Haliza, Hanim Rachma Nur and Sabila, Faradita and Riyadi, Alya Zahirah (2024) IMPLEMENTASI MODEL MACHINE LEARNING SUPERVISED DAN UNSUPERVISED DALAM PENGEMBANGAN APLIKASI PENCEGAHAN STUNTING. Project Report (Praktek Kerja Lapang dan Magang). Faultas Ilmu Komputer, Surabaya.
![[img]](https://repository.upnjatim.ac.id/style/images/fileicons/text.png) |
Text (Cover)
Cover.pdf Download (441kB) |
|
Text (Bab 1)
Bab 1.pdf Download (17kB) |
|
Text (Bab 2)
Bab 2.pdf Restricted to Repository staff only until 13 July 2029. Download (74kB) |
|
Text (Bab 3)
Bab 3.pdf Restricted to Repository staff only until 13 July 2029. Download (158kB) |
|
Text (Bab 4)
Bab 4.pdf Restricted to Repository staff only until 13 July 2029. Download (821kB) |
|
Text (Bab 5)
Bab 5.pdf Download (16kB) |
|
Text (Daftar Pustaka)
Daftar Pustaka.pdf Download (97kB) |
|
Text (Lampiran)
Lampiran.pdf Restricted to Repository staff only until 13 July 2029. Download (2MB) |
Abstract
Stunting is a serious health issue in Indonesia, with a prevalence of 21.6% in 2022. This figure remains far from the national target of reducing stunting prevalence to 14% by 2024. This study aims to implement supervised and unsupervised machine learning (ML) models for a stunting prevention application. The models employed include Artificial Neural Networks (ANN) and Regression Neural Networks. The "Check Stunting" feature utilizes an ANN to detect stunting risk based on age, weight, and height data, achieving 100% accuracy and a loss of 0.07, demonstrating high performance in binary classification. Meanwhile, the "Check Nutrition and Food Recommendation" feature implements a Regression Neural Network for nutritional calculations and Content-Based Filtering to provide food recommendations tailored to an infant's nutritional needs. The development process involved data cleaning, normalization using MinMaxScaler, and model validation via loss and accuracy metrics. Evaluations showed a relevance rate of up to 99% and a Mean Absolute Error (MAE) of 0.0149, ensuring accurate and appropriate recommendations. Challenges such as the lack of local datasets were overcome through model adjustment using existing data and data processing techniques to enhance dataset quality. The project results demonstrate that ML technology can support the early detection of stunting risk and evidence-based interventions. Future recommendations include enriching the local food dataset and integrating nutritional education features to enhance the application's effectiveness.
| Item Type: | Monograph (Project Report (Praktek Kerja Lapang dan Magang)) | ||||||||
|---|---|---|---|---|---|---|---|---|---|
| Contributors: |
|
||||||||
| Subjects: | T Technology > T Technology (General) > T58.6-58.62 Management Information Systems | ||||||||
| Divisions: | Faculty of Computer Science > Departemen of Information Systems | ||||||||
| Depositing User: | Alya Zahirah Riyadi | ||||||||
| Date Deposited: | 17 Jul 2026 08:46 | ||||||||
| Last Modified: | 20 Jul 2026 01:36 | ||||||||
| URI: | https://repository.upnjatim.ac.id/id/eprint/55176 |
Actions (login required)
 |
View Item |