CERES :: Browsing by Author "Tsourdos, Antonios"

Browsing by Author "Tsourdos, Antonios"

Now showing 1 - 20 of 329

Open Access
5G aviation networks using novel AI approach for DDoS detection
(IEEE, 2023-07-17) Whitworth, Huw; Al-Rubaye, Saba; Tsourdos, Antonios; Jiggins, Julia
The advent of Fifth Generation (5G) technology has ushered in a new era of advancements in the aviation sector. However, the introduction of smart infrastructure has significantly altered the threat landscape at airports, leading to an increased vulnerability due to the proliferation of endpoints. Consequently, there is an urgent requirement for an automated detection system capable of promptly identifying and thwarting network intrusions. This research paper proposes a deep learning methodology that merges a Convolutional Neural Network (CNN) with a Gated Recurrent Unit (GRU) to effectively detect various types of cyber threats using tabular-based image data. To transform time series features into 2D texture images, Gramian Angular Fields (GAFs) are utilized. These images are then stacked to form an N-channel image, which is fed into the CNN-GRU architecture for sequence analysis and identification of potential threats. The provide solution GAF-CNN-GRU achieved an accuracy of 98.6% on the Cranfield Embedded Systems Attack Dataset. We further achieved Precision, Recall and F1-scores of 97.84%, 91% and 94.3%. To evaluate model robustness we further tested this approach, using a benchmark random selection of input features, on the Canadian Institute for Cyber-Security (CIC) 2019 Distributed Denial-of-service attack (DDoS) Dataset achieving an Accuracy of 89.08%. Following feature optimisation our approach was able to achieve an accuracy of 98.36% with Precision, Recall and F1 scores of 93.09%, 95.45% and 94.56% respectively.
Open Access
Adaptive control with neural networks-based disturbance observer for a spherical UAV
(Elsevier, 2016-10-03) Matassini, T.; Shin, Hyosang; Tsourdos, Antonios; Innocenti, M.
This paper develops a control scheme for a Spherical Unmanned Aerial Vehicle (UAV) which can be used in complex scenarios where traditional navigation and communications systems would not succeed. The proposed scheme is based on the nonlinear control theory combined with Adaptive Neural-Networks Disturbance Observer (NN-DOB) and controls the attitude and altitude of the UAV in presence of model uncertainties and external disturbances. The NN-DOB can effectively estimate the uncertainties without the knowledge of their bounds and the control system stability is proven using Lyapunov’s stability theorems. Numerical simulation results demonstrate the validity of the proposed method on the UAV under model uncertainties and external disturbances.
Embargo
Adaptive multivariate reusable launch vehicles reentry attitude control with pre-specified performance in the presence of unmatched disturbances
(Elsevier, 2024-01-11) Ge, Tianshuo; Chai, Runqi; Zhu, Qinghua; Chen, Kaiyuan; Tsourdos, Antonios; Farhan, Ishrak M. D.
This paper introduces a novel adaptive multivariable attitude control method for a reusable launch vehicle (RLV) to track desired attitude trajectories in the presence of unknown external disturbances and uncertainties. Unlike most existing designs that overlook mismatched disturbances, this method employs an adaptive finite-time observer (AFO) to estimate the unknown states. Based on the outputs of the AFO and the prescribed performance function, a time-varying adaptive gain that is not overestimated is designed to establish the adaptive multivariable attitude control for the RLV system. The simulations demonstrate that the proposed approach successfully guides the RLV to follow desired attitude signals despite the presence of unmatched disturbances and uncertainties.
