KSC 2020
Current Result Document :
ÇѱÛÁ¦¸ñ(Korean Title) |
Nutrition-Based Food Recommendation System for Prediabetic Person |
¿µ¹®Á¦¸ñ(English Title) |
Nutrition-Based Food Recommendation System for Prediabetic Person |
ÀúÀÚ(Author) |
Kokoy Siti Komariah
Bong-Kee Shin
|
¿ø¹®¼ö·Ïó(Citation) |
VOL 47 NO. 02 PP. 0660 ~ 0662 (2020. 12) |
Çѱ۳»¿ë (Korean Abstract) |
|
¿µ¹®³»¿ë (English Abstract) |
Automatic food recommendation systems use machine learning algorithms to provide users with products or services to meet their needs or requirements. Recently, these systems have been using sophisticated machine learning algorithms from the field of artificial intelligence. In this research, we aim to analyze and build a system for helping a prediabetic person choose their grocery preferences based on their health profile and nutrition status. The proposed solution is a hybrid approach offering a food grocery recommendation using a combination of rulebased association methods, K-means clustering, and kNN classifiers. It helps prediabetics maintain their healthy lifestyle, advise them when buying a groceries product and prevent them from developing the diabetic disease. The proposed method can provide relatively good accuracy by RMSE score of 0.44 and an MAE score of 0.26. This result shows that the model can relatively predict the data accurately.
|
Å°¿öµå(Keyword) |
food recommendation system
nutrition-based
prediabetes
rule-based association
k-means clustering
knn classifiers
artificial intelligence
|
ÆÄÀÏ÷ºÎ |
PDF ´Ù¿î·Îµå
|