Mobile Digital Solution for Road Safety Through ECG Analysis of Driver’s Anxiety

Important road safety concerns are being addressed in this chapter through an ECG analysis of the driver’s anxiety. When people expect a risky or pessimistic consequence, anxiety is an incredible tendency that manifests as an unwelcome feeling of tension. It is regarded as a comprehensive perception of human reasoning habits, physiologic energy, and external improvements. In recent eras, statistical data has proven that most road accidents occur due to distraction in the driver’s mindset. Such incidents can be averted by incorporating suitable preventive measures. In this study, the electrocardiogram (ECG) parameters of various sorts of anxious drivers have been examined. The analysis has been carried out using different methods to impel drivers’ demeanor states (pushed and non-centered) and thereafter monitoring their driving performance through ECG signal data. Preprocessing of ECG picture data has been done using OpenCV and other Python libraries. After that, we incorporated extractions, such as average heart rate and heart rate variability, from ECG picture data using OpenCV. The results show that there are huge differences in ECG signal credits of drivers by direction, age, and driving experience, in the time-space, repeat region, and waveform under anxiety. Our revelations of this study add to the headway of a more shrewd and redone driver alert system, which could additionally foster road traffic prosperity. An attempt to train a machine learning model to develop a smart system is also presented that validates the possibility of an AI-enabled smart system for road safety.