Internet of Things Based Driver Distraction Detection and Assistance System: A Novel Approach

As the Internet of Things (IoT) continues to evolve, there is a growing need for expertise regarding different kinds of sensors. The lack of such expertise is one of the main hurdles to the acceptance of IoT among computer scientists working in the field of Intelligent Transport Systems (ITS). With this problem in mind, we present an innovative technique for developing and testing IoT-based next generation Driver Assistance Systems. Distraction, which is considered the main cause of road accidents, can be avoided by deploying the IoT-based Driver Distraction Detection Enabled- Adaptive Driver Assistance System (DDDE-ADAS). To compute different driver distraction types, practical field experiments are currently being conducted with real drivers; however, such experiments might harm the human drivers and might also lead to false results. To address this issue, we propose a new approach for driver distraction computing. Instead of deploying sensors in real world vehicles, we utilize HUB-NET technology using an Exploratory Agent-Based Modeling level of a Cognitive Agent-based Computing (CABC) framework, which works exactly like a real-world IoT-based driver distraction detection and collision avoidance system. The experimental results reveal that the proposed driver distraction computing methodology and the Driver Distraction Detection Enabled-ADAS outperform simple ADAS without the need to carry out risky and expensive field tests.