Automotive Doppler sensing: The Doppler profile with machine learning in vehicle-to-vehicle networks for road safety

2017 ◽  
Author(s):  
Billy Kihei ◽  
John A. Copeland ◽  
Yusun Chang
Keyword(s):  
Machine Learning ◽  
Road Safety ◽  
Vehicle To Vehicle ◽  
Doppler Profile ◽  
Vehicle Networks

Medium Access Protocols for Cooperative Collision Avoidance in Vehicular Ad-Hoc Networks

2013 ◽  
pp. 354-375
Author(s):  
Md. Imrul Hassan ◽  
Hai L. Vu ◽  
Taka Sakurai
Keyword(s):  
Collision Avoidance ◽  
Road Safety ◽  
Vehicular Ad Hoc Networks ◽  
Ad Hoc ◽  
Mac Protocol ◽  
Dynamic Networks ◽  
Medium Access ◽  
Vehicle To Vehicle ◽  
Hoc Networks ◽  
Safety Applications

It is envisaged that supporting vehicle-to-vehicle and vehicle-to-infrastructure communications with a Vehicular Ad-Hoc Network (VANET) can improve road safety and increase transportation efficiency. Among the candidate applications of VANETs, cooperative collision avoidance (CCA) has attracted considerable interest as it can significantly improve road safety. Due to the ad hoc nature of these highly dynamic networks, no central coordination or handshaking protocol can be assumed and safety applications must broadcast information of interest to many surrounding cars by sharing a single channel in a distributed manner. This gives rise to one of the key challenges in vehicle-to-vehicle communication systems, namely, the development of an efficient and reliable medium access control (MAC) protocol for CCA. In this chapter, we provide an overview of proposed MAC protocols for VANETs and describe current standardization activities. We then focus on the performance of the IEEE 802.11 carrier sense multiple access (CSMA) based MAC protocol that is being standardized by the IEEE standards body for VANET applications. In particular, we review prominent existing analytical models and study their advantages, disadvantages and their suitability for performance evaluation of the MAC protocol for VANETs. After a discussion of the shortcomings of these models, we develop a new analytical model in the second half of the chapter. Explicit expressions are derived for the mean and standard deviation of the packet delay, as well as for the packet delivery ratio (PDR) at the MAC layer in an unsaturated network formed by moving vehicles on a highway. We validate the analytical results using extensive simulations and show that good accuracy can be achieved with the proposed model for a range of topologies and traffic load conditions. More importantly, using the model, we show that hidden terminals can have a severe, detrimental impact on the PDR, which may compromise the reliability required for safety applications.

Trust Management for VANETs

2012 ◽  
Vol 3 (1) ◽  
pp. 48-62 ◽  
Author(s):  
Jie Zhang
Keyword(s):  
Road Safety ◽  
Trust Management ◽  
Vehicular Ad Hoc Networks ◽  
Ad Hoc ◽  
False Information ◽  
Future Directions ◽  
Vehicle Communication ◽  
Vehicle To Vehicle ◽  
Trust Models ◽  
Hoc Networks

An increasingly large number of cars are being equipped with GPS and Wi-Fi devices, forming vehicular ad-hoc networks (VANETs) and enabling vehicle to vehicle communication with the goal of providing increased passenger and road safety. However, dishonest peers (vehicles) in a VANET may send out false information to maximize their own utility. Given the dire consequences of acting on false information in this context, there is a serious need to establish trust among peers. This article first discusses the challenges for trust management caused by the important characteristics of VANET environments, and identifies desired properties that effective trust management should incorporate in order to address the challenges. The author then surveys and evaluates existing trust models in VANETs, and points out that none of the trust models has achieved all the properties. Finally, the author proposes some important future directions for research towards effective trust management for VANETs.

scholarly journals Design and Implementation of V2V and V2I Communication Systems using ML based Li-Fi technology

2021 ◽  
Author(s):  
Manimegaai C T ◽  
kali muthu ◽  
sabitha gauni
Keyword(s):  
Machine Learning ◽  
Communication Systems ◽  
Machine Learning Techniques ◽  
Light Emitting ◽  
Design And Implementation ◽  
Vehicle To Vehicle ◽  
The People ◽  
Learning Techniques ◽  
Vehicle To Infrastructure ◽  
Vehicle To Infrastructure Communication

Abstract These days population are taking a risk in their drive and in no time dangers are happening, and loosing lives by doing tiny wrongs when on drive near restricted zones. To escape these accidents to make population risk free traffic department are introducing signboards. But then again with the ignorance of the people, dangers are happening again, so “Li-Fi technology” is being used here to decrease the count of accidents. The transmission takes place with the help of LEDs (Light Emitting Diodes).Text, audio and video can also be transmitted with the help of this li-fi. The transmission is done when the light turns on and off. When this is compared to Wi-Fi it has many advantages like this light is not harmful to human body. The Transmission takes place in the form of zeroes and ones. Therefore to avoid accidents we suggested an intelligent, adaptable, and efficient model that utilizes Machine Learning techniques. The proposed system helps in vehicle to vehicle and vehicle to Infrastructure communication systems.

scholarly journals Computational classification of animals for a highway detection system

2021 ◽  
Vol 58 ◽  
pp. e174951
Author(s):  
Denis Sato ◽  
Adroaldo José Zanella ◽  
Ernane Xavier Costa
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Computer Vision ◽  
Convolutional Neural Network ◽  
Road Safety ◽  
Detection System ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
The World

Vehicle-animal collisions represent a serious problem in roadway infrastructure. To avoid these roadway collisions, different mitigation systems have been applied in various regions of the world. In this article, a system for detecting animals on highways is presented using computer vision and machine learning algorithms. The models were trained to classify two groups of animals: capybaras and donkeys. Two variants of the convolutional neural network called Yolo (You only look once) were used, Yolov4 and Yolov4-tiny (a lighter version of the network). The training was carried out using pre-trained models. Detection tests were performed on 147 images. The accuracy results obtained were 84.87% and 79.87% for Yolov4 and Yolov4-tiny, respectively. The proposed system has the potential to improve road safety by reducing or preventing accidents with animals.

Sign in / Sign up

Export Citation Format

Share Document