Lidé na fakultě
Ing. Martin Šrotýř, Ph.D.

2024, Applied Sciences, 14 (20), ISSN 2076-3417

In the field of Cooperative Intelligent Transport Systems (C-ITSs), the traditional approach to testing often emphasizes technological parameters, leaving the validation of message content insufficiently addressed. Since the content of these messages is crucial for the correct functioning of C-ITS, this article demonstrates the potential for automated evaluation of C-ITS message content against relevant standards. It leverages our novel tools, Karlos and C-ITS SIM, to facilitate this process. Through detailed laboratory testing and data analysis, the study showcases the effectiveness of these automated solutions in enhancing the accuracy and reliability of message content validation.

Článek v periodiku excerpovaném SCI Expanded

2024, 2024 Smart City Symposium Prague - IEEE PROCEEDINGS, New York, IEEE Press), ISBN 979-8-3503-6096-7, ISSN 2831-5618

In the era of Industry 4.0 and the rise of smart cities, the integration of industrial and telematics systems has become increasingly prevalent, revolutionizing the way we manage and optimize processes. These systems, which encompass everything from manufacturing plants to transportation networks, rely heavily on interconnected devices and data exchange to enhance efficiency and functionality. However, this interconnectedness also brings about a heightened level of vulnerability to cyber threats, emphasizing the critical importance of robust cybersecurity measures. This article specifically delves into a case study of a selected Denial of Service (DoS) cyber attack on industrial networks, highlighting the critical need for such cybersecurity solutions. Current software was utilized to simulate an attack. The results are provided using the software that was created specifically for this type of task, demonstrating the practical application and effectiveness of these cybersecurity measures in real-world scenarios.

Stať ve sborníku z prestižní konf.

2024, Proceedings of the 10th International Conference on Information Systems Security and Privacy 2024, Madeira, SciTePress), p. 682-690), ISBN 978-989-758-683-5, ISSN 2184-4356

With the increasing complexity of cyber attacks, traditional methods for anomaly detection in cybersecurity are insufficient, leading to the necessity of integrating deep learning and neural network approaches. This paper presents a comparative analysis of the most powerful deep learning methods for such anomaly detection. We analysed existing datasets for syslog and dataflow, compared several preprocessing methods and identified their strengths and weaknesses. Additionally, we trained and evaluated several deep learning models to provide a comprehensive overview of the current state-of-the-art in cybersecurity. The CNN model achieves excellent results, with 0.999 supervised and 0.938 semi-supervised F1-score in syslog anomaly detection on the BGL dataset and 0.985 F1-score in dataflow anomaly detection on the NIDS dataset. This research contributes to the field of cybersecurity by aiding researchers and practitioners in selecting effective deep-learning models for robust real-life anomaly detection systems. Our findings highlight the reusability of these models in real-life systems.

Stať ve sborníku z prestižní konf. (Scopus)

2024, The Lawyer Quarterly, 14 (2), p. 198-217), ISSN 1805-840X

In the dynamic realm of autonomous mobility, understanding legal protection for databases is crucial. The upcoming article focuses on key aspects in this area. It clarifies fundamental concepts, including both sui generis and copyright safeguards. Additionally, it outlines important characteristics for assessing potential legal protection. The article also introduces a unique set of coefficients, making complex legal concepts more tangible. This innovative approach offers makers concrete insights into their database’s level of legal protection. By combining theoretical understanding with practical application, the article equips makers in the autonomous mobility sector to implement effective strategies for securing legal protection. Furthermore, the article will delve into simplified typologies of databases within autonomous systems. It will also provide a step-bystep illustration of how to determine the degree of legal protection for these databases. This process will include supplementary information aimed at refining the assessment of legal protection, offering makers the necessary guidance for accurate decisions. Through this comprehensive approach, the article aims to provide makers with practical tools to navigate the complex landscape of database legal protection efficiently.

Článek v periodiku excerpovaném databází Scopus cizojaz.

