Machine Learning-Based Methods for Enhancement of UAV-NOMA and D2D Cooperative Networks.

The cooperative aerial and device-to-device (D2D) networks employing non-orthogonal multiple access (NOMA) are expected to play an essential role in next-generation wireless networks. Moreover, machine learning (ML) techniques, such as artificial neural networks (ANN), can significantly enhance network performance and efficiency in fifth-generation (5G) wireless networks and beyond. This paper studies an ANN-based unmanned aerial vehicle (UAV) placement scheme to enhance an integrated UAV-D2D NOMA cooperative network.The proposed placement scheme selection (PSS) method for integrating the UAV into the cooperative network combines supervised and unsupervised ML techniques. Specifically, a supervised classification approach is employed utilizing a two-hidden layered ANN with 63 neurons evenly distributed among the layers. The output class of the ANN is utilized to determine the appropriate unsupervised learning method-either k-means or k-medoids-to be employed. This specific ANN layout has been observed to exhibit an accuracy of 94.12%, the highest accuracy among the ANN models evaluated, making it highly recommended for accurate PSS predictions in urban locations. Furthermore, the proposed cooperative scheme allows pairs of users to be simultaneously served through NOMA from the UAV, which acts as an aerial base station. At the same time, the D2D cooperative transmission for each NOMA pair is activated to improve the overall communication quality. Comparisons with conventional orthogonal multiple access (OMA) and alternative unsupervised machine-learning based-UAV-D2D NOMA cooperative networks show that significant sum rate and spectral efficiency gains can be harvested through the proposed method under varying D2D bandwidth allocations.

Motion Shield: An Automatic Notifications System for Vehicular Communications.

Motion Shield is an automatic crash notification system that uses a mobile phone to generate automatic alerts related to the safety of a user when the user is boarding a means of transportation. The objective of Motion Shield is to improve road safety by considering a moving vehicle's risk, estimating the probability of an emergency, and assessing the likelihood of an accident. The system, using multiple sources of external information, the mobile phone sensors' readings, geolocated information, weather data, and historical evidence of traffic accidents, processes a plethora of parameters in order to predict the onset of an accident and act preventively. All the collected data are forwarded into a decision support system which dynamically calculates the mobility risk and driving behavior aspects in order to proactively send personalized notifications and alerts to the user and a public safety answering point (PSAP) (112).

A Survey on Machine-Learning Techniques for UAV-Based Communications.

Unmanned aerial vehicles (UAVs) will be an integral part of the next generation wireless communication networks. Their adoption in various communication-based applications is expected to improve coverage and spectral efficiency, as compared to traditional ground-based solutions. However, this new degree of freedom that will be included in the network will also add new challenges. In this context, the machine-learning (ML) framework is expected to provide solutions for the various problems that have already been identified when UAVs are used for communication purposes. In this article, we provide a detailed survey of all relevant research works, in which ML techniques have been used on UAV-based communications for improving various design and functional aspects such as channel modeling, resource management, positioning, and security.