Diet and Physical Exercise Recommendation System Using a Combination of K-Means and Random Forest
DOI:
https://doi.org/10.34818/INDOJC.2024.9.2.959Keywords:
Recommendation System, K-Means, Random Forest, Mean Absolute Percentage Error (MAPE)Abstract
Public health has become a significant focus in this modern era due to the increasing number of people suffering from various diseases. Unhealthy diets and lack of physical activity are often associated with multiple health problems, one of which is obesity. Several studies have been conducted to develop food recommendation systems for individuals with obesity, using K-Means and Random Forest algorithms to provide food recommendations based on user-specific aspects. However, these studies do not provide supporting information, such as physical activity recommendations to address fitness issues or lack of physical activity. This study develops a diet and physical exercise recommendation system for individuals with obesity using a combination of K-Means and Random Forest. The system categorizes and classifies foods and physical exercises and provides customized recommendations based on user data analysis. The accuracy of the system was evaluated using the MAPE metric, with the highest accuracy for dietary food recommendations being 99.03% for the non-vegan lunch diet meal recommendation and the lowest being 70.74% for the vegan morning meal diet recommendation. The MAPE for physical exercise recommendations was consistently at 26.35%, indicating a stable accuracy of 73.65%. The test results show that the system recommends diet and physical exercise accurately.
Downloads
References
P. Widya Hapsari, “The Application of UNICEF'S 2020 Conceptual Framework of Maternal and Child Nutrition in Indonesia.” [Online]. Available: https://www.researchgate.net/publication/349161215.
"Obesity and overweight." World Health Organization. Accessed September 12, 2015. http://www.who.int/mediacentre/factsheets/fs311/en/.
Kardam, S. S., Yadav, P., Thakkar, R., & Ingle, A. (2021). Website on diet recommendation using machine learning. Int Res J Eng Technol (IRJET), 2021, 3708-3711.
Golagana, R., Sravani, V., Reddy, T. M., & Kavitha, C. H. (2023). Diet Recommendation System Using Machine Learning. Journal of Health and Nutrition, 15(2), 233-245.
Shah, J., Yadav, V., Pandey, S., Patel, Y., & Patil, M. S. (2023). Sports Physical Training and Diet Plan. International Journal of Advances in Engineering and Management (IJAEM), 5(4), 857-860.
Navastara, D. A., Mursidah, E., Gonti, Y. A., Wahyuni, D., Wiyadi, P. D. S., & Suadi, W. (2019). CLUSTERING TOPIK PENELITIAN BERBASIS UNSUPERVISED LEARNING UNTUK REKOMENDASI KOLEKSI PUSTAKA DI PERPUSTAKAAN ITS. JUTI: Jurnal Ilmiah Teknologi Informasi, 17(2).
Jaja, V. L., Susanto, B., & Sasongko, L. R. (2020). Penerapan Metode ItemBased Collaborative Filtering Untuk Sistem Rekomendasi Data MovieLens. D’CARTESIAN, 9(2).
Zayyad, M. R. A., & Kurnawardhani, A. (2021). Penerapan Metode Deep Learning pada Sistem Rekomendasi Film. Automata, 2(1). 24
Fadlil, J., & Mahmudy, W. F. (2007). Pembuatan Sistem Rekomendasi Menggunakan Decision Tree dan Clustering. Jurnal Ilmiah Kursor, 3(1).
Centers for Disease Control and Prevention. Body mass index: Considerations for practitioners. Cdc [Internet]. 2011:1-4.
Arisman. Obesitas, Diabetes Mellitus & Dislipidemia. Jakarta: EGC. 2011
Sugondo. Buku Ajar Penyakit Dalam. Jakarta: EGC.2009
Phanich, M., Pholkul, P., & Phimoltares, S. (2010, April). Food recommendation system using clustering analysis for diabetic patients. In 2010 international conference on information science and applications (pp. 1-8). IEEE.
Naik, P. A. (2020). Intelligent food recommendation system using machine learning. Nutrition, 5(8).
Syahpitri Damanik, N. A., Irianto, I., & Dahriansah, D. (2021). Penerapan Metode Clustering Dengan Algoritma K-Means Tindak Kejahatan Pencurian di Kabupaten Asahan. J-Com (Journal of Computer)
Haristu, R. A., & Rosa, P. H. P. (2019). Penerapan Metode Random Forest Untuk Prediksi Win Ratio Pemain Player Unknown Battleground. Media Informasi Analisa Dan Sistem, (2), 120-128.
Samudra, A. Y. (2019). Pendekatan Random Forest untuk Model Peramalan Harga Tembakau Rajangan Di Kabupaten Temanggung. Universitas Sanata Dharma, Yogyakarta.
Fatichah, C., & Purwitasari, D. (2017). Deteksi Gempa Berdasarkan Data Twitter Menggunakan Decision Tree, Random Forest, dan SVM. Jurnal Teknik ITS (SINTA: 4, IF: 1.1815), 6(1), A159-A162.
Wulansari, M. J. (2018). ANALISIS FAKTOR-FAKTOR YANG MEMPENGARUHI SESEORANG TERKENA PENYAKIT DIABETES MELITUS MENGGUNAKAN REGRESI RANDOM FOREST (Studi Kasus: Data Diabetes di Virginia Amerika Serikat).
Gouthami, B., & Gangappa, M. (2020). Nutrition diet recommendation system using user's Interest. International Journal of Advanced Research in Engineering and Technology, 11(12), 2910-2919.
Downloads
Published
How to Cite
Issue
Section
License
- Manuscript submitted to IndoJC has to be an original work of the author(s), contains no element of plagiarism, and has never been published or is not being considered for publication in other journals.Â
- Copyright on any article is retained by the author(s). Regarding copyright transfers please see below.
- Authors grant IndoJC a license to publish the article and identify itself as the original publisher.
- Authors grant IndoJC commercial rights to produce hardcopy volumes of the journal for sale to libraries and individuals.
- Authors grant any third party the right to use the article freely as long as its original authors and citation details are identified.
- The article and any associated published material is distributed under the Creative Commons Attribution 4.0License