2023, Symmetry, 15 (7), ISSN 2073-8994

The article presents a novel algorithm for merging Bayesian networks generated by different methods, such as expert knowledge and data-driven approaches, while leveraging a symmetry-based approach. The algorithm combines the strengths of each input network to create a more comprehensive and accurate network. Evaluations on traffic accident data from Prague in the Czech Republic and accidents on railway crossings demonstrate superior predictive performance, as measured by prediction error metric. The algorithm identifies and incorporates symmetric nodes into the final network, ensuring consistent representations across different methods. The merged network, incorporating nodes selected from both the expert and algorithm networks, provides a more comprehensive and accurate representation of the relationships among variables in the dataset. Future research could focus on extending the algorithm to deal with cycles and improving the handling of conditional probability tables. Overall, the proposed algorithm demonstrates the effectiveness of combining different sources of knowledge in Bayesian network modeling.

Článek v periodiku excerpovaném SCI Expanded

2023, 2023 14th International Conference on Information and Communication Systems (ICICS), IEEE Jordan Section), p. 1-6), ISBN 979-8-3503-0786-3, ISSN 2573-3346

With the increasing number of cybersecurity attacks and their increasing complexity, it is necessary to adapt the detection methods to be able to prevent such attacks. The replacement of traditional detection methods based on machine learning with more advanced deep learning and neural network approaches is the crucial step for this. In this paper, we present a comparative analysis of different deep learning models for anomaly detection in syslog. We analysed existing datasets for system logs and compared several preprocessing methods. We evaluated different deep learning models on those preprocessed datasets to provide a comprehensive overview of the current state-of-the-art in cybersecurity. We achieved the best results with the CNN model with 0.999 F1-score on the BGL dataset showing the great potential in such techniques for the real-life models monitoring the system and detecting anomalies.

Stať ve sborníku z prestižní konf. (Scopus)

2023, The Lawyer Quarterly, 13 (4), p. 388-407), ISSN 1805-840X

This paper introduces the issue of personal and non-personal data in autonomous vehicles. Its main objective is to provide a procedure for determining the processed and retained data, to explain the current legal regulation that must be met, and to propose appropriate recommendations for each data category. Current law (and the regulatory framework which it has produced) generally distinguishes between two basic types of data, i.e. non-personal data and personal data. The phenomenon that a combination of several pieces of non-personal data may, under certain circumstances2, result in processing of personal data, which is subject to significant regulation, is not limited solely to the field of autonomous mobility. This paper deals with data classification in autonomous vehicles, focusing on the challenging cases of non-personal data that can turn into personal data. The initial stage involves identifying the data to be processed, followed by the classification of the identified data. Based on this classification, relevant legal obligations and recommendations are described. The primary objective of this article is to provide guidance to data administrators (or, to use the terminology of data protection laws, data controllers) in autonomous mobility, enabling them to identify data and take appropriate measures to ensure compliance with legal regulations. The ultimate aim is to ensure that data controllers adhere to legal requirements, a goal that is critical for all data controllers. Beyond that, this article should be relevant also for other stakeholders in the autonomous mobility ecosystem, such as vehicle manufacturers and their suppliers, software application and service providers, and others.

Článek v periodiku excerpovaném databází Scopus cizojaz.

2023

Tento dokument shrnuje podstatnou právní regulaci dopadající na oblast autonomní mobility a stejně tak relevantní výkladovou praxi ze strany příslušných institucí. Z těchto poznatků následně čerpá při návrzích doporučení legislativního rázu cílených na klíčové hráče na poli autonomní mobility.

Výsledek promítnutý do schvál. strateg. a koncepčních dokumentů

2023, 15th International Congress on Ultra Modern Telecommunications and Control Systems and Workshops (ICUMT), Brussels, IEEE), p. 22-27), ISBN 979-8-3503-9328-6, ISSN 2157-023X

owadays, there are limited capabilities to limit the speed of vehicles or to stop them. The current methods used within communication on the roads use informative messages that are not influencing the movement of the vehicles. Currently, to limit the speed of the vehicles only destructive and invasive methods are used. These methods can lead to threats to the health and lives involved in road traffic. In this paper, we designed and verified a unique system for influencing the speed of vehicles. The test-bed consists of two vehicles that contain COHDA-MK6 OBU devices and a mobile application for managing the vehicles. The verification for the developed system was performed on a race circuit in the Czech Republic with the cooperation of the Czech police. During the testing, two vehicles were going almost 100 km/h and the security forces in a police vehicle successfully stopped the other car. The process for stopping the car consists of the mobile application that sends the C-ITS (Cooperative Intelligent Transport Systems) message that is transmitted to the target vehicle. In this paper, we successfully verified in practice on a race circuit that the proposed system to limit the speed of vehicles is working.