Open Access
Advanced air mobility operation and infrastructure for sustainable connected eVTOL vehicle
(MDPI, 2023-05-16) Al-Rubaye, Saba; Tsourdos, Antonios; Namuduri, Kamesh
Advanced air mobility (AAM) is an emerging sector in aviation aiming to offer secure, efficient, and eco-friendly transportation utilizing electric vertical takeoff and landing (eVTOL) aircraft. These vehicles are designed for short-haul flights, transporting passengers and cargo between urban centers, suburbs, and remote areas. As the number of flights is expected to rise significantly in congested metropolitan areas, there is a need for a digital ecosystem to support the AAM platform. This ecosystem requires seamless integration of air traffic management systems, ground control systems, and communication networks, enabling effective communication between AAM vehicles and ground systems to ensure safe and efficient operations. Consequently, the aviation industry is seeking to develop a new aerospace framework that promotes shared aerospace practices, ensuring the safety, sustainability, and efficiency of air traffic operations. However, the lack of adequate wireless coverage in congested cities and disconnected rural communities poses challenges for large-scale AAM deployments. In the immediate recovery phase, incorporating AAM with new air-to-ground connectivity presents difficulties such as overwhelming the terrestrial network with data requests, maintaining link reliability, and managing handover occurrences. Furthermore, managing eVTOL traffic in urban areas with congested airspace necessitates high levels of connectivity to support air routing information for eVTOL vehicles. This paper introduces a novel concept addressing future flight challenges and proposes a framework for integrating operations, infrastructure, connectivity, and ecosystems in future air mobility. Specifically, it includes a performance analysis to illustrate the impact of extensive AAM vehicle mobility on ground base station network infrastructure in urban environments. This work aims to pave the way for future air mobility by introducing a new vision for backbone infrastructure that supports safe and sustainable aviation through advanced communication technology.
Open Access
Advanced UAV design optimization through deep learning-based surrogate models
(MDPI, 2024-08-14) Karali, Hasan; Inalhan, Gokhan; Tsourdos, Antonios
The conceptual design of unmanned aerial vehicles (UAVs) presents significant multidisciplinary challenges requiring the optimization of aerodynamic and structural performance, stealth, and propulsion efficiency. This work addresses these challenges by integrating deep neural networks with a multiobjective genetic algorithm to optimize UAV configurations. The proposed framework enables a comprehensive evaluation of design alternatives by estimating key performance metrics required for different operational requirements. The design process resulted in a significant improvement in computational time over traditional methods by more than three orders of magnitude. The findings illustrate the framework’s capability to optimize UAV designs for a variety of mission scenarios, including specialized tasks such as intelligence, surveillance, and reconnaissance (ISR), combat air patrol (CAP), and Suppression of Enemy Air Defenses (SEAD). This flexibility and adaptability was demonstrated through a case study, showcasing the method’s effectiveness in tailoring UAV configurations to meet specific operational requirements while balancing trade-offs between aerodynamic efficiency, stealth, and structural weight. Additionally, these results underscore the transformative impact of integrating AI into the early stages of the design process, facilitating rapid prototyping and innovation in aerospace engineering. Consequently, the current work demonstrates the potential of AI-driven optimization to revolutionize UAV design by providing a robust and effective tool for solving complex engineering problems.
Open Access
Advancing fault diagnosis in aircraft landing gear: an innovative two-tier machine learning approach with intelligent sensor data management
(AIAA, 2024-01-04) Kadripathi, K. N.; Ignatyev, Dmitry; Tsourdos, Antonios; Perrusquía, Adolfo
Revolutionizing aircraft safety, this study unveils a pioneering two-tier machine learning model specifically designed for advanced fault diagnosis in aircraft landing gear systems. Addressing the critical gap in traditional diagnostic methods, our approach deftly navigates the challenges of sensor data anomalies, ensuring robust and accurate real-time health assessments. This innovation not only promises to enhance the reliability and safety of aviation but also sets a new benchmark in the application of intelligent machine-learning solutions in high-stakes environments. Our method is adept at identifying and compensating for data anomalies caused by faulty or uncalibrated sensors, ensuring uninterrupted health assessment. The model employs a simulation-based dataset reflecting complex hydraulic failures to train robust machine learning classifiers for fault detection. The primary tier focuses on fault classification, whereas the secondary tier corrects sensor data irregularities, leveraging redundant sensor inputs to bolster diagnostic precision. Such integration markedly improves classification accuracy, with empirical evidence showing an increase from 95.88% to 98.76% post-imputation. Our findings also underscore the importance of specific sensors—particularly temperature and pump speed—in evaluating the health of landing gear, advocating for their prioritized usage in monitoring systems. This approach promises to revolutionize maintenance protocols, reduce operational costs, and significantly enhance the safety measures within the aviation industry, promoting a more resilient and data-informed safety infrastructure.
