Classification of Stunting in Children Under Five Years in Padang City Using Support Vector Machine

Rahmi, Izzati; Susanti, Mega; Yozza, Hazmira; Wulandari, Frilianda

doi:10.30598/barekengvol16iss3pp771-778

Cited by 2 publications

(2 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Atribut yang digunakan antara lain yaitu umur, panjang bayi saat lahir, jumlah tanggungan, jenis kelamin, pemasukan rata-rata, status pekerjaan, status menyusui, status kebiasaan ibu, pendidikan terakhir ibu, dan status pengetahuan ibu. Dari penelitian tersebut, parameter terbaik algoritma SVM dalam mengklasifikasikan data tersebut adalah dengan menggunakan cost = 10, gamma = 5 dan fungsi kernel RBF, dengan akurasi yang didapat yaitu 100%, menunjukkan bahwa data dapat diklasifikasikan dengan sangat baik [13].…”

Section: Pendahuluanunclassified

Klasifikasi Status Stunting Balita Dengan Metode Support Vector Machine Berbasis Web

Adzhima,

Budianita,

Nazir

et al. 2023

ISI

View full text Add to dashboard Cite

Abstrack -Parents should pay attention to their children during their toddler years because at that age, they are vulnerable to various growth and developmental disorders, one of which is stunting. Stunting is a growth and developmental disorder caused by nutritional deficiencies and is characterized by a height that does not meet the normal growth criteria for children of the same age. To prevent stunting, healthcare workers or integrated health post (Posyandu) cadres measures the anthropometry of children's bodies at Posyandu. The data from these body measurements are then processed manually, which poses a significant risk of processing errors due to human error. By studying the patterns in measurement data, data mining can help address issues in the data processing process. Support Vector Machine (SVM) is one of the commonly used data mining methods for classification problems, known for its ability to work with small memory and separate data that cannot be linearly separated. Age, gender, Early Initiation of Breastfeeding (EIBF), weight, and height are the attributes used for classification using the SVM algorithm. Based on the conducted tests, there were 1172 data points with an average performance result of the best model using the parameter γ = 0.01, achieving an accuracy of 98.99%. This means that the model can be used to accurately predict new measurement data, enabling timely preventive measures for stunting.

show abstract

Section: Pendahuluanunclassified

Klasifikasi Status Stunting Balita Dengan Metode Support Vector Machine Berbasis Web

Adzhima,

Budianita,

Nazir

et al. 2023

ISI

View full text Add to dashboard Cite

show abstract

“…Stunting is a crisis problem in the field of health and welfare that is of concern in various countries, including Indonesia.In 2022, the prevalence of stunting in Indonesia is considered high with a figure of 21.6% based on the results of the Indonesian Nutrition Status survey (Kemenkes RI, 2023).Even according to the World Health Organization (WHO), in 2022 there were 148.1 million children under the age of 5 years experiencing stunting (WHO, 2023).Stunting is a disorder of child growth and development caused by chronic malnutrition characterized by the condition of infants who have a height less than 2 times the average standard deviation of growth set by WHO (Rahmi et al, 2022). Stunting is mostly experienced by children under 5 years old, where as much as 70% of stunting occurs in the age range of 0 -23 months (Pohan et al, 2021).…”

Section: Introductionmentioning

confidence: 99%

Stunting Disease Classification Using Multi-Layer Perceptron Algorithm with GridSearchCV

Cahyani,

Ashuri,

Aditya

2024

SinkrOn

View full text Add to dashboard Cite

Stunting is a growth and development disorder caused by malnutrition characterized by a child's height less than the standard deviation set by WHO. In 2022, stunting cases in Indonesia are considered a high prevalence rate, reaching 21.6%. There are several factors that can cause stunting in children, namely maternal and antenatal care factors, home environment factors, breastfeeding practices, and feeding factors during toddlerhood. There are several impacts that occur when children are stunted, namely increased risk of child mortality, susceptibility to illness, impaired brain development, physical disorders and metabolic disorders. Currently, deep learning has been widely used for disease classification and prediction, one of the deep learning methods is Multi-Layer Perceptron (MLP). The purpose of this research is to classify stunting disease using a deep learning method, namely MLP. The dataset used consists of 8 attributes, namely gender, age, birth weight, birth length, body weight, body length, breastfeeding and stunting with a total of 10,000 records. The encoding process is carried out to convert categorical data into numeric attributes of gender, breastfeeding, and stunting. This research produces a higher accuracy value than previous research which used the C4.5 algorithm with an accuracy of 61.82%, whereas in this study using MLP which was integrated with the GridSearchCV hyperparameter it obtained an accuracy of 82.37%. This proves that the MLP method is successful in classifying stunting compared to previous research algorithms.

show abstract

Classification of Stunting in Children Under Five Years in Padang City Using Support Vector Machine

Cited by 2 publications

References 9 publications

Klasifikasi Status Stunting Balita Dengan Metode Support Vector Machine Berbasis Web

Klasifikasi Status Stunting Balita Dengan Metode Support Vector Machine Berbasis Web

Stunting Disease Classification Using Multi-Layer Perceptron Algorithm with GridSearchCV

Contact Info

Product

Resources

About