Artificial intelligence (AI) is one of the key technologies emerging in the Industrial Revolution that could protect against cybersecurity threats. AI is a key component of big data analytics and enables accurate real-time data analysis. AI can analyze big data, but it has some issues with security, privacy, and centralization of data. Moreover, cybercriminals continue to advance, so law enforcement faces more threats. With traditional cybersecurity solutions, sophisticated cyber-attacks are harder to detect and defend against. In complex cyberspaces, AI algorithms mine valuable features from data. However, the data on the Internet is scattered and controlled by different parties, making it challenging to authorize and validate its use. The AICyber-Chain model is presented in this paper for securely storing, calculating, and distributing data on the Internet at an enterprise scale. In a large-scale Internet environment, our proposed AICyber-Chain model integrates three key components to ensure a more secure cyberspace, enhancing AI, namely: Firstly, blockchain-based data sharing guarantees ownership at a large scale, enabling real-time data sharing. Secondly, a platform powered by AI makes cyberspace more trustworthy. Thirdly, sharing data or services rewards participants financially, which promotes sharing. We also discuss a typical use scenario, an alternative deployment method, and its security and commercial efficacy. Also, we simulated our model on Ethereum’s official test network, called Rinkeby, to demonstrate its practicality and efficiency. This model speeds up authentication by 1.8 times compared to the centralized model. In addition, our proposed solution reduces gas consumption by 20 to 25%. Our paper aims to serve as a guide and reference point for cybersecurity researchers and industry practitioners, especially from an intelligent computing or AI-based technical standpoint.

Vehicular ad hoc Networks (VANETs) enable vehicles to communicate with each other as well as with roadside units (RSUs). Although there is a significant research effort in radio channel modeling focused on vehicle-to-vehicle (V2V), not much work has been done for vehicle-to-infrastructure (V2I) using 3D ray-tracing tools. This work evaluates some important parameters of a V2I wireless channel link such as large-scale path loss and multipath metrics in a typical urban scenario using a deterministic simulation model based on an in-house 3D Ray-Launching (3D-RL) algorithm at 5.9 GHz. Results show the high impact that the spatial distance; link frequency; placement of RSUs; and factors such as roundabout, geometry and relative position of the obstacles have in V2I propagation channel. A detailed spatial path loss characterization of the V2I channel along the streets and avenues is presented. The 3D-RL results show high accuracy when compared with measurements, and represent more reliably the propagation phenomena when compared with analytical path loss models. Performance metrics for a real test scenario implemented with a VANET wireless sensor network implemented ad-hoc are also described. These results constitute a starting point in the design phase of Wireless Sensor Networks (WSNs) radio-planning in the urban V2I deployment in terms of coverage.

In this work, Vehicle-to-everything (V2X) wireless communications performance is analyzed, in order to account for inherent scenario complexity, in the deployment phase of wireless systems towards the implementation of a Context Aware environment. An urban environment has been simulated by means of an in-house three-dimensional (3D) Ray Launching algorithm, coupled with a microscopic vehicular movement simulator, accounting for embedded urban elements as well as variable traffic densities within the complex environment. Large-scale and small-scale results are presented, as well as statistical analysis of the impact of different traffic densities. A campaign of measurements in the same real scenario has been performed, showing good agreement with wireless channel estimations for the considered frequency. These results can aid in V2X deployment configurations in urban environments, in order to minimize power consumption, optimize interference levels and increase overall system performance.

In this paper, intra-wagon wireless communication performance is analyzed, in order to account for inherent scenario complexity in the deployment phase of wireless systems toward the implementation of a context-aware environment. A real commercial passenger wagon has been simulated by means of an in-house-developed 3-D ray launching code, accounting for embedded wagon elements as well as variable user densities within the passenger wagon. Onboard measurements of a designed and deployed wireless sensor network are obtained, showing good agreement with wireless channel estimations for two different frequencies of operation. Energy consumption behavior and user density impact have also been analyzed and estimated as a function of network topology and the operational mode. These results can aid in wireless transceivers deployment configurations, in order to minimize power consumption, optimize interference levels, and increase overall service performance.

Vehicular Ad Hoc Networks (VANETs) are envisaged to be a critical building block of Smart Cities and Intelligent Transportation System (ITS) where applications for pollution, congestion reduction, vehicle mobility improvement, accident prevention and safer roads are some of the VANETs expected benefits towards Intelligent Vehicle Communications. Although there is a significant research effort in Vehicle-to-Infrastructure (V2I) and Vehicle-to-Vehicle (V2V) communication radio channel characterization, the use of a deterministic approach as a complement of theoretical and empirical models is required to understand more accurately the propagation phenomena in urban environments. In this work, a deterministic computational tool based on an in-house 3D Ray-Launching algorithm is used to represent and analyze large-scale and small-scale urban radio propagation phenomena, including vehicle movement effects on each of the multipath components. In addition, network parameters such as throughput, packet loss and jitter, have been obtained by means of a set of experimental measurements for different V2I and V2V links. Results show the impact of factors such as distance, frequency, location of antenna transmitters (TX), obstacles and vehicle speed. These results are useful for radio-planning Wireless Sensor Networks (WSNs) designers and deployment of urban Road Side Units (RSUs).

This paper presents a vibration-based machine learning approach for road surface monitoring using smartphone sensors. With Mexico’s road network experiencing significant deterioration and potholes ranking as citizens’ top concern, we propose a convolutional neural network (CNN) model that analyzes accelerometer and gyroscope data from Android smartphones to detect road anomalies. Our methodology includes a custom mobile application for data collection, feature extraction through moving average filtering, and a 2-CNN architecture for classification. Experimental results demonstrate 98% accuracy in distinguishing potholes from speed bumps when using six sensor features, compares favorably with previously reported vibration-based approaches.The system’s low-cost implementation and high accuracy indicate that it may be well suited for large-scale road condition monitoring using mobile crowd-sensing paradigms.