Search Results (12)

The increasing occurrence of extreme rainfall events often leads to flash floods, infrastructure damage, loss of human life, and significant economic impacts. There is a pressing need for data-driven assessments and the application of robust analytical approaches to better understand these changes. Analyzing ground-level daily rainfall data from 1985 to 2023 from 26 monitoring stations, this study first employs the Mann–Kendall test using robust statistics including minimum, median, various quartiles, and maximum rainfall values for detecting long-term trends across Saudi Arabia. Next, the k-means clustering technique is applied to characterize the annual rainfall cycles across different regions of the country. Finally, the Peaks Over Threshold (POT) approach within Extreme Value Theory (EVT) is employed to identify site-specific thresholds for extreme rainfall using the Generalized Pareto Distribution (GPD). This automated, data-driven method offers a more objective alternative to the commonly used ad hoc percentile-based threshold selection, thereby enhancing the rigour and reproducibility of extreme rainfall analysis. Local specific thresholds were computed ranging from about 16 to 47 mm from Arar and Jazan, respectively. These thresholds were then used to calculate the frequency and intensity of extreme rainfall events. The fitted GPD parameters were further used to estimate return levels (RLs) for different return periods (2-, 5-, 10-, 20-, 50-, and 100-year) into the future. The results underscore considerable spatial variability in extreme rainfall behaviour across Saudi Arabia, with a higher likelihood of intense and infrequent precipitation events in the coming decades. Full article

With the arrival of sixth-generation (6G) wireless systems comes radical potential for the deployment of autonomous aerial vehicle (AAV) swarms in mission-critical applications, ranging from disaster rescue to intelligent transportation. However, 6G-supporting AAV environments present challenges such as dynamic three-dimensional topologies, highly restrictive energy constraints, and extremely low latency demands, which substantially degrade the efficiency of conventional routing protocols. To this end, this work presents a Q-learning-enhanced ad hoc on-demand distance vector (QL-AODV). This intelligent routing protocol uses reinforcement learning within the AODV protocol to support adaptive, data-driven route selection in highly dynamic aerial networks. QL-AODV offers four novelties, including a multipath route set collection methodology that retains up to ten candidate routes for each destination using an extended route reply (RREP) waiting mechanism, a more detailed RREP message format with cumulative node buffer usage, enabling informed decision-making, a normalized 3D state space model recording hop count, average buffer occupancy, and peak buffer saturation, optimized to adhere to aerial network dynamics, and a light-weighted distributed Q-learning approach at the source node that uses an ε-greedy policy to balance exploration and exploitation. Large-scale simulations conducted with NS-3.34 for various node densities and mobility conditions confirm the better performance of QL-AODV compared to conventional AODV. In high-mobility environments, QL-AODV offers up to 9.8% improvement in packet delivery ratio and up to 12.1% increase in throughput, while remaining persistently scalable for various network sizes. The results prove that QL-AODV is a reliable, scalable, and intelligent routing method for next-generation AAV networks that will operate in intensive environments that are expected for 6G. Full article

Every year, about 1.19 million people are killed in traffic accidents; hence, the United Nations has a goal of halving the number of road traffic deaths and injuries by 2030. In line with this objective, technological innovations in telecommunication, particularly brought about by the rise of 5G networks, have contributed to the development of modern Vehicle-to-Everything (V2X) systems for communication. A New Radio V2X (NR-V2X) was introduced in the latest Third Generation Partnership Project (3GPP) releases which allows user devices to exchange information without relying on roadside infrastructures. This, together with Massive Machine Type Communication (mMTC) and Ultra-Reliable Low Latency Communication (URLLC), has led to the significantly increased reliability, coverage, and efficiency of vehicular communication networks. The use of artificial intelligence (AI), especially K-means clustering, has been very promising in terms of supporting efficient data exchange in vehicular ad hoc networks (VANETs). K-means is an unsupervised machine learning (ML) technique that groups vehicles located near each other geographically so that they can communicate with one another directly within these clusters while also allowing for inter-cluster communication via cluster heads. This paper proposes a multi-layered VANET-enabled Intelligent Transportation System (ITS) framework powered by unsupervised learning to optimize communication efficiency, scalability, and reliability. By leveraging AI in VANET solutions, the proposed framework aims to address road safety challenges and contribute to global efforts to meet the United Nations’ 2030 target. Additionally, this framework’s robust communication and data processing capabilities can be extended to eHealth monitoring systems, enabling real-time health data transmission and processing for continuous patient monitoring and timely medical interventions. This paper’s contributions include exploring AI-driven approaches for enhanced data interaction, improved safety in VANET-based ITS environments, and potential applications in eHealth monitoring. Full article

