Internet of vehicles supports to transfer of safety-related messages, which help to mitigate road accidents. Internet of vehicles allows vehicle to cooperative communicate, share position and speed data among vehicles and road side units. The vehicular network become prone to large number of attacks including false warnings, mispositioning of vehicles etc. The authentication of messages to identify the normal message packet from attack messages packet and its prevention is a major challenging task. This paper focuses on applying deep learning approach using binary classification to classify the normal packets from malicious packets. The process starts with preparing the training dataset from the open-source KDD99 and CICIDS 2018 datasets, consisting of 1,20,223 network packets with 41 features. The one-dimensional network data is preprocessed using an autoencoder to eliminate the unwanted data in the initial stage. The valuable features are then filtered as 23 out of 41, and the model is trained with structured deep neural networks, then combined with the Softmax classifier and Relu activation functions. The proposed Intrusion prevention model is trained and tested with google Colab, an open platform cloud service, and the open-source tensor flow. The proposed prevention classifier model was validated with the simulation dataset generated in network simulation. The experimental results show 99.57% accuracy, which is the highest among existing RNN and CNN-based models. In the future, the model can be trained on different datasets, which will further improve the model's efficiency and accuracy.

No abstract

The increasing rate of road fatalities has demanded the attention of the researchers, scientists, Industry and government organizations and technologies. The impact of accidents is simulated by rear-end collision with parameters such as vehicle position, direction, speed, inter-vehicle distance, and relative speeds, etc. Open source simulators have to be adopted to study and analyze various collision scenarios in vehicular networks. Safety mechanism proposed to minimize the possibility of accidents and mitigate the effect of the escalating incident. The proposed mechanism estimates the point of intersection, time to collision, and time to avoid accidents. Using parameters, the proposed mechanism able to determine accidents with 92.6% accuracy. The remaining 7.4% cases enable the passive safety system to help the people to stay alive, minimize the damage in case an accident.

No abstract

In this paper, we proposed a new technique for channel estimation using Orthogonal Frequency Division Multiplexing, (OFDM). Channel estimation is an integral part of the OFDM system based on the latest high speed transmission technology. Channel estimation is a vital technique used at the receiver side in order to estimate actual transmitted signal which gets affected by Interference. In OFDM, the known pilot signal is inserted to get a channel estimate and then the channel response is obtained by interpolation algorithms. We propose two algorithms and studied their characteristics qualities in channel estimation by simulation in NS-2. Firstly, the channel estimation scheme named Frequently Constructed Pilot Based Channel Estimation(FCPCE), which fully utilizes the pilot symbols is used to estimate the channel response and then the equalizer technique Maximum Minimizing Null Adaptive filters(MMNF) is used to completely remove the inter-symbol interference (ISI) and noise at the receiver side. Further, analysis and simulations show better performance of the proposed techniques based on 802.11p standard.