Nowadays, advanced communication technologies are being utilized to develop intelligent transportation management and driving assistance. Through the ability to exchange traffic and infotainment information between road infrastructure and vehicles, vehicular ad-hoc networks (VANETs) promise to improve transport efficiency, accident prevention, and pedestrians comfort. The deployment of VANETs in the real world is based on the message’s correctness and timely delivery and assuredness of privacy protection and data security. In this regard, many researchers have conducted surveys and studies that present models and solutions related to the improvement of VANET from different aspects such as architectural design, networking, and data security. Motivated by these influences, this study presents a detailed survey of VANETs to provide a complete picture of particular VANET applications, networking, and challenges. None of them collected all data in one survey. VANET communication techniques and their improvements are the focus of this study. The contributions of this paper are as follows. First, a complete taxonomy of VANET wireless access techniques has been provided based on various parameters. Second, a detailed discussion and classification VANET services and applications are provided. Third, the challenges related to VANET according to the applicability area, data networking, and resource management are explored in detail. Based on this classification, a complete description of the challenges for each category, including the proposed solutions and development models, is provided to overcome such challenges. Finally, the integration of evolutionary technologies with VANET is comprehensively presented. In this regard, a thorough explanation is provided for each technology, including the challenges, solutions, and suggestions for further improvements. This study enables various users working in the vehicular networking domain to select one of the proposals based on its relative advantages.

A Comprehensive Survey on Vehicular Networking: Communications, Applications, Challenges, and Upcoming Research Directions

Vehicle detection using improved region convolution neural network for accident prevention in smart roads

The increasing diffusion of tiny wearable devices and, at the same time, the advent of machine learning techniques that can perform sophisticated inference, represent a valuable opportunity for the development of pervasive computing applications. Moreover, pushing inference on edge devices can in principle improve application responsiveness, reduce energy consumption and mitigate privacy and security issues. However, devices with small size and low-power consumption and factor form, like those dedicated to wearable platforms, pose strict computational, memory, and energy requirements which result in challenging issues to be addressed by designers. The main purpose of this study is to empirically explore this trade-off through the characterization of memory usage, energy consumption, and execution time needed by different types of neural networks (namely multilayer and convolutional neural networks) trained for human activity recognition on board of a typical low-power wearable device.Through extensive experimental results, obtained on a public human activity recognition dataset, we derive Pareto curves that demonstrate the possibility of achieving a 4× reduction in memory usage and a 36× reduction in energy consumption, at fixed accuracy levels, for a multilayer Perceptron network with respect to more sophisticated convolution network models.

/pdf/exploring-artificial-neural-networks-efficiency-in-tiny-3bhjnko0.pdf

Exploring Artificial Neural Networks Efficiency in Tiny Wearable Devices for Human Activity Recognition

Now a day's usage of Two-wheeler is exponentially increasing and the accidents met by them also increases every year. Even though the Safety precautions and traffic rules are there the riders are not showing interest in following the safety measures and rules. An intelligent Bike Safety and Surveillance (IBSS) is a real time system which makes a rider to follow safety measures and the rules. The System Comprise of Helmet unit & Vehicle unit with antitheft and Speed Control mode. The helmet unit ensures whether the Rider is wearing a helmet, Alcohol Consumption of the rider and the proper release of Side stand. The Vehicle unit Comprises of the Surveillance system which check and intimate if an Accident is occurred. The antitheft mode protects the vehicle from unauthorized users. The Speed control mode monitors the speed and automatically control the speed of the Vehicle. The System is implemented using Arduino UNO and ATmega 328 Microcontroller with different sensors. 

An intelligent bike safety and surveillance system

This paper explores the advancement of the Internet of Things (IoT) and Machine Learning in the field of Road Safety and accident prevention with a state-of-the-art review of various techniques adopted for implementing an intelligent road Safety System. In this review, emphasis is given on the behavior of drivers, the condition of vehicles (two-wheelers, four-wheelers), health condition of roads and bridges, and theft-related issues using Radio Frequency Identification (RFID). It is seen that, with the help of IoT, the safety system can be updated on a real-time basis which can help to create a smart, intelligent, and highly efficient Road Safety system. Artificial Intelligence (AI) is applied to enhance the technology further for detecting the driver's behavior like drowsiness with the help of real-time camera feed or high-resolution images. Additionally, the role of AI in detecting the condition of roads and bridges in preventing road accidents is also discussed. Though the paper provides a good insight into the application of IoT and Machine Learning in the smart Road safety system, certain limitations are highlighted.

Application of IoT and Artificial Intelligence in Road Safety

Transportation is playing a vital role in our daily life and its development has made many of our chores much easier. But in recent years, driver drowsiness, distractions, and speed limit crossing cause ruinous road accidents which lead to fatalities. Slumbering, dozing, alcohol consumption cause intrusiveness which needs to alert the driver before a mishap happens. In this paper, a prototype is designed using Raspberry Pi, Pi Camera, sensors for monitoring driver’s eye movements, detecting yawning, detecting toxic gases, and alcohol consumption to prevent accidents and provide safety assistance to drivers. Internet of Things and machine learning-enabled system is implemented in vehicles for transmitting the behavior of the driver and his driving pattern to the cloud to take quick response under emergency situations. Several lives are saved by alerting the driver with help of a sound system that is deemed to prevent any distractions before happen. The cloud services and machine learning are employed in identifying fatigue drivers through the collected and stored dataset from cloud services. The device is experimentally tested, and the results show its efficiency and effectiveness.

S. Uma

Papers

Accident prevention and safety assistance using IOT and machine learning