Open Access
Adversarial proximal policy optimisation for robust reinforcement learning
(AIAA, 2024-01-04) Ince, Bilkan; Shin, Hyo-Sang; Tsourdos, Antonios
Robust reinforcement learning (RL) aims to develop algorithms that can effectively handle uncertainties and disturbances in the environment. Model-free methods play a crucial role in addressing these challenges by directly learning optimal policies without relying on a pre-existing model of the environment. This abstract provides an overview of model-free methods in robust RL, highlighting their key features, advantages, and recent advancements. Firstly, we discuss the fundamental concepts of RL and its challenges in uncertain environments. We then delve into model-free methods, which operate by interacting with the environment and collecting data to learn an optimal policy. These methods typically utilize value-based or policy-based approaches to estimate the optimal action-value function or the policy directly, respectively. To enhance robustness, model-free methods often incorporate techniques such as exploration-exploitation strategies, experience replay, and reward shaping. Exploration-exploitation strategies facilitate the exploration of uncertain regions of the environment, enabling the discovery of more robust policies. Experience replay helps improve sample efficiency by reusing past experiences, allowing the agent to learn from a diverse set of situations. Reward shaping techniques provide additional guidance to the RL agent, enabling it to focus on relevant features of the environment and mitigate potential uncertainties. In this paper, a robust reinforcement learning methodology is adapted utilising a novel Adversarial Proximal Policy Optimisation (A-PPO) method integrating an Adaptive KL penalty PPO. Comparison is made with DQN, DDQN and a conventional PPO algorithm.
Open Access
AI-based multifidelity surrogate models to develop next generation modular UCAVs
(AIAA, 2023-01-19) Karali, Hasan; Inalhan, Gokhan; Tsourdos, Antonios
The next generation low-cost modular unmanned combat aerial vehicles (UCAVs) provide the opportunity to implement innovative solutions to complex tasks, while also bringing new challenges in design, production, and certification subjects. Solving these problems with tools that provide fast modeling in line with the digital twin concept is possible. In this work, we develop an artificial intelligence (AI) based multifidelity surrogate model to determine performance parameters of innovative modular UCAVs. First, we develop a data generation algorithm that includes a high-fidelity model based on computational fluid dynamics methods and a low-fidelity model based on computational aerodynamic approaches. In the next step, a new transfer learning-based surrogate model is generated using multifidelity data. Thanks to this approach, the developed AI model more accurately predicted the flow conditions that were missing in the high-fidelity data with the data obtained from the low-order model. The performance of the proposed AI-based surrogate model is to be investigated in terms of accuracy, robustness, and computational cost using a generic modular UCAV configuration.
Open Access
AI-driven multidisciplinary conceptual design of unmanned aerial vehicles
(AIAA, 2024-01-04) Karali, Hasan; Inalhan, Gokhan; Tsourdos, Antonios
This paper presents a multidisciplinary conceptual design framework for unmanned aerial vehicles based on artificial intelligence-driven analysis models. This approach leverages AI- driven analysis models that include aerodynamics, structural mass, and radar cross-section predictions to bring quantitative data to the initial design stage, enabling the selection of the most appropriate configuration from various optimized concept designs. Due to the design optimization cycle, the initial dimensions of key components such as the wing, tail, and fuselage are provided more accurately for later design activities. Simultaneously, the generated structure enables more suitable design point selection through the feedback loop within the design iteration. Therefore, in addition to reducing design costs, this approach also offers a substantial time advantage in the overall design process.
