Kumara Dewi, Putu (2023) KLASIFIKASI STATUS GIZI BALITA MENGGUNAKAN ALGORITMA C4.5 (STUDI KASUS : PUSKESMAS KALIRUNGKUT). Undergraduate thesis, UPN Veteran Jawa Timur.
|
Text (Cover)
19082010118-cover.pdf Download (1MB) | Preview |
|
|
Text (BAB 1)
19082010118-bab1.pdf Download (138kB) | Preview |
|
![[img]](http://repository.upnjatim.ac.id/style/images/fileicons/text.png) |
Text (BAB 2)
19082010118-bab2.pdf Restricted to Registered users only until 24 July 2025. Download (467kB) |
|
|
Text (BAB 3)
19082010118-bab3.pdf Restricted to Registered users only until 24 July 2025. Download (203kB) |
|
|
Text (BAB 4)
19082010118-bab4.pdf Restricted to Registered users only until 24 July 2025. Download (1MB) |
|
|
Text (BAB 5)
19082010118-bab5.pdf Download (12kB) | Preview |
|
|
Text (DAFTAR PUSTAKA)
19082010118-daftarpustaka.pdf Download (234kB) | Preview |
|
|
Text (LAMPIRAN)
19082010118-lampiran.pdf Restricted to Registered users only until 24 July 2025. Download (106kB) |
Abstract
Nutrition is an external factor of growth and development of toddlers. At the Kalirungkut Health Center, nutrition monitoring for toddlers aged 0-5 years is important for their growth and development. However, with the amount of data that continues to grow every month, it is difficult to predict the nutritional status of toddlers quickly. Therefore, the C4.5 algorithm is used in data processing to accelerate the prediction of the nutritional status of toddlers. In a business sense, there are 825 toddler data with 23 columns at the Kalirungkut Health Center. 752 toddlers with good nutritional status, 4 toddlers with poor nutritional status, 11 toddlers with less nutritional status, 7 toddlers with overweight status, 1 toddler with obesity status, and 50 toddlers with excess nutrition risk. Obesity class was omitted, so that in exploration, 824 data were used with 6 columns containing Weight, Height, Lila, Age, Gender, and Nutritional Status. Modeling uses the C4.5 algorithm with 3 scenarios (80:20, 70:30, 60:40) using the Oversampling technique to handle imbalance data, oversampling is done on the training data in each scenario in the modeling. Evaluation of the 70:30 scenario after imbalance data, the resulting F1-Score is 97% good nutrition, 67% poor nutrition, 67% malnutrition, 0% over nutrition, and 60% risk of over nutrition. The accuracy obtained is 93%. The model is implemented on the website. The level of accuracy of the website in predicting the nutritional status of toddlers reaches 92.13% correct predictions and 7.86% wrong predictions. Keywords : Classification algorithm C4.5, prediction of nutritional status of toddlers, flask, python
| Item Type: | Thesis (Undergraduate) | ||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Contributors: |
|
||||||||||||
| Subjects: | Q Science > Q Science (General) Q Science > QA Mathematics > QA75 Electronic computers. Computer science Q Science > QA Mathematics > QA76 Computer software Q Science > QA Mathematics > QA76.6 Computer Programming Q Science > QA Mathematics > QA76.625 Internet Programming T Technology > T Technology (General) |
||||||||||||
| Divisions: | Faculty of Computer Science > Departemen of Information Systems | ||||||||||||
| Depositing User: | Putu Kumara Dewi | ||||||||||||
| Date Deposited: | 24 Jul 2023 07:53 | ||||||||||||
| Last Modified: | 24 Jul 2023 07:53 | ||||||||||||
| URI: | http://repository.upnjatim.ac.id/id/eprint/15969 |
Actions (login required)
 |
View Item |