Driver behaviour prediction and enhanced ad hoc on-demand distance vector routing protocol in VANET

Mobility pattern recognition is a complex task in vehicle ad hoc networks (VANET) because the driving state of each vehicle is different. An intelligent transportation system on VANET is used for traffic control and accident prevention. For this reason, human driver behaviour is first analysed to identify mobility patterns. A novel driver behaviour prediction model using a Siamese deep learning architecture is proposed to achieve the goal. Here, an image-based behaviour prediction model is performed to achieve the highly accurate driving state of the driver. A warning message is forwarded to the neighbouring vehicles based on the driver's behaviour. Due to the dynamic properties of real-time vehicle mobility, a faster data transmission model is achieved using the ad hoc on-demand distance vector routing protocol. To achieve faster data transmission and nullified retransmission, here a weighted location-based routing model is framed. The optimization problem in the location-aided routing protocol is solved using the vector algorithm's weighted mean. As a result, the proposed method improved the throughput of ASHLOSR to 8.1% and AODV to 7.6%. For the safest driving of road user, an image-based neighbouring driver behaviour prediction model is highlighted and proposed in this research. Human driver behaviour is first analysed to identify mobility patterns. A novel driver behaviour prediction model using a Siamese deep learning architecture is proposed to achieve the goal. A warning or alert message of abnormal driver behaviour is successfully send to the vehicles through weighted location-aided routing protocol. The protocol has improved the VANET metrics by selecting optimal path of congestion free and shortest distance, which reduces retransmission rate. The optimization uses congestion-free route selection, so the proposed method increased the throughput to 8.1% from ASHLOSR and 7.6% from traditional AODV.image