Open Access
AI-driven unmanned aerial system conceptual design with configuration selection
(IEEE, 2023-08-02) Karali, Hasan; Inalhan, Gokhan; Tsourdos, Antonios
This paper presents an intelligent conceptual design framework for the configuration selection of aerial vehicles. In this approach, the quantitative data is brought to the earliest stage of design utilizing AI-driven analysis models and it allows to choose the most suitable one among the possible configurations. Thanks to the design optimization cycle, the initial dimensions of the main components such as the wing, tail and fuselage are more accurately provided for later design activities. At the same time, the generated structure provides a more appropriate design point selection thanks to the feedback loop in design iteration. Thus, while reducing the design cost, a significant time advantage is also provided in the design process. The paper presents a generic use case based on a high-performance combat UAV design study to demonstrate the abilities of the proposed model.
Open Access
AI-enabled interference mitigation for autonomous aerial vehicles in urban 5G networks
(MDPI, 2023-10-13) Warrier, Anirudh; Al-Rubaye, Saba; Inalhan, Gokhan; Tsourdos, Antonios
Integrating autonomous unmanned aerial vehicles (UAVs) with fifth-generation (5G) networks presents a significant challenge due to network interference. UAVs’ high altitude and propagation conditions increase vulnerability to interference from neighbouring 5G base stations (gNBs) in the downlink direction. This paper proposes a novel deep reinforcement learning algorithm, powered by AI, to address interference through power control. By formulating and solving a signal-to-interference-and-noise ratio (SINR) optimization problem using the deep Q-learning (DQL) algorithm, interference is effectively mitigated, and link performance is improved. Performance comparison with existing interference mitigation schemes, such as fixed power allocation (FPA), tabular Q-learning, particle swarm optimization, and game theory demonstrates the superiority of the DQL algorithm, where it outperforms the next best method by 41.66% and converges to an optimal solution faster. It is also observed that, at higher speeds, the UAV sees only a 10.52% decrease in performance, which means the algorithm is able to perform effectively at high speeds. The proposed solution effectively integrates UAVs with 5G networks, mitigates interference, and enhances link performance, offering a significant advancement in this field.
Open Access
Airborne behaviour monitoring using Gaussian processes with map information
(Institution of Engineering and Technology, 2013-07-31T00:00:00Z) Oh, Hyondong; Shin, Hyosang; Kim, Seungkeun; Tsourdos, Antonios; White, Brian A.
This paper proposes an airborne behaviour monitoring methodology of ground vehicles based on a statistical learning approach with domain knowledge given by road map information. To monitor and track the moving ground target using UAVs aboard a moving target indicator, an interactive multiple model (IMM) filter is firstly applied. {\color{red}The IMM filter consists of an on-road moving mode using a road-constrained filter and an off-road moving mode using a conventional filter.} Mode probability is also calculated from the IMM filter, and it provides deviation of the vehicle from the road. Then, a novel hybrid algorithm for anomalous behaviour recognition is developed using a Gaussian process regression on velocity profile along the one-dimensionalised position of the vehicle, as well as the deviation of the vehicle. To verify the feasibility and benefits of the proposed approach, a numerical simulation is performed using realistic car trajectory data in a city traffic.
Open Access
Airborne mapping of complex obstacles using 2D Splinegon
(2008-06-04T00:00:00Z) Lazarus, Samuel B.; Shanmugavel, Madhavan; Tsourdos, Antonios; Zbikowski, Rafal; White, Brian A.
This paper describes a recently proposed algorithm in mapping the unknown obstacle in a stationary environment where the obstacles are represented as curved in nature. The focus is to achieve a guaranteed performance of sensor based navigation and mapping. The guaranteed performance is quantified by explicit bounds of the position estimate of an autonomous aerial vehicle using an extended Kalman filter and to track the obstacle so as to extract the map of the obstacle. This Dubins path planning algorithm is used to provide a flyable and safe path to the vehicle to fly from one location to another. This description takes into account the fact that the vehicle is made to fly around the obstacle and hence will map the shape of the obstacle using the 2D-Splinegon technique. This splinegon technique, the most efficient and a robust way to estimate the boundary of a curved nature obstacles, can provide mathematically provable performance guarantees that are achievable in practice.
