UAV Fleet as a Dependable Service for Smart Cities: Model-Based Assessment and Application

Kharchenko, Vyacheslav; Kliushnikov, Ihor; Ruciński, Andrzej; Fesenko, Herman; Illiashenko, Oleg

doi:10.3390/smartcities5030058

Cited by 16 publications

(16 citation statements)

References 50 publications

(99 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It also performs better than the conventional approach. It is very important to assure resilience to cyber attacks and the fault tolerance of UAV-based intelligent systems to monitor severe accidents of critical infrastructure objects, such as NPPs [59], and delivering services for smart cities [60].…”

Section: Discussionmentioning

confidence: 99%

Model and Training Method of the Resilient Image Classifier Considering Faults, Concept Drift, and Adversarial Attacks

et al. 2022

Self Cite

View full text Add to dashboard Cite

Modern trainable image recognition models are vulnerable to different types of perturbations; hence, the development of resilient intelligent algorithms for safety-critical applications remains a relevant concern to reduce the impact of perturbation on model performance. This paper proposes a model and training method for a resilient image classifier capable of efficiently functioning despite various faults, adversarial attacks, and concept drifts. The proposed model has a multi-section structure with a hierarchy of optimized class prototypes and hyperspherical class boundaries, which provides adaptive computation, perturbation absorption, and graceful degradation. The proposed training method entails the application of a complex loss function assembled from its constituent parts in a particular way depending on the result of perturbation detection and the presence of new labeled and unlabeled data. The training method implements principles of self-knowledge distillation, the compactness maximization of class distribution and the interclass gap, the compression of feature representations, and consistency regularization. Consistency regularization makes it possible to utilize both labeled and unlabeled data to obtain a robust model and implement continuous adaptation. Experiments are performed on the publicly available CIFAR-10 and CIFAR-100 datasets using model backbones based on modules ResBlocks from the ResNet50 architecture and Swin transformer blocks. It is experimentally proven that the proposed prototype-based classifier head is characterized by a higher level of robustness and adaptability in comparison with the dense layer-based classifier head. It is also shown that multi-section structure and self-knowledge distillation feature conserve resources when processing simple samples under normal conditions and increase computational costs to improve the reliability of decisions when exposed to perturbations.

show abstract

Section: Discussionmentioning

confidence: 99%

Model and Training Method of the Resilient Image Classifier Considering Faults, Concept Drift, and Adversarial Attacks

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…The SIS/CSIS approach is entropy oriented since the impact of security on safety is characterised by tremendous uncertainty, which grows as physical assets are replaced by cyber assets at an increasing pace, as well as the diversification of cyber threats, alongside the increase in the intensity and impact of cyber wars. Considering the role played by ATSs, first of all, UAVs and UAV fleets in modern wars and their use in smart cities as efficient, robust, and dependable services [ 41 ], shows that the relevance of developing and applying the SIS-based approach appears very high.…”

Section: Methodsmentioning

confidence: 99%

Security-Informed Safety Analysis of Autonomous Transport Systems Considering AI-Powered Cyberattacks and Protection

Illiashenko

Kharchenko

Babeshko

et al. 2023

Entropy

Self Cite

View full text Add to dashboard Cite

The entropy-oriented approach called security- or cybersecurity-informed safety (SIS or CSIS, respectively) is discussed and developed in order to analyse and evaluate the safety and dependability of autonomous transport systems (ATSs) such as unmanned aerial vehicles (UAVs), unmanned maritime vehicles (UMVs), and satellites. This approach allows for extending and integrating the known techniques FMECA (Failure Modes, Effects, and Criticality Analysis) and IMECA (Intrusion MECA), as well as developing the new SISMECA (SIS-based Intrusion Modes, Effects, and Criticality Analysis) technique. The ontology model and templates for SISMECA implementation are suggested. The methodology of safety assessment is based on (i) the application and enhancement of SISMECA considering the particularities of various ATSs and roles of actors (regulators, developers, operators, customers); (ii) the development of a set of scenarios describing the operation of ATS in conditions of cyberattacks and physical influences; (iii) AI contribution to system protection for the analysed domains; (iv) scenario-based development and analysis of user stories related to different cyber-attacks, as well as ways to protect ATSs from them via AI means/platforms; (v) profiling of AI platform requirements by use of characteristics based on AI quality model, risk-based assessment of cyberattack criticality, and efficiency of countermeasures which actors can implement. Examples of the application of SISMECA assessment are presented and discussed.

show abstract

“…The research results are not limited to the use of UAV swarms. Still, they can be extended, e.g., laying paths for ground robots and surface and underwater unmanned vehicles for developing systems for detecting and identifying explosive objects [28] or for civil applications of UAV fleets and swarms for Smart Cities [29], etc.…”

Section: Conflict Of Interestmentioning

confidence: 99%

Deployment of a UAV swarm-based LiFi network in the obstacle-ridden environment: algorithms of finding the path for UAV placement

Leichenko,

Fesenko,

Kharchenko

et al. 2024

reks

View full text Add to dashboard Cite

The subject of this study is unmanned aerial vehicle (UAV)-based wireless networks in an obstacle-ridden environment. The aim of this study is to develop methods and software to ensure reliable LiFi communication using swarm UAVs in an obstacle-ridden environment. The objectives are as follows: 1) to describe the problem of providing a reliable UAV swarm-based LiFi network, requirements for the composition and use of UAVs, and assumptions; 2) to develop the methodology for solving research tasks; 3) to develop the method and algorithms for solving the problem, considering the requirements, assumptions, and practical limitations; 4) to explore the algorithms by developing software for modeling and searching for rational UAV placement to ensure the required UAV-based LiFi network characteristics; 5) to provide experiments and illustrative examples of the developed tool’s application. The following results were obtained. 1) The requirements for the composition and use of UAVs for creating LiFi networks, as well as assumptions and limitations for the methodology development and research task solving. 2) An obstacle avoidance method using the left and right angles algorithm. 3) A method for obstacle avoidance using the controlled waterfall algorithm. 4) A software tool for modeling and searching for rational UAV placement to ensure the required LiFi network characteristics. The tool allows route construction under obstacles in 2D space and a comparison of the developed algorithms for various variants of obstacle placement. Conclusions. The main contribution of this research is a set of methods, algorithms, and software tools for providing communications between two points using LiFi technologies and a swarm of UAVs supporting these communications as transmitters in conditions of mechanical obstacles.

show abstract

UAV Fleet as a Dependable Service for Smart Cities: Model-Based Assessment and Application

Cited by 16 publications

References 50 publications

Model and Training Method of the Resilient Image Classifier Considering Faults, Concept Drift, and Adversarial Attacks

Model and Training Method of the Resilient Image Classifier Considering Faults, Concept Drift, and Adversarial Attacks

Security-Informed Safety Analysis of Autonomous Transport Systems Considering AI-Powered Cyberattacks and Protection

Deployment of a UAV swarm-based LiFi network in the obstacle-ridden environment: algorithms of finding the path for UAV placement

Contact Info

Product

Resources

About