Real time collision warning system in the context of vehicle-to-vehicle data exchange based on drivings behaviours analysis

Ameen, Hussein Ali (2021) Real time collision warning system in the context of vehicle-to-vehicle data exchange based on drivings behaviours analysis. Doctoral thesis, Universiti Tun Hussein Onn Malaysia.


Download (12MB) | Preview
[img] Text (Copyright Declaration)
Restricted to Repository staff only

Download (13MB) | Request a copy
[img] Text (Full Text)
Restricted to Registered users only

Download (14MB) | Request a copy


Worldwide injuries in vehicle accidents have been on the rise in recent years, mainly due to driver error regardless of technological innovations and advancements for vehicle safety. Consequently, there is a need for a reliable-real time warning system that can alert drivers of a potential collision. Vehicle-to-Vehicle (V2V) is an extensive area of ongoing research and development which has started to revolutionize the driving experience. Driving behaviour is a subject of extensive research which gains special attention due to the relationship between speeding behaviour and crashes as drivers who engage in frequent and extreme speeding behaviour are overinvolved in crashes. National Highway Traffic Safety Administration (NHTSA) set guidelines on how different vehicle automation levels may reduce vehicle crashes and how the use of on-board short-range sensors coupled with V2V technologies can help facilitate communication among vehicles. Based on the previous works, it can be seen that the assessment of drivers’ behaviours using their trajectory data is a fresh and open research field. Most studies related to driving behaviours in terms of acceleration�deceleration are evaluated at the laboratory scale using experimental results from actual vehicles. Towards this end, a five-stage methodology for a new collision warning system in the context of V2V based on driving behaviours has been designed. Real-time V2V hardware for data collection purposes was developed. Driving behaviour was analyzed in different timeframes prior obtained from actual driving behaviour in an urban environment collected from OBD-II adapter and GPS data logger of an instrumented vehicle. By measuring the in-vehicle accelerations, it is possible to categorize the driving behaviour into four main classes based on real-time experiments: safe drivers, normal, aggressive, and dangerous drivers. When the vehicle is in a risk situation, the system based on NRF24L01+PA/LNA, GPS, and OBD-II will pass a signal to the driver using a dedicated LCD and LED light signal. The driver can instantly decide to make the vehicle in a safe mood, effectively avoid the happening of vehicle accidents. The proposed solution provides two main functions: (1) the detection of the dangerous vehicles involved in the road, and (2) the display of a message informing the driver if it is safe or unsafe to pass. System performance was evaluated to ensure that it achieved the primary objective of improving road safety in the extreme behaviour of the driver in question either the safest (or the least aggressive) and the most unsafe (or the most aggressive). The proposed methodology has retained some advantages for other literature studies because of the simultaneous use of speed, acceleration, and vehicle location. The V2V based on driving behaviour experiments shows the effectiveness of the selected approach predicts behaviour with an accuracy of over 87% in sixty-four real-time scenarios presented its capability to detect behaviour and provide a warning to nearby drivers. The system failed detection only in few times when the receiving vehicle missed data due to high speed during the test as well as the distances between the moving vehicles, the data was not received correctly since the power transmitted, the frequency range of the signals, the antenna relative positions, and the number of in-range vehicles are of interest for the V2V test scenarios. The latter result supports the conclusion that warnings that efficiently and quickly transmit their information may be better when driver are under stress or time pressure.

Item Type: Thesis (Doctoral)
Subjects: T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK5101-6720 Telecommunication. Including telegraphy, telephone, radio, radar, television
T Technology > TL Motor vehicles. Aeronautics. Astronautics > TL1-484 Motor vehicles. Cycles
Divisions: Faculty of Electrical and Electronic Engineering > Department of Electrical Engineering
Depositing User: Mrs. Sabarina Che Mat
Date Deposited: 03 Feb 2022 02:24
Last Modified: 03 Feb 2022 02:24

Actions (login required)

View Item View Item