Open Access
Aircraft to operations communication analysis and architecture for the future aviation environment
(IEEE, 2021-11-15) Whitworth, Huw; Al-Rubaye, Saba; Tsourdos, Antonios; Jiggins, Julia; Silverthorn, Nigel; Thomas, Karim
Fifth Generation (5G) systems are envisaged to support a wide range of applications scenarios with varying requirements. 5G architecture includes network slicing abilities which facilitate the partitioning of a single network infrastructure on to multiple logical networks, each tailored to a given use case, providing appropriate isolation and Quality of Service (QoS) characteristics. Radio Access Network (RAN) slicing is key to ensuring appropriate QoS over multiple domains; achieved via the configuration of multiple RAN behaviours over a common pool of radio resources. This Paper proposes a novel solution for efficient resource allocation and assignment among a variety of heterogeneous services, to utilize the resources while ensuring maximum QoS for network services. First, this paper evaluates the effectiveness of different wireless data bearers. Secondly, the paper proposes a novel dynamic resource allocation algorithm for RAN slicing within 5G New Radio (NR) networks utilising cooperative game theory combined with priority-based bargaining. The impact of this work to industry is to provide a new technique for resource allocation that utilizes cooperative bargaining to ensure all network services achieve minimum QoS requirements – while using application priority to reduce data transfer time for key services to facilitate decreased turnaround time at the gate.
Open Access
Airport connectivity optimization for 5G ultra-dense networks
(IEEE, 2020-06-08) Al-Rubaye, Saba; Tsourdos, Antonios
The rapid increase of air traffic demand and complexity of radio access network motivate developing scalable wireless communications by adopting system intelligence. The lack of adaptive reconfiguration in radio transmission systems may cause dramatic impacts on the traffic management concerning congestion and demand-capacity imbalances driving the industry to jointly access licensed and unlicensed bands for improved airport connectivity. Therefore, intelligent system is embedded into fifth generation (5G) ultra-dense networks (UDNs) to provision dense and irregular deployments that maintain extended coverage and also to improve the energy-efficiency for the entire airport network providing high speed services. To define the technical aspects of this solution, this paper addresses new intelligent technique that configures the coverage and capacity factors of radio access network considering the changes in air traffic demands. This technique is analysed through mathematical models that employ power consumption constraints to support dynamic traffic control requirements to improve the overall network capacity. The presented problem is formulated and exactly solved for medium or large airport air transportation network. The power optimization problem is solved using linear programming with careful consideration to latency and energy efficiency factors. Specifically, an intelligent pilot power method is adopted to maintain the connectivity throughout multi-interface technologies by assuming minimum power requirements. Numerical and system-level analysis are conducted to validate the performance of the proposed schemes for both licenced macrocell Long-Term Evolution (LTE) and unlicensed wireless fidelity (WiFi) topologies. Finally, the insights of problem modelling with intelligent techniques provide significant advantages at reasonable complexity and brings the great opportunity to improve the airport network capacity
Open Access
Analysis of optimization strategies for solving space manoeuvre vehicle trajectory optimization problem
(Springer, 2017-12-15) Chai, Runqi; Savvaris, Al; Tsourdos, Antonios
In this paper, two types of optimization strategies are applied to solve the Space Manoeuvre Vehicle (SMV) trajectory optimization problem. The SMV dynamic model is constructed and discretized applying direct multiple shooting method. To solve the resulting Nonlinear Programming (NLP) problem, gradient-based and derivative free optimization techniques are used to calculate the optimal time history with respect to the states and controls. Simulation results indicate that the proposed strategies are effective and can provide feasible solutions for solving the constrained SMV trajectory design problem.
