A novel intrusion detection system (IDS) using a deep neural network (DNN) is proposed to enhance the security of in-vehicular network. The parameters building the DNN structure are trained with probability-based feature vectors that are extracted from the in-vehicular network packets. For a given packet, the DNN provides the probability of each class discriminating normal and attack packets, and, thus the sensor can identify any malicious attack to the vehicle. As compared to the traditional artificial neural network applied to the IDS, the proposed technique adopts recent advances in deep learning studies such as initializing the parameters through the unsupervised pre-training of deep belief networks (DBN), therefore improving the detection accuracy. It is demonstrated with experimental results that the proposed technique can provide a real-time response to the attack with a significantly improved detection ratio in controller area network (CAN) bus.

/pdf/intrusion-detection-system-using-deep-neural-network-for-in-3lt35sprh7.pdf

Intrusion Detection System Using Deep Neural Network for In-Vehicle Network Security

We investigated the mixed traffic flow with human-driving and autonomous cars. A new mathematical model with adjustable sensitivity and smooth factor was proposed to describe the autonomous car’s moving behavior in which smooth factor is used to balance the front and back headway in a flow. A lemma and a theorem were proved to support the stability criteria in traffic flow. A series of simulations were carried out to analyze the mixed traffic flow. The fundamental diagrams were obtained from the numerical simulation results. The varying sensitivity and smooth factor of autonomous cars affect traffic flux, which exhibits opposite varying tendency with increasing parameters before and after the critical density. Moreover, the sensitivity of sensors and smooth factors play an important role in stabilizing the mixed traffic flow and suppressing the traffic jam.

Analysis of mixed traffic flow with human-driving and autonomous cars based on car-following model

Delayed-feedback control in a Lattice hydrodynamic model

This paper studies a problem of designing trajectories of a platoon of vehicles on a highway segment with advanced connected and automated vehicle technologies. This problem is very complex because each vehicle trajectory is essentially an infinite-dimensional object and neighboring trajectories have complex interactions (e.g., car-following behavior). A parsimonious shooting heuristic algorithm is proposed to construct vehicle trajectories on a signalized highway segment that comply with boundary conditions for vehicle arrivals, vehicle mechanical limits, traffic lights and vehicle following safety. This algorithm breaks each vehicle trajectory into a few sections that are analytically solvable. This decomposes the originally hard trajectory design problem to a simple constructive heuristic. Then we slightly adapt this shooting heuristic algorithm to efficiently solve a leading vehicle problem on an uninterrupted freeway. To study theoretical properties of the proposed algorithms, the time geography theory is generalized by considering finite accelerations. With this generalized theory, it is found that under mild conditions, these algorithms can always obtain a feasible solution to the original complex trajectory design problem. Further, we discover that the shooting heuristic solution is a generalization of the solution to the classic kinematic wave theory by incorporating finite accelerations. We identify the theoretical bounds to the difference between the shooting heuristic solution and the kinematic wave solution. Numerical experiments are conducted to verify the theoretical results and to draw additional managerial insights into the potential of trajectory design in improving traffic performance. In summary, this paper provides a methodological and theoretical foundation for advanced traffic control by optimizing the trajectories of connected and automated vehicles. Building upon this foundation, an optimization framework will be presented in a following paper as Part II of this study.

/pdf/parsimonious-shooting-heuristic-for-trajectory-design-of-2lrzh1niay.pdf

Parsimonious shooting heuristic for trajectory design of connected automated traffic part I: Theoretical analysis with generalized time geography

An extended continuum model accounting for the driver's timid and aggressive attributions

In this paper, we construct a new car-following model with inter-vehicle communication (IVC) to study the driving behavior under an accident. The numerical results show that the proposed model can qualitatively describe the effects of IVC on each vehicle’s speed, acceleration, movement trail, and headway under an accident and that the new model can overcome the full velocity difference (FVD) model’s shortcoming that collisions occur under an accident, which illustrates that the new model can better describe the driving behavior under an accident than the FVD model.

A new car-following model with consideration of inter-vehicle communication

An extended car-following model with consideration of the reliability of inter-vehicle communication

Based on existing traffic flow models, in this paper we develop a macro traffic flow model taking into consideration road capacity to study the impact of the road capacity on traffic flow The numerical results show that the road capacity destroys the stability of uniform flow and produces stop-and-go traffic under a moderate density and that the road capacity enhances the traffic risk coefficient and reduces the traffic system’s reliability In addition, the numerical results show that properly improving the road condition can enhance the road capacity, reduce the traffic risk coefficient and enhance the traffic system’s reliability

A macro traffic flow model accounting for road capacity and reliability analysis

In this paper, we propose an extended helicopter's rescuing model to explore the effects of multiple rescuing points on each helicopter's flying behavior during the whole rescuing process from the numerical perspective. The numerical results show that the proposed model can describe the qualitative effects of multiple rescuing points on each helicopter's speed, running trail and safe region.

An extended helicopter's rescuing model with multiple points

In this paper, we develop a helicopter rescuing model based on the interactions between two adjacent helicopters and the effects of the telegraph poles and electric wire on the helicopter’s flying behavior. We apply the proposed model to explore the properties of each helicopter’s flying behavior (including the evolutions of each helicopter’s trail, speed, and some related safe distances) during the rescuing process. The numerical results show that the proposed model can qualitatively reproduce the influences of the telegraph pole, electric wire, the interactions between two adjacent helicopters and the rescuing task on each helicopter’s flying behavior.

Weifang Shi

Papers

A new car-following model with consideration of inter-vehicle communication

An extended car-following model with consideration of the reliability of inter-vehicle communication

A macro traffic flow model accounting for road capacity and reliability analysis

An extended helicopter's rescuing model with multiple points

A helicopter rescuing model in the low airspace with two telegraph poles and an electric wire