The development of intelligent transportation systems (ITS), vehicular ad hoc networks (VANETs), and autonomous driving (AD) has progressed rapidly in recent years, driven by artificial intelligence (AI), the internet of things (IoT), and their integration with dedicated short-range communications (DSRC) systems and fifth-generation (5G) networks. This has led to improved mobility conditions in different road propagation environments: urban, suburban, rural, and highway. The use of these communication technologies has enabled drivers and pedestrians to be more aware of the need to improve their behavior and decision making in adverse traffic conditions by sharing information from cameras, radars, and sensors widely deployed in vehicles and road infrastructure. However, wireless data transmission in VANETs is affected by the specific conditions of the propagation environment, weather, terrain, traffic density, and frequency bands used. In this paper, we characterize the path loss based on the extensive measurement campaign carrier out in vehicular environments at 700 MHz and 5.9 GHz under realistic road traffic conditions. From a linear dual-slope path loss propagation model, the results of the path loss exponents and the standard deviations of the shadowing are reported. This study focused on three different environments, i.e., urban with high traffic density (U-HD), urban with moderate/low traffic density (U-LD), and suburban (SU). The results presented here can be easily incorporated into VANET simulators to develop, evaluate, and validate new protocols and system architecture configurations under more realistic propagation conditions. Full article

The success of the Internet of Things (IoT) has driven the development, among others, of many different software architectures for producing, processing, and analyzing heterogeneous data. In many cases, IoT applications share common features, such as the use of a platform or middleware, also known as message broker, that collects and manages data traffic between endpoints. However, in general, data processing is very dependent on the case study (sensors that send temperature data, drones that send images, etc.). Thus, the applications responsible for receiving and processing data, which we call consumers, have to be built ad hoc, since some of their elements have to be specially configured to solve specific needs of the case study. This paper presents Flextory, a software factory tool to make it easier for IoT developers to automatically construct configurable consumer applications, which we call FLEX-consumers. Flextory guides developers through the process of generating Java consumers by selecting some desired features such as, for instance, the particular communication protocol to be used. This way, the developer only has to concentrate on designing the algorithm to process the data. In short, the use of Flextory will result in consumer applications with configurable behavior, namely FLEX-consumers, that can connect to a messaging server (for example RabbitMQ) and process the received messages. Full article

As data-driven models gain importance in driving decisions and processes, recently, it has become increasingly important to visualize the data with both speed and accuracy. A massive volume of data is presently generated in the educational sphere from various learning platforms, tools, and institutions. The visual analytics of educational big data has the capability to improve student learning, develop strategies for personalized learning, and improve faculty productivity. However, there are limited advancements in the education domain for data-driven decision making leveraging the recent advancements in the field of machine learning. Some of the recent tools such as Tableau, Power BI, Microsoft Azure suite, Sisense, etc., leverage artificial intelligence and machine learning techniques to visualize data and generate insights from them; however, their applicability in educational advances is limited. This paper focuses on leveraging machine learning and visualization techniques to demonstrate their utility through a practical implementation using K-12 state assessment data compiled from the institutional websites of the States of Texas and Louisiana. Effective modeling and predictive analytics are the focus of the sample use case presented in this research. Our approach demonstrates the applicability of web technology in conjunction with machine learning to provide a cost-effective and timely solution to visualize and analyze big educational data. Additionally, ad hoc visualization provides contextual analysis in areas of concern for education agencies (EAs). Full article

Nineteen percent of global final energy consumption is used to generate electricity and heat in buildings. Therefore, it is undisputed that the building sector needs to cut consumption. However, this reduction needs to be driven by data analysis from real building operations. Starting from this concept and with the aim of proving the benefits deriving from the installation of a monitoring system in a real operating environment, in this work a monitoring system has been installed to monitor the centralised heating and cooling system of a residential building composed of 57 residential units. The data acquired from the installed sensors are collected and subsequently analysed in an ad hoc tool to detect anomalies, performance decay, malfunctions, and failures of the machines, as well as to understand if the implemented management strategy is appropriate in terms of energy and cost savings. The results show the key role of the data acquired by the monitoring system and analysed by the developed tool in terms of ability to detect failures and malfunctions in both the heating and cooling modes, as well as to help both in finding the proper management strategy and in identifying the performance deviation precursors of machine failure. Full article

Wing-sailed autonomous sailing monohulls are promising platforms used in various scenarios to provide data for marine science research. These platforms need to operate long-term in changing seas; their general configurations (size matching between sail, hull, and keel) necessitate careful trade-offs to balance safety and efficiency. Since autonomous sailboats are often designed for different observation missions, scientific pay-loads and target areas, their design space is considerably large. It is also challenging to obtain prior performance estimation from historical designs. Therefore, traditional offline surrogate-based simulation-driven design frameworks suffer from a large amount of sampling required, the computational cost of which remains too expensive for such ad hoc design tasks. This paper proposes an innovative, generalised simulation-driven framework combining Bayesian optimisation and knowledge transfer. It allows for high-quality, low-cost optimisation of autonomous sailing monohulls’ general configuration without initial design and prior performance estimation. The proposed optimisation framework has been used to optimise the ‘Seagull’ prototype within the design constraints. The optimised design exhibits significant performance improvements. At the same time, the results show that the present method is significantly superior to traditional offline methods. The authors believe that the proposed framework promises to provide the autonomous sailing community with a solution for a general design methodology. Full article

