As an essential part of the emerging Internet of Things, connected and autonomous vehicles (CAVs) have the potential to reshape future transportation systems and change the commute style in people’s everyday life. Among many vehicular on-board devices, radar system and vehicle-to-vehicle (V2V) communication system are two important pillars for the realization of CAVs. In this paper, the concept of coordinated CRC (C-CRC) is proposed to serve as a cognitive mediator for bridging vehicular radar and communication systems. By establishing a mutual-assistance relationship, C-CRC provides a new safety mechanism that allows one system to learn from and react to the risks that the other system has encountered. Simulation results have shown that the proposed method has desirable performance in face of motion perturbation and/or jamming attack under various scenarios.

The work presented in this chapter is an extension of our previous research of bringing together the Cognitive Dynamic System (CDS) and the Smart Grid (SG) by focusing on AC state estimation and Cyber-Attack detection. Under the AC power flow model, state estimation is complex and computationally expensive as it relies on iterative procedures. On the other hand, the False Data Injection (FDI) attacks are a new category of cyber-attacks targeting the SG that can bypass the current bad data detection techniques in the SG. Due to the complexity of the nonlinear system involved, the amount of published works on AC based FDI attacks have been fewer compared to their DC counterpart. Here, we will demonstrate how the entropic state, which is the objective function of the CDS, can be used as a metric to monitor the grid’s health and detect FDI attacks. The CDS, acting as the supervisor of the system, improves the entropic state on a cycle to cycle basis by dynamically optimizing the state estimation process through the reconfiguration of the weights of the sensors in the network. In order to showcase performance of this new structure, computer simulations are carried out on the IEEE 14-bus system for optimal state estimation and FDI attack detection.

Vehicular radar is one of the key components for connected and autonomous vehicles (CAVs). Through adaptive transmit-waveform selection, cognitive vehicular radar (CVR) can be developed to support advanced driver assistance systems (ADAS). In this paper, we study the improvement of CVR tracking performance with the assistance of 5G vehicle-to-vehicle (V2V) communications. The model of cognitive dynamic system (CDS) and its function of cognitive risk control (CRC) is incorporated in the design. Specifically, the perceptor of CVR has flexible filtering formulation, which will take the expanded form when V2V messages are available; on the other hand, the executive of CVR has flexible operational modes, which is expanded when unexpected risk needs to be brought under control. Simulation results have shown that the proposed method will improve tracking accuracy significantly in an uncertain and dynamic environment.

Building on historical notes, this paper consists of three basic parts: Part One deals with environment, artificial intelligence, and cognitive dynamic system (CDS); Part Two deals with mathematics and the brain; and Part Three deals with switches. To expand this paper in a different context, the emphasis is on artificial intelligence and CDS. With switches being relatively new and highly important, we first discuss regular switches followed by the special switch, we then introduce task-switch control, and then AI and CDS for describing their individual structures. Finally, this paper finishes with conclusion.

As one of the largest applications for the Internet of Things in smart cities, the Internet of Vehicles has attracted increasing attention over the years due to its great potential for reshaping both transportation systems and human society. While connected and autonomous vehicles (CAVs) are currently being developed all over the world, they are unfortunately under various potential threats that c...

Connected and autonomous vehicles (CAVs) and unmanned aerial vehicles (UAVs) are viewed as revolutionary technologies in the era of Internet of Things (IoT). However, both CAV and UAV can be exploited by potential adversaries and pose serious threats to the intelligent transportation system (ITS), such as damaging the vehicle-to-vehicle (V2V) communication. In this paper, we investigate the anti-jamming V2V communication in an integrated UAV-CAV network with hybrid attackers, which consist of a malicious CAV with intelligent jamming capability and a malicious UAV without. To solve this problem, we propose to use a unique research tool named cognitive dynamic system (CDS), and apply its function of cognitive risk control (CRC) to develop an effective countermeasure. In each perception-action cycle (PAC), the power control will always be performed by a legitimate transmitting vehicle; meanwhile, the process of channel selection only takes place if the risk level is evaluated as high after completing the power control. This kind of design that involves task-switching is inspired by the predictive-adaptation feature of the human brain. Simulation results have shown that the proposed method based on CRC is able to defend hybrid attackers effectively under various settings.

The future of intelligent transportation system (ITS) is expected to be composed of connected and autonomous vehicles (CAVs), the development of which will have great impact on people's everyday life. Unfortunately, this progress will be accompanied by all kinds of potential threats and attacks rising in CAV network. As a legacy from traditional wireless networks, jamming attack is still one of the major and serious threats to vehicle-to-vehicle (V2V) communications. In this paper, we investigate the anti-jamming V2V communication in CAV networks through power control in conjunction with channel selection. Bringing into play a brain-inspired research tool called cognitive dynamic system (CDS), the general structure of cognitive risk control (CRC) is well-tailored to analyze and address the jamming problem. Specifically, power control is carried out first using reinforcement learning, the result of which is then examined by a module called task-switch control. Based on the risk assessment, a multi-armed bandit (MAB) problem is formulated to perform the channel-selection process when necessary. Through continuous perception-action cycles (PACs), the feature of predictive adaptation is realized for the legitimate vehicle in its behavioral interactions with the jammer. Simulation results have shown that the proposed method has desirable performance in terms of several evaluation metrics.