Stať ve sborníku z prestižní konf. (Scopus)

2023, IEEE Intelligent Transportation Systems Magazine, 15 (1), p. 8-22), ISSN 1939-1390

Currently, the number of vehicles in road traffic is increasing, which enhances the variety of traffic situations and needs related to road traffic and safety. A cooperative intelligent transport system (C-ITS) can improve road safety and benefit drivers and traffic participants. The C-Roads specification defines many different use cases for informing road vehicles about speed limits, impending danger, road work, signalized intersections, and more. In this article, we propose a new use case targeting the need for Integrated Rescue System services to slow down or stop selected vehicles that are violating rules. Unlike most use cases in C-Roads, in our case, it is not enough to only notify the driver’s vehicle; it must also be slowed down or stopped completely. This intervention requires addressing issues from a technical and a procedural/legal point of view. In this work, we define the use case itself, following the templates of the specification in C-Roads. Then, we discuss the issues in terms of secure communication between vehicles and privacy. We also analyze existing protection security techniques against typical cybersecurity attacks and privacy countermeasures. Next, we propose a system architecture concerning appropriate C-ITS messages and communication between vehicles and present an onboard diagnostics simulator implementing the proposed architecture for the core needs of a given use case. Furthermore, we create a practical demonstrator of our proposal based on real vehicle components. Finally, we discuss open research questions and the ongoing development of the use case before the application on the Internet of Vehicles.

Článek v periodiku excerpovaném SCI Expanded

2022

Tento dokument obshauje doporučení, jak by se mělo platné právo dále rozvíjet a zohledňovat současné výzvy a specifika systémů autonomních vozidel s ohledem na ochranu osobních údajů, neboť v současné době jsou některé právní předpisy značně nejednoznačné nebo s fungováním těchto systémů neumějí pracovat. V dokumentu jsou uvedena doporučení, co by se mělo změnit a budou navrženy i konkrétní právní předpisy, kde by k dané změně mělo dojít.

Výsledek promítnutý do schvál. strateg. a koncepčních dokumentů

2022

Součástí tohoto dokumentu je návrh legislativních doporučení pro rozvoj zpracování včetně uchovávání neosobních dat v inteligentních dopravních systémech a autonomním řízení . Kromě toho je také provedena identifikace klíčových oblastí právní úpravy, vč. konkrétních právních předpisů.

Výsledky promítnuté do právních předpisů a norem

2022

Cílem předkládaného dokumentu je analýza stávajícího právního rámce České republiky a Evropské unie a identifikace oblastí právní regulace, které mají či v budoucnu mohou mít vliv na všechny aspekty provozu automatizovaných vozidel v České republice (tj. schvalování automatizovaných vozidel do provozu, registrace, provoz na pozemních komunikacích, odpovědnost za škodu způsobenou provozem automatizovaného vozidla, výkon veřejné moci, zajištění kybernetické bezpečnosti a ochrany osobních údajů atp.). Tato analýza bude zpracována pro každý stupeň automatizace dle standardu SAE J3016 s důrazem na stupeň 3 a vyšší, z pohledu práva však bude rozdělení aplikováno na vozidla, kde řidič je ve vozidle přítomen a může předat řízení vozidla autonomnímu systému, ale zároveň může ovládání vozidla kdykoliv převzít (resp. je povinen převzít v případě, že je k tomu vozidlem vyzván) a na vozidla, kde je řízení předáno autonomnímu systému a řidič navíc nemusí být ve vozidle přítomen, kdy možnost převzetí řízení řidičem není možné a veškeré řízení vozidla zajišťují příslušné technické systémy ve vozidle. Z pohledu právního řádu se v tomto případě jedná o dvě zcela odlišné situace, které je nutné odpovídajícím způsobem zohlednit v právním řádu.

Výsledky promítnuté do směrnic a nelegisl. předpisů

2022

Soubor doporučení vychází z provedených analýz a představuje klíčový dokument pro zhodnocení povahy, rozsahu a způsobu zpracování včetně uchovávání neosobních dat v různých etapách vývoje a provozu inteligentních dopravních systémech a autonomním řízení.

