IoE-powered Smartphone Feedback for Real-time Driver Improvement

Abstract

This research analyzes risky driving that contributes to accidents and environmental damage from existing data. Existing driver monitoring systems, which analyze driving patterns through diagnostic data, fail to provide specific real-time feedback for critical events. This study proposes an innovative framework built on the Internet of Everything (IoE) that leverages in-vehicle sensors and smartphones to deliver real-time contextual driving feedback. The system measures hard accelerations and detects unsafe turns by analyzing time-series data from accelerometers and gyroscopes. Machine learning algorithms enable instant alerts during these critical events, prompting drivers to modify their behavior. The developed graphical user interface enables drivers to visually represent and comprehend many sensor data related to driving incidents, facilitating self-evaluation and corrective actions. Nevertheless, for the smartphone-based IoE solution to effectively enhance driving performance by providing real-time feedback, it is imperative to tackle obstacles such as energy consumption, data dependability, metrics formulation, and user approval. The system prioritizes user privacy - identity abstraction techniques reduce concerns about driver monitoring. Additionally, a user-friendly graphical interface presents analytical data to encourage self-improvement in driving habits. Field tests will evaluate the system's effectiveness, with plans for integration with emerging vehicle-to-infrastructure (V2X) connectivity to enhance functionality. The analysis results of this ethical and accessible IoE system will have a large-scale positive impact on driving habits, safer road use and a more conducive environment.