Application of Machine Learning Approach to Classify Human Activity Level Based on Lifelog Data
Sensors · 04.03.2026 · 26 (5) · 1612
DOI: 10.3390/s26051612 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 04.03.2026. Verfasst von Si-Hwa Jeong und 2 weiteren Autor:innen. Beteiligte Einrichtung: Energy Solution R&D Center Hanwha Ocean Co., Ltd., 14 Sejong-daero, Jung-gu, Seoul 04527, Republic of Korea. Hauptthemen laut MEDLINE: Machine Learning, Exercise, Human Activities. Die Arbeit nennt 29 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the Korea Agency for Infrastructure Technology Advancement, Korea Agency for Infrastructure Technology Advancement.
Abstract (Originalsprache)
The present paper provides a human activity-level classification model based on the patient’s lifelog collected from wearable devices. During about two months, the heart rate, step count, and calorie consumption for a total of 182 patients were collected from a wearable device. Using the lifelog data, the machine learning models were developed to classify the physical activity status of patients into five levels. Three types of wearable data with heart rate, step count, and calorie consumption were pre-processed as integrated data in time series. A total of 80% of the integrated data was used as the training dataset, and the remaining 20% was used as the test dataset. Sixteen algorithms were evaluated, including 12 traditional machine learning models (SVM, KNN, RF, etc.) and 4 deep learning models (CNN, RNN, etc.), and cross-validation was performed by dividing the training dataset into 5 folds. By changing the parameters required for training, the models with optimal parameters were derived. The performance of the final models with the new patient lifelog data was evaluated, and it was shown that the classification for human activity level based on heart rate and step count can be performed with high accuracy.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Energy Solution R&D Center Hanwha Ocean Co., Ltd., 14 Sejong-daero, Jung-gu, Seoul 04527, Republic of Korea.
- Industry-Academic Cooperation Foundation, Tech University of Korea, Siheung 15073, Republic of Korea.
- Business Administration Department, Tech University of Korea, Siheung 15073, Republic of Korea.
ORCID-Profile: Keon Chul Park
Förderung
- the Korea Agency for Infrastructure Technology Advancement
- Korea Agency for Infrastructure Technology Advancement
Zitieren
APA
Jeong, S. H., Nam, W., & Park, K. C. (2026). Application of Machine Learning Approach to Classify Human Activity Level Based on Lifelog Data. Sensors, 26(5), 1612. https://doi.org/10.3390/s26051612
Vancouver
Jeong SH, Nam W, Park KC. Application of Machine Learning Approach to Classify Human Activity Level Based on Lifelog Data. Sensors. 2026;26(5):1612. doi:10.3390/s26051612
BibTeX
@article{Jeong2026,
author = {Jeong, Si-Hwa and Nam, Woomin and Park, Keon Chul},
title = {Application of Machine Learning Approach to Classify Human Activity Level Based on Lifelog Data},
journal = {Sensors},
year = {2026},
volume = {26},
number = {5},
pages = {1612},
doi = {10.3390/s26051612}
}
EUVIMED