Výsledek promítnutý do schvál. strateg. a koncepčních dokumentů

2022, Sustainable Management of Manufacturing Systems in Industry 4.0, Springer Science and Business Media Deutschland GmbH), p. 15-29), ISBN 978-3-030-90461-6, ISSN 2522-8609

This overview chapter lists the various use cases where vehicle-to-vehicle communication or vehicle-to-infrastructure is used and also presents selected results of performed testing of the pilot project (C-ROADS) of C-ITS technology in the Czech Republic. Communication is important for different road situations. Currently, use cases for warning messages for drivers are being tested internationally, and the Czech Republic is also involved in this testing through the C-ROADS Czech Republic project. The below list of use cases is not exhaustive, but represents a comprehensive list of major situations in which dangerous situations may occur that endanger the lives of all road users. The chapter is divided into two basic parts. The first part contains a list of use cases for testing. The second part deals with the C-ITS testing in real traffic conditions within the C-ROADS CZ project. © 2022, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG.

Kapitola v knize s nadnárodní působností

2021

V tomto dokumentu jsou uvedeny dopravní a provozní data a jejich rozsah, která jsou zpracovávána a uchovávána v rámci systémů autonomního řízení ve 3 oblastech zpracování: data uvnitř systému autonomního vozidla; data v komunikačních sítích a aktivních prvcích; data v koncových bodech, tj. dalších vozidlech, inteligentní infrastruktuře apod.

Výzkumná zpráva v češtině

2021, 2021 Smart City Symposium Prague, Piscataway, IEEE Signal Processing Society), ISBN 9780738131580

Nowadays, when new technologies are being developed and people are looking for smart solutions, the field of automation and digitization grows faster and faster. The demand on the telecommunications is increasing in economy, healthcare as well as in the transportation. The transportation systems are facing the challenge of smart infrastructure, autonomous vehicles, and its connectivity. The requirements for these systems lie mainly in safety, interoperability and sustainability, especially in the area of cooperative transport systems (C-ITS). This article focuses on a possible approach to test and evaluate C-ITS, threats that have to be ruled out in future, possibilities to ensure connectivity among the vehicles and infrastructure in C-ITS. For these purposes, Czech Technical University in Prague (CTU) and its laboratory Certilab develop special procedures based mainly on the C-ITS SIM tool. This tool ensures validation and verification of C-ITS messages and its interoperability among all equipment. This paper also reviews the already developed applications and proposal of the functionalities that should be implemented for the testing as well as the examples of real usage of the developed tool in testing the communication of C-ITS messages.

Stať ve sborníku z prestižní konf. (Scopus)

2021, Applied Sciences, 11 (20), ISSN 2076-3417

In the area of smart cities, great emphasis is placed on many different fields such as energetics, information systems, and transportation. All of these should lead to a simplification of life thanks to smart technologies. If we talk about the transportation field, the main issues related to this area are safety, traffic efficiency, or the environment. Another condition is the successful acceptance of any new technology by its users. Cooperative systems prove to be a suitable solution for these issues, especially in urban areas. Today, pilot implementations of cooperative systems in European countries are being carried out. However, before they are put into full operation, they need to be tested, evaluated, and assessed. This article focuses on the latter two points, i.e., evaluation and assessment of the cooperative systems. For this purpose, a methodology was created, which describes the procedure chosen in the evaluation and assessment of cooperative systems in the Czech Republic and a demonstration of its use by example. The methodology is focused on three main areas, which in this case are functional evaluation, user acceptance, and impact assessment. For the area of user acceptance, the main source was questionnaires, impact assessment relied on measured data while functional evaluation was based on discussions with the drivers, evaluating the cooperative systems, the measured data, and the expert observations. All collected and measured data were then processed and some of the results of the evaluation of the selected service are presented at the end of this article.

