No abstract

No abstract

The objective of this paper is to detect the car driver behavior. Many factors can influence the behavior of the driver that includes fatigue, distraction, eye-blinking, taking eyes off from the road, time of the driving etc. The in appropriate behavior while driving the car can leads to accidents that in return damages one’s life or the vehicle. The papers discuss the various techniques to monitor the driver behaviors and describes the advantages and disadvantages of the methods used to detect the driver behavior in a car.

The automotive industry has gained popularity in the past decade, leading to tremendous advancements in intelligent vehicular networks. The increase in the number of vehicles on the roads makes it essential for vehicles to act intelligently as humans do. The concept of machine learning is that when vehicles learn and improve to operate by the previously processed data. The machine learning techniques have helped the automotive industry develop the driverless car. With the help of sensors and cameras, it is quite possible to use the machine learning algorithms and provide the user with its benefits. It helps to allow the vehicle to perform specific tasks that actually can replace the vehicle's driver. The Artificial Intelligence (AI) chips integrated into the vehicles enable the vehicle to navigate roads. This paper provides insight into the machine learning algorithms widely used by the automotive industries, and a comparison is made between them concerning the Vehicular Ad Hoc Network (VANET) applications.

The accelerated evolution in computing and transmission automation of the Internet of Vehicles (IoV) has led to enormous research standards that attract many researchers and industries. This century of the Internet of Things (IoT) is propulsive to the routine vehicular ad hoc networks (VANETs) in the IoV. It has emerged as one of the major driving forces for innovations in the intelligent vehicular industry. The World Health Organization (WHO) report confirms that approximately 1.35 million people die because of accidents on the road every year. This requires considerable attention to incorporate more and more safety measures into the automobile industry. Intelligent transportation systems can help bridge the gap between the traditional and the intelligent automotive industry by connecting vehicle to vehicle (V2V) and vehicle to infrastructure (V2I), hence adding much safety in vehicular communication. This paper provides a comprehensive review of the Internet of Vehicles (IoV) which discusses the architectures of IoV including layer types, functions of layers, application area, and communication type supported. Further, it also provides an in-depth insight into state-of-the-art Medium Access Control (MAC) protocols and routing protocols used in IoV communication. The routing protocol comparative summarization considers important parameters which include communication types broadcast, unicast, cluster, multicast, forwarding strategy, recovery strategy, availability of map, and the type of environment urban or highway. The summarization of various protocols highlights strengths, research gaps, and application areas. Finally, the paper addresses various research challenges along with potential future enhancements for the IoV communication.