Comparative Study of Random Forest and SVM for Daily Activity Level Prediction Using Wearable Device Data
Abstract & Details
Research Area
Computer Applications
Keywords
Human Activity Recognition
Daily Activity Prediction
Random Forest
Support Vector Machine
Wearable Devices
Machine Learning
Feature Importance
ROC-AUC
Health Monitoring
Abstract
Human activity recognition with wearable sensors has vast uses in health monitoring, exercise tracking, and lifestyle management. This paper provides a comparison of the Random Forest (RF) and Support Vector Machine (SVM) models for predicting daily activity levels from the dailyActivity_merged.csv dataset. The models classify days as active or inactive based on total steps and corresponding activity measures. Performance evaluation was done based on accuracy, precision, recall, F1-score, confusion matrices, and ROC/AUC curves. Experimental results show that Random Forest classifier performs better than SVM in all the measures, giving higher predictive accuracy and generalization. Moreover, feature importance analysis shows the most crucial activity parameters that contribute most towards active day prediction. The results highlight the value of machine learning methods in accurate activity classification and their utility for guiding individualized health interventions and exercise planning.
License
This work is licensed under a Creative
Commons
Attribution-ShareAlike 4.0 International License.
Author Information
| # | Name | Institute / Affiliation |
|---|---|---|
| 1 | R Deekshayini | CMR University |
| 2 | K Kanagalakshmi | CMR University |
How to Cite
Use the following formats to cite this article in your research.
APA Style
Deekshayini, R & Kanagalakshmi, K (2025). Comparative Study of Random Forest and SVM for Daily Activity Level Prediction Using Wearable Device Data. International Journal of Advance Research and Innovative Ideas In Education, 11(4), 3804-3812.
MLA Style
Deekshayini, R, and K Kanagalakshmi. "Comparative Study of Random Forest and SVM for Daily Activity Level Prediction Using Wearable Device Data." International Journal of Advance Research and Innovative Ideas In Education, vol. 11, no. 4, 2025, pp. 3804-3812.
IEEE Style
R Deekshayini and K Kanagalakshmi, "Comparative Study of Random Forest and SVM for Daily Activity Level Prediction Using Wearable Device Data," International Journal of Advance Research and Innovative Ideas In Education, vol. 11, no. 4, pp. 3804-3812, 2025.
Vancouver Style
Deekshayini R, Kanagalakshmi K. Comparative Study of Random Forest and SVM for Daily Activity Level Prediction Using Wearable Device Data. International Journal of Advance Research and Innovative Ideas In Education. 2025;11(4):3804-3812.
Harvard Style
Deekshayini, R & Kanagalakshmi, K (2025) 'Comparative Study of Random Forest and SVM for Daily Activity Level Prediction Using Wearable Device Data', International Journal of Advance Research and Innovative Ideas In Education, 11(4), pp. 3804-3812.
Chicago Style
Deekshayini, R and K Kanagalakshmi. "Comparative Study of Random Forest and SVM for Daily Activity Level Prediction Using Wearable Device Data." International Journal of Advance Research and Innovative Ideas In Education 11, no. 4 (2025): 3804-3812.
Turabian Style
Deekshayini, R and K Kanagalakshmi. "Comparative Study of Random Forest and SVM for Daily Activity Level Prediction Using Wearable Device Data." International Journal of Advance Research and Innovative Ideas In Education 11, no. 4 (2025): 3804-3812.
Related Research
EduQuest AI: A Gamified Learning Platform for Interactive and Personalized Digital Education
Download PDF
Distributed Real-Time Stream Analytics and Ingestion Engine for High-Velocity Big Data Architectures
Download PDF