Článek v periodiku excerpovaném SCI Expanded

2021, Revue pro právo a technologie, 12 (24), p. 3-37), ISSN 1804-5383

Autoři se zabývají problematikou ochrany osobních údajů v systémech autonomního řízení představujících celé ekosystémy dílčích vzájemně komunikujících prvků a různorodých spolupracujících entit. Při provozu těchto systémů dochází k přenosu a zpracování obrovského množství dat, mezi kterými lze nalézt i řadu významných osobních údajů, které lze zpracovávat pouze v souladu s právními předpisy. V první části článku jsou tak obecně popsány systémy autonomního řízení, specifikace jejich prvků a představení klíčových hráčů, kteří se podílejí na vytváření nebo dalším zpracování těchto dat. Dále jsou rozpracovány jednotlivé kategorie osobních údajů, se kterými budou předmětné systémy autonomního řízení pracovat nebo v nichž se budou nalézat. Stěžejní částí je pak návrh řešení přístupu k ochraně osobních údajů napříč celým ekosystémem s využitím principů privacy by design a privacy by default. V neposlední řadě se autoři zabývají dílčími právními oblastmi jako je kybernetická bezpečnost a ochrana soukromí v elektronických komunikacích, které v souvislosti s problematikou autonomního řízení nemohou být opomenuty.

Článek v odborném recenzovaném periodiku česky

2020

V rámci tohoto výsledku jsou v dokumentu uvedeny identifikované osobní údaje a jejich rozsah, které jsou zpracovávány v rámci systémů autonomního řízení ve 3 oblastech zpracování: zpracování údajů uvnitř systému autonomního vozidla; zpracování údajů v komunikačních sítích a aktivních prvcích; zpracování údajů v koncových bodech, tj. vozidlech, infrastruktuře apod. Současně bude zohledněno, kde a jak jsou osobní údaje zpracovávány a zda nejde o automatizované individuální rozhodování.

Výzkumná zpráva v češtině

2020, 2020 Smart City Symposium Prague, New York, IEEE Press), ISBN 978-1-7281-6821-0

Nowadays, when a traffic flow increases extremely and cities are more and more congested by vehicles, the information about unexpected events (use-cases) occurred during travels has a big added value. Some of the use-cases are currently defined and can be directly sent to a driver via C-ITS messages. This is crucial in the field of smart cities because there is an effort to reduce emissions, to decrease traffic accidents and make traffic safer, fluent and efficient. Before the whole C-ITS system will be deployed, there is a need to evaluate itself. This paper provides general information about a model of the system and its parts as well as methods for testing and technical evaluation primary based on the log-analysis of the C-ITS communication.

Stať ve sborníku z prestižní konf.

2017, Proceedings of the 8th International Multi-Conference on Complexity, Informatics and Cybernetics, Orlando, Florida, International Institute of Informatics and Systemics), p. 57-63), ISBN 978-1-941763-55-1

Cooperative Systems are part of the Smart Cities solutions and the essential part of the cooperative systems represents guaranteed quality of information exchange both between VANET members (V2V) as well as between VANET and Infrastructure (V2I). This article presents proposal of multiplatform routing protocol designed for combination of two most widely accepted mobile technologies. Properties of proposed protocol are in VANET communication simulation compared with selection of mostly discussed routing protocols designed for VANET conditions.

Vyzvaná předn. uvedená ve sborníku z prestižní konf. (Scopus)

2017, Journal of Systemics, Cybernetics and Informatics, 15, p. 72-78), ISSN 1690-4524

Cooperative Systems are part of the Smart Cities solutions and the essential part of the cooperative systems represents guaranteed quality of information exchange both between VANET members (V2V) as well as between VANET and Infrastructure (V2I). This article presents proposal of multiplatform routing protocol designed for combination of two most widely accepted mobile technologies. Properties of proposed protocol are in VANET communication simulation compared with selection of mostly discussed routing protocols designed for VANET conditions.

Článek v odborném recenzovaném periodiku

2017, 2017 Smart City Symposium Prague, Praha, ČVUT, Fakulta dopravní, Ústav dopravních systémů), ISBN 978-1-5386-3825-5

Smart mobility based on cooperative systems (C-ITS) represents one of the Smart Cities topics. Guaranteed quality of data exchange both between VANET (Vehicular Ad hoc Network) members (V2V) as well as between VANET and Infrastructure (V2I) represents critical condition for suitable functions of the cooperative systems. We proposed hybrid routing protocol for VANET networking based on application of two most widely accepted mobile technologies and theirs combination. Finally, we compared in VANET communication simulation proposed protocol performance with performance of mostly discussed routing protocols designed for VANET conditions.

Stať ve sborníku z prestižní konf.