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 Paper's PDF

Download/View Count: 150

Share this Article