Article Per Year (5 Year)
p-Index From 2020 - 2025
0.408
P-Index
This Author published in this journals
All Journal Sinkron : Jurnal dan Penelitian Teknik Informatika MIND (Multimedia Artificial Intelligent Networking Database) Journal
CAHYANI, INDAH ARDHIA
Unknown Affiliation
Computer Science & IT

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
Klasifikasi Penyakit Stunting Menggunakan Algoritma Multi-Layer Perceptron ASHURI, PUTRI INTAN; CAHYANI, INDAH ARDHIA; ADITYA, CHRISTIAN SRI KUSUMA
MIND (Multimedia Artificial Intelligent Networking Database) Journal Vol 9, No 1 (2024): MIND Journal
Publisher : Institut Teknologi Nasional, Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26760/mindjournal.v9i1.52-63

Abstract

AbstrakStunting adalah gangguan pertumbuhan dan perkembangan yang disebabkan kekurangan gizi yang ditandai dengan tinggi anak kurang dari dua kali standar deviasi yang ditetapkan oleh WHO. Kekurangan asupan gizi mengakibatkan menurunnya pertumbuhan anak, hal ini berhubungan dengan meningkatnya resiko sakit, kematian, hambatan pertumbuhan fisik maupun gangguan metabolisme tubuh. Beberapa metode telah dilakukan untuk membantu mengklasifikasi stunting pada anak salah satunya C4.5. Tujuan penelitian ini adalah mengklasifikasikan penyakit stunting menggunakan metode Multi-Layer Perceptron (MLP) dengan hyperparameter tuning RandomSearchCV. MLP memiliki beberapa kelebihan diantaranya mampu merepresentasikan hubungan lebih kompleks antara fitur input dan output, serta memproses data dalam berbagai bentuk, termasuk data tidak terstruktur. Penelitian ini menunjukan model MLP menggunakan hyperparameter tuning RandomSearchCV mendapatkan performa terbaik berdasarkan hasil evaluasi didapatkan accuracy sebesar 81.78%, precision 85.00%, recall 94.34%, dan F1-Score 89.43%.Kata kunci: Stunting, Kekurangan gizi, Multi-Layer Perceptron (MLP), Hyperparameter tuning, RandomSearchCVAbstract Stunting is a growth and development disorder caused by malnutrition which is characterized by a child's height being less than twice the standard deviation set by WHO. Lack of nutritional intake results in decreased growth in children, this is associated with an increased risk of illness, death, physical growth restrictions and metabolic disorders. Several methods have been used to help classify stunting in children, one of which is C4.5. The aim of this research is to classify stunting using the Multi-Layer Perceptron (MLP) method with RandomSearchCV hyperparameter tuning. MLP has several advantages, including being able to represent more complex relationships between input and output features, as well as processing data in various forms, including unstructured data. This research shows that the MLP model using RandomSearchCV hyperparameter tuning got the best performance based on the evaluation results, which obtained accuracy of 81.78%, precision of 85.00%, recall of 94.34%, and F1-Score of 89.43%.Keywords: author’s guideline, document’s template, format, style, abstract
Stunting Disease Classification Using Multi-Layer Perceptron Algorithm with GridSearchCV Cahyani, Indah Ardhia; Ashuri, Putri Intan; Aditya, Christian Sri Kusuma
Sinkron : jurnal dan penelitian teknik informatika Vol. 8 No. 1 (2024): Articles Research Volume 8 Issue 1, January 2024
Publisher : Politeknik Ganesha Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33395/sinkron.v9i1.13245

Abstract

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.
Co-Authors ASHURI, PUTRI INTAN Christian Sri kusuma Aditya, Christian Sri kusuma