This paper introduces a new way of thinking that characterizes itself by uniting two entities, namely state estimation in the smart grid (SG) and cognitive dynamic system (CDS). False data injection (FDI) attacks are a family of new attacks that have been considered to be the most dangerous cyber-attack as it leads to cascaded bad decision making throughout the SG network, which can lead to severe repercussions. The conventional state estimation and bad data detection techniques, which have been applied to reduce observation errors and detect bad data in energy system state estimators, cannot detect FDI attacks. Here, we bring into play an objective-seeking system to act as the supervisor of the SG network. To this end, we propose to introduce a new metric for the SG: the entropic state. The entropic state has two purposes: 1) it provides an indication of the grid's health on a cycle-to-cycle basis and 2) it can be used to detect FDI attacks. Consequently, improving the entropic state is the goal of the supervisor. To achieve that objective, the supervisor dynamically optimizes the state estimation process by reconfiguring the weights of the sensors in the network. With optimality in mind, the CDS is the superior choice for the supervisory system. In this structure, the CDS interacts with the SG network, which is considered as the environment. Computer simulations are carried out on a 4-bus and the IEEE 14-bus systems to highlight the performance of the proposed approach in detecting both bad data and FDI attacks in the SG, respectively.

In this paper, we extend our previous research on uniting the Cognitive Dynamic Systems (CDS) and the Smart Grid (SG) by introducing Cognitive Risk Control (CRC). The CDS is a structured physical model and research tool inspired by certain features of the brain. The CRC is an advanced feature of the CDS that embodies the concept of predictive adaptation allowing it to bring risk under control in situations involving unexpected or abnormal uncertainty such as a cyber-attack. The False Data Injection (FDI) attack is a special class of cyber-attack targeting the SG that is able to bypass the traditional bad data detection techniques. Here we will demonstrate how the entropic state, which is the objective function of the CDS, is able to detect and bring FDI attacks under control under the action of CRC. Through Task-Switch control, the CDS is able to switch on a new executive with different set of actions that affects the system configuration to bring the risk under control during an attack. With the CDS acting as the supervisor of the SG, simulations are carried out on a 4 bus-system and IEEE 14-bus system to demonstrate the capability of CRC when faced with FDI attacks. The results show that this system has great potential for future SG systems.

A modified version of the probabilistic data association (PDA) is proposed for target tracking under measurement uncertainty conditions. This method uses the likelihood of each validated measurement, and selects the best k candidates to be integrated with the PDA. Different computer simulations with a single target under dense-cluttered environment are presented. Comparison to the standard PDA shows a track loss reduction with the proposed method.

In this study, the authors extend the high-degree cubature Kalman filter to operate with continuous-time non-linear stochastic systems with discrete measurements. For this purpose, they utilise two known approximations to solve the stochastic differential equation used in the modelling of continuous-time dynamics. The first approach is grounded in an ordinary differential equations solver. The second approach is based on the Ito-Taylor expansion of order 1.5. In addition, the errors presented in each approach were classified. Finally, the proposed filters were compared with the continuous-discrete cubature Kalman filter in a challenging radar-tracking experiment. The results of the experiment show an improvement in the accuracy of the proposed method, and more importantly, a better performance of the filters based on the Ito-Taylor expansion.

Cognitive dynamic system (CDS) is a structured engineering model and research tool inspired by certain features of the human brain. As a special function of CDS, cognitive risk control (CRC) actualizes the concept of predictive adaptation to bring risk under control when encountered with unexpected uncertainty. In this paper, the first experimental demonstration of CRC is presented in the practical application of vehicular radar systems, and an algorithm for transmit-waveform selection in cognitive vehicular radar (CVR) based on CRC is proposed. During each perception-action cycle, the perceptor of CVR processes new environmental inputs and provides the processed information to the executive through feedback channel for the selection of cognitive action. With the mechanism of task-switch control being functional all the time, the CVR will switch to a more capable operation mode in the face of unexpected disturbances or adverse events. In such cases, a new subsystem of executive is brought into play, in which the risk-sensitive cognitive action is finally selected and applied to the environment. Simulation results have shown the robustness and effectiveness of the proposed CVR system, which can make the next-generation vehicular radars more intelligent and play an important role in future self-driving cars.

This article proposes to integrate two entities, the Internet of Things and a cognitive dynamic system (CDS), and studies a smart home scenario as the application of interest. As a people-centric loT, the smart home aims to enhance the intelligence level of the living environment and improve the quality of human life. Cognition, the distinct principles of which are perception-action cycle, memory, attention, intelligence, and language, can play a key role to pave the way for building truly smart homes. With cognition as its foundation, the engineering paradigm of CDS provides step-by-step guidelines for systematic development of smart homes. Hence, CDS can significantly contribute to the interactive loT ecosystem.

In this chapter, we describe a cognitive radar that mimics the visual brain [1]. Although the visual brain and radar are different in that the visual brain does not transmit a probing signal to the environment, while the active radar greatly relies on the probing signal it transmits to the environment; nevertheless, both of them are observers of the surrounding environment. As such, there is much that we can learn from the visual brain in building a new generation of cognitive radars that outperform traditional radars. In this chapter, we confine the discussion, in both analytic and experimental terms, to cognitive radar aimed at target tracking.

The cognitive dynamic system (CDS) is a structured physical model and research tool inspired by certain features of the human brain. One such feature is the predictive adaptation of the organism to the future environment. From an engineering perspective, this property of the brain is of profound practical importance, particularly when the system, in the pursuit of goals or performing tasks, confronts unexpected adverse events or obstacles, which in the aggregate are commonly referred to as risk. To avert risk efficiently, much of the information processed in the past by the CDS is available for processing new information in one of the system’s components termed the perceptor. In the face of uncertainty, the perceptor will provide the processed information to the executive in order for the latter to avoid probable risk. To that effect, the executive will be fitted with Bayesian filtering mechanisms that will guide the CDS to its goal through timely risk-avoiding actions. Those mechanisms not only have unique engineering applications but also potential value for understanding the predictive-adaptation property of the brain, which modern neuroscience attributes to the prefrontal cortex.