Adaptive Exercise Prescription: A Machine Learning Approach to Personalized Fitness Recommendations Using Smartphone Sensor Data
Author(s): Vijaya Chaitanya Palanki
Publication #: 2410012
Date of Publication: 07.10.2020
Country: USA
Pages: 1-6
Published In: Volume 6 Issue 5 October-2020
DOI: https://doi.org/10.5281/zenodo.13949737
Abstract
The proliferation of smartphones equipped with advanced sensors presents unprecedented opportunities for personalized health interventions. This paper proposes a novel framework for generating personalized exercise recommendations based on data collected from smartphone sensors. By leveraging machine learning algorithms and real-time sensor data, our system adapts to individual user characteristics, fitness levels, and environmental factors to provide tailored exercise suggestions. The methodology encompasses data collection from accelerometers, gyroscopes, and GPS sensors, feature extraction, user profiling, and a multi-stage recommendation engine. This research contributes to the field of mobile health by offering a scalable approach to personalized fitness interventions, potentially improving public health outcomes through widespread smartphone adoption.
Keywords: Personalized exercise, smartphone sensors, machine learning, adaptive recommendations, mobile health, fitness tracking, context-aware computing
Download/View Count: 150
Share this Article