With their inherent attributes such as mobility, flexibility, and adaptive altitude, Unmanned Aerial Vehicles (UAVs) can potentially enable Intelligent Transportation Systems (ITS) to be more efficient by playing the role of aerial base stations for data collection, data analysis, and communication networks. Their ability to access hard-to-reach locations makes UAVs helpful in emergencies to search for and assess damages/accidents and support communication relays in disrupted infrastructures. Although there is a rising interest in the application of UAVs in the realm of ITS, a comprehensive survey that consolidates existing contributions is noticeably absent. This paper fulfils this research gap by investigating the contributions of UAVs in diverse domains of ITS. We divide existing works into three main categories: Functionality Level, Application Level, and Planning Level. For each category, this paper explores the tasks that UAVs enable in ITS and describes the related proposed schemes. Furthermore, various simulation testbeds and datasets used for the implementation and evaluation of UAV-enabled ITS are described. Based on the identified challenges, we provide recommendations for future research.

This study presents internet of things (IOT) and artificial intelligence technologies that are critical in reducing the harmful effects of this illness and assisting its recovery. It explores COVID-19’s economic impacts before learning about new technologies and potential solutions. The research objective was to propose a solution for self-diagnosis, self-monitoring, and self-management of COVID-19 with personal mobiles and personal data using cloud solutions and mobile applications with the help of an intelligent IoT system, artificial intelligence, machine learning, and 5G technologies. The proposed solution based on self-diagnosis without any security risk for users’ data with low cost of cloud-based data analytics by using handsets only is an innovative approach. Since the COVID-19 outbreak, the global social, economic, religious, and cultural frameworks and schedules have been affected adversely. The fear and panic associated with the new disease, which the world barely knew anything about, amplified the situation. Scientists and epidemiologists have traced the first outbreak of COVID-19 at Wuhan, China. A close examination of the genetic makeup of the virus showed that the virus is zoonotic, meaning that the virus changed hosts from animals to humans. The uncertainty associated with the above features and characteristics of the virus, as well as the high mortality rates witnessed in many parts of the globe, significantly contributed to the widespread global panic that brought the world to a standstill. Different authorities and agencies associated with securing the public have implemented different means and methods to try and mitigate the transmission of the infection as scientists and medical practitioners work on remedies to curb the spread of COVID-19. Owing to different demographics, different parts of the globe have attempted to effectively implement locally available resources to efficiently fight and mitigate the adverse effects of the COVID-19 pandemic. The general framework provided by the World Health Organization (WHO) has been implemented or enhanced in different parts of the globe by locally available resources and expertise to effectively mitigate the impact of COVID-19. There is currently no effective vaccine for COVID-19, but new technology can be available within weeks to reduce the spread of the disease; current approaches such as contact tracing and testing are not secure, and the cost of testing is high for end users. The proposed solution based on self-diagnosis without any security risk for users’ data with low cost of cloud-based data analytics functions by using an intelligent internet of things (IOT) system for collecting sensors data and processing them with artificial intelligence to improve efficiency and reduce the spread of COVID-19.

Reinforcement learning (RL) is renowned for its proficiency in modeling sequential tasks and adaptively learning latent data patterns. Deep learning models have been extensively explored and adopted in regression and classification tasks. However, deep learning has limitations, such as the assumption of equally spaced and ordered data, and the inability to incorporate graph structure in time-series prediction. Graph Neural Network (GNN) can overcome these challenges by capturing the temporal dependencies in time-series data effectively. In this study, we propose a novel approach for predicting time-series data using GNN, augmented with Reinforcement Learning(GraphRL) for monitoring. GNNs explicitly integrate the graph structure of the data into the model, enabling them to naturally capture temporal dependencies. This approach facilitates more accurate predictions in complex temporal structures, as encountered in healthcare, traffic, and weather forecasting domains. We further enhance our GraphRL model's performance through fine-tuning with a Bayesian optimization technique. The proposed framework surpasses baseline models in time-series forecasting and monitoring. This study's contributions include introducing a novel GraphRL framework for time-series prediction and demonstrating GNNs' efficacy compared to traditional deep learning models, such as Recurrent Neural Networks (RNN) and Long Short-Term Memory Networks(LSTM). Overall, this study underscores the potential of GraphRL in yielding accurate and efficient predictions within dynamic RL environments.

Personalized clinical decision support systems are increasingly being adopted due to the emergence of data-driven technologies, with this approach now gaining recognition in critical care. The task of incorporating diverse patient conditions and treatment procedures into critical care decision-making can be challenging due to the heterogeneous nature of medical data. Advances in Artificial Intelligence (AI), particularly Reinforcement Learning (RL) techniques, enables the development of personalized treatment strategies for severe illnesses by using a learning agent to recommend optimal policies. In this study, we propose a Deep Reinforcement Learning (DRL) model with a tailored reward function and an LSTM-GRU-derived state representation to formulate optimal treatment policies for vasopressor administration in stabilizing patient physiological states in critical care settings. Using an ICU dataset and the Medical Information Mart for Intensive Care (MIMIC-III) dataset, we focus on patients with Acute Respiratory Distress Syndrome (ARDS) that has led to Sepsis, to derive optimal policies that can prioritize patient recovery over patient survival. Both the DDQN ( RepDRL-DDQN ) and Dueling DDQN ( RepDRL-DDDQN ) versions of the DRL model surpass the baseline performance, with the proposed model’s learning agent achieving an optimal learning process across our performance measuring schemes. The robust state representation served as the foundation for enhancing the model’s performance, ultimately providing an optimal treatment policy focused on rapid patient recovery.