Open Access
Analysis of the traffic conflict situation for speed probability distributions
(Cambridge University Press, 2023-03-30) Öreg, Zs.; Shin, Hyo-Sang; Tsourdos, Antonios
The increasingly widespread application of drones and the emergence of urban air mobility leads to a challenging question in airspace modernisation: how to create a safe and scalable air traffic management system that can handle the expected density of operations. Increasing the number of vehicles in a given airspace volume and enabling routine operations are essential for these services to be economically viable. However, a higher density of operations increases risks, poses a great challenge for coordination and necessitates the development of a novel solution for traffic management. This paper contributes to the research towards such a strategy and the field of airspace management by calculating and analysing the conflict probability in an en-route, free-flight scenario for autonomous vehicles. Analytical methods are used to determine the directional dependence of conflict probabilities for exponential and normal prescribed speed probability distributions. The notions of geometric and speed conflict are introduced and distinguished throughout the calculations of the paper. The effect of truncating the set of available flight speeds is also investigated. The sensitivity of the calculated results to speed and heading perturbations is studied within the analytical framework and verified by numerical simulations. Results enable a fresh approach to conflict detection and resolution through distribution shaping and are intended to be used in an integrated, stochastic coordination framework.
Open Access
Analysis of wireless connectivity applications at airport surface
(IEEE, 2020-04-30) Ayub, Shahid; Petrunin, Ivan; Tsourdos, Antonios; Xu, Zhengjia
The main objective of the current work is to carry out the research to explore the potential wireless communication technologies that can be used during a flight operation at the airport surface for current and potential data applications in future. An important part of this work is the analysis of these services and applications from the perspective of understanding the stakeholders and communication means involved. Different communication services including both critical and non-critical ones are analyzed for aircrafts, airlines, and airport connectivity covering flight stages from landing at the airport to taking off from the airport. We are also proposing the ways of more effective use of communication means including the proposed measures for throughput improvement in order to better meet the needs of the airport stakeholders
Open Access
Anomaly detection of aircraft engine in FDR (flight data recorder) data
(IET, 2018-05-21) Lee, Chang-Hun; Shin, Hyosang; Tsourdos, Antonios; Skaf, Zakwan
This paper deals with detection of anomalous behaviour of aircraft engines in FDR (flight data recorder) data to improve airline maintenance operations. To this end, each FDR data that records different flight patterns is first sampled at a fixed time interval starting at the take-off phase, in order to map each FDR data into comparable data space. Next, the parameters related to the aircraft engine are only selected from the sampled FDR data. In this analysis, the feature points are chosen as the mean value of each parameter within the sampling interval. For each FDR data, the feature vector is then formed by arranging all feature points. The proposed method compares the feature vectors of all FDR data and detects an FDR data in which the abnormal behaviour of the aircraft engine is recorded. The clustering algorithm called DBSCAN (density-based spatial clustering of applications with noise) is applied for this purpose. In this paper, the proposed method is tested using realistic FDR data provided by NASA's open database. The results indicate that the proposed method can be used to automatically identify an FDR data in which the abnormal behaviour of the aircraft engine is recorded from a large amount of FDR data. Accordingly, it can be utilized for a high-level diagnosis of engine failure in airline maintenance operations.
Open Access
Anonymous hedonic game for task allocation in a large-scale multiple agent system
(IEEE, 2018-08-20) Jang, Inmo; Shin, Hyosang; Tsourdos, Antonios
This paper proposes a novel game-theoretical autonomous decision-making framework to address a task allocation problem for a swarm of multiple agents. We consider cooperation of self-interested agents, and show that our proposed decentralized algorithm guarantees convergence of agents with social inhibition to a Nash stable partition (i.e., social agreement) within polynomial time. The algorithm is simple and executable based on local interactions with neighbor agents under a strongly connected communication network and even in asynchronous environments. We analytically present a mathematical formulation for computing the lower bound of suboptimality of the outcome, and additionally show that at least 50% of suboptimality can be guaranteed if social utilities are nondecreasing functions with respect to the number of coworking agents. The results of numerical experiments confirm that the proposed framework is scalable, fast adaptable against dynamical environments, and robust even in a realistic situation.