SCUT Sampling and Classification Algorithms to Identify Levels of Child Malnutrition

Baraybar-Huambo, Juan; Gutiérrez-Cárdenas, Juan

doi:10.1007/978-3-030-46140-9_19

Cited by 1 publication

(1 citation statement)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The SCUT model demonstrated high accuracy and significantly improved malnutrition identification. Yin et al proposed using a classification and regression tree (CART) method based on the Global Leadership Initiative on Malnutrition (GLIM) to construct a decision tree for identifying the severity of malnutrition [16].…”

Section: Literature Surveymentioning

confidence: 99%

Prediction of malnutrition in newbornInfants using machine learning techniques

Kishore,

Suman,

Mnikyamba

et al. 2023

Preprint

View full text Add to dashboard Cite

This paper aims to predict malnutrition in newborn babies using various machine learning techniques. Malnutrition is characterized by the insufficient acquisition of fat and muscle mass during intrauterine growth. It is primarily caused by poor maternal nutrition and placental insufficiency, resulting in increased neonatal morbidity and mortality worldwide. In this study, we calculate the Z-score of newborns, taking into account factors such as age in months, weight, height, and sex, to determine the presence of malnutrition. The dataset utilized for this project is obtained from UNICEF for network training. The dataset is divided into two parts: one for validation and another for testing. We calculate WAZ (underweight) and LAZ (stunting) and train the models to detect neonatal malnutrition. Various machine learning models, including SVM, KNN, logistic regression, Naïve Bayes, and a two-layer neural network, are employed to identify malnutrition in children. Among these models, logistic regression demonstrates superior accuracy compared to the other algorithms.

show abstract

Section: Literature Surveymentioning

confidence: 99%