Wearable Mobile-Based Emotional Response-Monitoring System for Drivers

Abstract

Negative emotional responses are a growing problem among drivers, particularly in countries with heavy traffic, and may lead to serious accidents on the road. Measuring stress- and fatigue-induced emotional responses by means of a wireless, wearable system would be useful for potentially averting roadway tragedies. The focus of this study was to develop and verify an emotional response-monitoring paradigm for drivers, derived from electromyography signals of the upper trapezius muscle, photo-plethysmography signals of the earlobe, as well as inertial motion sensing of the head movement. The relevant sensors were connected to a microcontroller unit equipped with a Bluetooth-enabled low energy module, which allows the transmission of those sensor readings to a mobile device in real time. A mobile device application was then used to extract the data from the sensors and to determine the drivers current emotion status, via a trained support vector machine (SVM). The emotional response paradigm, tested in ten subjects, consisted of 10 min baseline, 5 min pre-stimulus, and 5 min post-stimulus measurements. Emotional responses were categorized into three classes: relaxed, stressed, and fatigued. The proposed wearable system could be applied to an intelligent drivers safety alert system, to use those emotional responses to prevent accidents affecting themselves and/or other innocent victims.

Existing System

Real-time demotion detection for advanced driver assistance systems.

Proposed System

In this paper, we proposed a wearable, driver emotional response monitoring system, employing a using mobile device. Our results revealed that physiological features, such as PR, muscle activities, etc., are good indicators for discriminating certain emotional responses among the neutral (relaxed), fatigue (bored), and stress (frustrated/panicked) states. Indeed, by incorporating multiple features extracted from PPG, EMG, and IMU to train the SVM model, the accuracy rates of emotional response is evaluated. The sensors were designed to be wearable either at the neck or at the back of the head. All three sensor modules, the microcontroller, the BLE module, and the rechargeable battery are placed on a custom-made enclosure that was constructed using a three-dimensional printer. The enclosure was designed to fit well at the back of the neck or the head of the driver, so as not to cause any driver discomfort. The PPG signal is obtained via the drivers earlobe, the EMG signal from the upper trapezius muscle, given that it exhibits a high level of muscle activity during stressed conditions. Moreover, the IMU sensor is positioned within the package as close to the back of the drivers head as possible, in order to track the drivers head motion with 9-DOF.

Architecture

Overview of the system design