Detecting and classifying driver distractions is crucial in the prevention of road accidents. These distractions impact both driver behavior and vehicle dynamics. Knowing the degree of driver distraction can aid in accident prevention techniques, including transitioning of control to a level 4 semi-autonomous vehicle, when a high distraction severity level is reached. Thus, enhancement of Advanced Driving Assistance Systems (ADAS) is a critical component in the safety of vehicle drivers and other road users. In this paper, a new methodology is introduced, using an expert knowledge rule system to predict the severity of distraction in a contiguous set of video frames using the Naturalistic Driving American University of Cairo (AUC) Distraction Dataset. A multi-class distraction system comprises the face orientation, drivers' activities, hands and previous driver distraction, a severity classification model is developed as a discrete dynamic Bayesian (DDB). Furthermore, a Mamdani-based fuzzy system was implemented to detect multi-class of distractions into a severity level of safe, careless or dangerous driving. Thus, if a high level of severity is reached the semi-autonomous vehicle will take control. The result further shows that some instances of driver's distraction may quickly transition from a careless to dangerous driving in a multi-class distraction context. INDEX TERMS Fuzzy logic systems, driver distraction, severity level, ADAS, image processing, dynamic Bayesian.

No abstract

No abstract

Abstract-More and more real-time IoT applications such as smart cities or autonomous vehicles require big data analytics with reduced latencies. However, data streams produced from distributed sensing devices may not suffice to be processed traditionally in the remote cloud due to: (i) longer Wide area network (WAN) latencies and (ii) limited resources held by a single Cloud. To solve this problem, a novel Software-defined network (SDN) based InterCloud architecture is presented for mobile edge computing environments, known as EdgeIoT. An adaptive resource capacity management approach is proposed to employ a policy-based QoS control framework using principles in coalition games with externalities. To optimise resource capacity policy, the proposed QoS management technique solves, adaptively, a lexicographic ordering bi-criteria coalition structure generation (CSG) problem. It is an onerous task to guarantee in a deterministic way that a real-time EdgeIoT application satisfies low latency requirement specified in service level agreements (SLA). CloudSim 4.0 toolkit is used to simulate an SDN-based InterCloud scenario, and the empirical results suggest that the proposed approach can adapt, from an operational perspective, to ensure low latency QoS for real-time EdgeIoT application instances.