AI-Driven Energy Efficiency Optimizations in mHealth Applications: A Comprehensive Review on User Behavior Prediction and System Performance

Abstract

Recently, mHealth applications have gained immense popularity, revolutionizing healthcare management for chronic diseases and fitness tracking. However, continuous data processing and transmission increase the strain on battery life. This study examines AI and machine learning-based techniques to reduce energy consumption in mHealth applications without compromising functionality. Adaptive sampling, task scheduling, and predictive user behavior modeling were implemented, significantly reducing power consumption and extending battery life. Challenges such as data privacy and model generalization in deploying these AI technologies are also addressed, along with future research and broader adoption.