We propose a fully data-driven approach to calibrate local stochastic volatility (LSV) models, circumventing in particular the ad hoc interpolation of the volatility surface. To achieve this, we parametrize the leverage function by a family of feed-forward neural networks and learn their parameters directly from the available market option prices. This should be seen in the context of neural SDEs and (causal) generative adversarial networks: we generate volatility surfaces by specific neural SDEs, whose quality is assessed by quantifying, possibly in an adversarial manner, distances to market prices. The minimization of the calibration functional relies strongly on a variance reduction technique based on hedging and deep hedging, which is interesting in its own right: it allows the calculation of model prices and model implied volatilities in an accurate way using only small sets of sample paths. For numerical illustration we implement a SABR-type LSV model and conduct a thorough statistical performance analysis on many samples of implied volatility smiles, showing the accuracy and stability of the method. Full article

Named Data Networking (NDN) is a promising communication paradigm for the challenging vehicular ad hoc environment. In particular, the built-in pervasive caching capability was shown to be essential for effective data delivery in presence of short-lived and intermittent connectivity. Existing studies have however not considered the fact that multiple vehicular contents can be transient, i.e., they expire after a certain time period since they were generated, the so-called FreshnessPeriod in NDN. In this paper, we study the effects of caching transient contents in Vehicular NDN and present a simple yet effective freshness-driven caching decision strategy that vehicles can implement autonomously. Performance evaluation in ndnSIM shows that the FreshnessPeriod is a crucial parameter that deeply influences the cache hit ratio and, consequently, the data dissemination performance. Full article

Currently, there is growing interest in the modeling of high concentrator photovoltaic modules, due to the importance of achieving an accurate model, to improve the knowledge and understanding of this technology and to promote its expansion. In recent years, some techniques of artificial intelligence, such as the Artificial Neural Network, have been used with the goal of obtaining an electrical model of these modules. However, little attention has been paid to applying Fuzzy Rule-Based Systems for this purpose. This work presents two new models of high concentrator photovoltaics that use two types of Fuzzy Systems: the Takagi-Sugeno-Kang, characterized by the achievement of high accuracy in the model, and the Mamdani, characterized by high accuracy and the ease of interpreting the linguistic rules that control the behavior of the fuzzy system. To obtain a good knowledge base, two learning methods have been proposed: the “Adaptive neuro-fuzzy inference system” and the “Ad Hoc data-driven generation”. These combinations of fuzzy systems and learning methods have allowed us to obtain two models of high concentrator photovoltaic modules, which include two improvements over previous models: an increase in the model accuracy and the possibility of deducing the relationship between the main meteorological parameters and the maximum power output of a module. Full article

Flying Ad hoc Network (FANET) is a new resource-constrained breed and instantiation of Mobile Ad hoc Network (MANET) employing Unmanned Aerial Vehicles (UAVs) as communicating nodes. These latter follow a predefined path called ’mission’ to provide a wide range of applications/services. Without loss of generality, the services and applications offered by the FANET are based on data/content delivery in various forms such as, but not limited to, pictures, video, status, warnings, and so on. Therefore, a content-centric communication mechanism such as Information Centric Networking (ICN) is essential for FANET. ICN addresses the problems of classical TCP/IP-based Internet. To this end, Content-centric networking (CCN), and Named Data Networking (NDN) are two of the most famous and widely-adapted implementations of ICN due to their intrinsic security mechanism and Interest/Data-based communication. To ensure data security, a signature on the contents is appended to each response/data packet in transit. However, trusted communication is of paramount importance and currently lacks in NDN-driven communication. To fill the gaps, in this paper, we propose a novel trust-aware Monitor-based communication architecture for Flying Named Data Networking (FNDN). We first select the monitors based on their trust and stability, which then become responsible for the interest packets dissemination to avoid broadcast storm problem. Once the interest reaches data producer, the data comes back to the requester through the shortest and most trusted path (which is also the same path through which the interest packet arrived at the producer). Simultaneously, the intermediate UAVs choose whether to check the data authenticity or not, following their subjective belief on its producer’s behavior and thus-forth reducing the computation complexity and delay. Simulation results show that our proposal can sustain the vanilla NDN security levels exceeding the 80% dishonesty detection ratio while reducing the generated end-to-end delay to less than 1 s in the worst case and reducing the average consumed energy by more than two times. Full article