support Vector Machine algorithm can classify infant nutrition data at the Posyandu, Bangun Purba District, well.

Comparison of Algorithms for Sentiment Analysis of Operator Satisfaction Level for Increasing Neo Feeder Applications in PDDikti Higher Education LLDIKTI Region VI Semarang Central Java

“…With in-depth training the SVM classifier then creates emerging values or patterns that are used in the SVM testing process to characterize data sentiment. To obtain the optimal hyperplane line to separate data from the two classes, the hyperplane limit calculation is used and the maximum point is sought (Khotimah et al, 2022;Ramon et al, 2022). How to get a hyperplane with a support vector machine using the equation:…”

Klasifikasi dan Monitoring Status Gizi Balita Melalui Penerapan Metode Naïve Bayes Classification Berbasis GIS

“…Penelitian ini akan menggunakan algoritma Naïve Bayes Classification dalam melakukan classification karena tingkat akurasi dan MAPE yang dihasilkan oleh Naïve Bayes Classifier umumnya lebih tinggi bila dibandingkan dengan KNN [4], selain itu juga Naïve Bayes Classifier memiliki performa recall terbaik bila dibandingkan dengan Decision Tree dan KNN [5]. Selain menggunakan Naïve Bayes Classification, penentuan status gizi balita juga pernah dilakukan dengan menggunakan algoritma decision tree dengan kriteria berat badan menurut umur (BB/U) dengan akurasi 98,86% [6], KNN melalui feature selection backward elimination dengan atribut identitas balita, BB/TB, z-score dari masing-masing nilai indeks Antropometrinya dan indeksasi binary stunting dan tidak stunting dengan akurasi yang dihasilkan sebesar 92,20% [7], algoritma C4.5 melalui pendekatan indeks BB/TB dengan akurasi sebesar 90% [8], serta algoritma SVM dengan kriteria yang digunakan adalah identitas balita, data posyandu, dan indeks Antropometri dengan akurasi yang dihasilkan sebesar 87% [9].…”

Machine Learning Method to Predict the Toddlers’ Nutritional Status

“…Several ML methods are used to classify/predict malnutrition or nutritional status in toddlers, including the naïve Bayes (NB) method [3][4][5][6], logistic regression [7], k-nearest neighbor (kNN) [4,5,8], decision tree (DT) [6,[9][10][11], support vector machine (SVM) [12], and learning vector quantization [13]. Several studies compare several ML methods to classify malnutrition in toddlers [4,[14][15][16][17][18][19].…”