Skripsi
HYBRID MACHINE LEARNING MODEL UNTUK PREDIKSI RISIKO BERAT BADAN BERLEBIH PADA REMAJA
Background: Overweight and obesity are conditions of excessive fat accumulation in the body that can have a negative impact on health. The incidence of overweight in adolescents in the world and in Indonesia continues to increase and is a problem that must be addressed. The use of artificial intelligence can help provide an easy tool for predicting overweight in adolescents so that they can prevent overweight from progressing to obesity and other cardiometabolic diseases. This research aims to predict overweight in adolescents using a hybrid machine learning model by combining Logistic Regression and Random Forest methods to increase the prediction accuracy value so that a model with even better performance is obtained. Method: This type of research is an analytic observational with a cross-sectional design using secondary data on adolescents aged 10-19 years. Sampling used purposive sampling technique. Analysis using SPSS version 27, Python 3.12, and Jupyter Notebook. Result: The accuracy value obtained from the hybrid machine learning model using the Logistic Regression and Random Forest methods was 76.41%. There is an increase in the accuracy value of the Hybrid Machine Learning Model compared to the single model Logistic Regression (75.38%) or Random Forest (51.79%). Conclusion: Hybrid machine learning model with Logistic Regression and Random Forest models is quite accurate (fair) to predict the risk of overweight in adolescent. Keywords: Overweight, Adolescent, Hybrid Model, Machine Learning, Logistic Regression, Random Forest
Inventory Code | Barcode | Call Number | Location | Status |
---|---|---|---|---|
2407000280 | T137608 | T1376082023 | Central Library (Referens) | Available but not for loan - Not for Loan |
No other version available