CPS

Cyber-Physical Systems

Project RAILS (Roadmaps for AI integration in the raiL Sector) selected for EU funding (Horizon2020 – Shift2Rail JU)

2019-11-12

The research project named RAILS (Roadmaps for AI integration in the raiL Sector) has been selected for EU funding by the Horizon 2020 Shift2Rail Joint Undertaking (call ID: S2R-OC-IPX-01-2019). The project will be in cooperation between Linnaeus University, Italian Interuniversity Consortium for Informatics (CINI), Delft University of Technology, University of Leeds, and will leverage on the input from big industry players like Hitachi Rail STS.

 

PROJECT ABSTRACT

The overall objective of the RAILS research project is to investigate the potential of Artificial Intelligence (A.I.) approaches in the rail sector and contribute to the definition of roadmaps for future research in next generation signalling systems, operational intelligence, and network management. RAILS will address the training of PhD students to support the research
capacity in A.I. within the rail sector across Europe by involving research institutions in four different countries with a combined background in both computer science and transportation systems. RAILS will produce knowledge, ground breaking research and experimental proof-of-concepts for the adoption of A.I. in rail automation, predictive maintenance and defect detection, traffic planning and capacity optimization. To that aim, RAILS will combine A.I. paradigms with the Internet of Things, in order to leverage on the big amount of data generated by smart sensors and applications. The research activities will be conducted in continuity with ongoing research in railways, but the methodological and technological concepts developed in RAILS are expected to stimulate further innovation providing new research directions to improve reliability, maintainability, safety, security, and performance. With respect to safety, emerging threats and certification issues will be addressed when adopting A.I. in autonomous and cooperative driving, based on the concepts of “explainable A.I.” and “Trustworthy AI”. With respect to cyber-physical threat detection, innovative approaches will be developed based on A.I. models like Artificial Neural Networks and Bayesian Networks together with multi-sensor data fusion and artificial vision. Resilience and optimization techniques based on genetic algorithms and self-healing will be addressed to face failures and service disruptions as well as to increase efficiency and line capacity. All those techniques will pave the way to the development of the new “Railway 4.0”.

RAILS_leaflet_final

LNU Project Page

CORDIS Page

RAILS Project Website

Paper on Data-Driven Fault Diagnosis to be presented at 4th International Conference on System Reliability and Safety (sponsored by IEEE)

2019-11-04

The paper entitled “Data-Driven Fault Diagnosis of Once-Through Benson Boilers” (Mehdi Saman Azari, Francesco Flammini, Stefania Santini, Mauro Caporuscio) will be presented at the 4th International Conference on System Reliability and Safety (ICSRS’19), sponsored by the IEEE, which will be held in Rome (Italy) on November 20-22, 2019.

The new PhD student Mehdi Saman Azari will attend the conference and present the paper, which will be published in the IEEE Digital Library.

Congratulations to Mehdi for his first paper as a PhD student at LNU!

 

Abstract

Fault Diagnosis (FD) of once-through Benson boilers, as a crucial equipment of many thermal power plants, is of paramount importance to guarantee continuous performance. In this study, a new fault diagnosis methodology based on data-driven methods is presented to diagnose faults in once-through Benson boilers. The present study tackles this issue by adopting a combination of data-driven methods to improve the robustness of FD blocks. For this purpose, one-class versions of minimum spanning tree and K-means algorithms are employed to handle the strong interaction between measurements and part load operation and also to reduce computation time and system training error. Furthermore, an adaptive neuro-fuzzy inference system algorithm is adopted to improve accuracy and robustness of the proposed fault diagnosing system by fusion of the output of minimum spanning tree (MST) and K-means algorithms. Performance of the presented scheme against six major faults is then assessed by analyzing several test scenarios.

 

UPDATE February 17th 2020

The paper is now available in the IEEE Digital Library and accessible at the following link:

https://ieeexplore.ieee.org/document/8987699

 

Study on smart-troubleshooting accepted for publication on top Elsevier journal

2019-09-08

The paper entitled “Smart-Troubleshooting Connected Devices: Concept, Challenges and Opportunities” (Mauro Caporuscio, Francesco Flammini, Narges Khakpour, Prasannjeet Singh, Johan Thornadtsson) has been accepted for publication on Future Generation Computer Systems (Elsevier, Impact Factor: 5.768). The paper includes the results achieved during the SEED project entitled Smart-Troubleshooting in the Connected Society in cooperation with Sigma Technology, and addresses several challenges towards self-healing for resilient IoT.

 

Abstract

Today’s digital world and evolving technology has improved the quality of our lives but it has also come with a number of new threats. In the society of smart-cities and Industry 4.0, where many cyber-physical devices connect and exchange data through the Internet of Things, the need for addressing information security and solve system failures becomes inevitable. System failures can occur because of hardware failures, software bugs or interoperability issues. In this paper we introduce the industry-originated concept of “smart-troubleshooting” that is the set of activities and tools needed to gather failure information generated by heterogeneous connected devices, analyze them, and match them with troubleshooting instructions and software fixes. As a consequence of implementing smart-troubleshooting, the system would be able to self-heal and thus become more resilient. This paper aims to survey frameworks, methodologies and tools related to this new concept, and especially the ones needed to model, analyze and recover from failures in a (semi)automatic way. Smart-troubleshooting has a relation with event analysis to perform diagnostics and prognostics on devices manufactured by different suppliers in a distributed system. It also addresses management of appropriate product information specified in possibly unstructured formats to guide the troubleshooting workflow in identifying fault-causes and solutions. Relevant research is briefly surveyed in the paper in order to highlight current state-of-the-art, open issues, challenges to be tackled and future opportunities in this emerging industry paradigm.

Digital Object Identifier:

https://doi.org/10.1016/j.future.2019.09.004

Research on intelligent cybersecurity at IEEE SMC 2019

2019-07-29

The paper entitled “A Review of Intelligent Cybersecurity with Bayesian Networks” (Mauro Pappaterra, Francesco Flammini) has been accepted for conference presentation and publication in the proceedings of the 2019 IEEE SMC international conference, i.e. the flagship event of the  IEEE Systems, Man and Cybernetics society, special session on Homeland Security: Tools and Methodologies.

The paper will be presented by master student Mauro Pappaterra, who has been granted registration costs and travel expenses by the Department of Computer Science and Media Technology.

 

Abstract

Cybersecurity threats have surged in the past decades. Experts agree that conventional security measures will soon not be enough to stop the propagation of more sophisticated and harmful cyberattacks. Recently, there has been a growing interest in mastering the complexity of cybersecurity by adopting methods borrowed from Artificial Intelligence (AI) in order to support automation. In this paper, we provide a brief survey and some hints about Bayesian Network applications to intelligent cybersecurity in order to enable quantitative threat assessment for superior risk analysis and situation awareness.

See also:

https://lnu.se/en/meet-linnaeus-university/current/news/2019/research-on-intelligent-cyber-security-to-be-presented-at-ieee-conference/

 

UPDATE, August 20th 2019

Mauro has also been selected as “Student or Young Professional Travel Grant Winner” for the SMC 2019 conference.

 

UPDATE, October 7th 2019

A picture of Mauro’s presentation:

 

UPDATE, December 2nd 2019

The paper is finally available from IEEE Digital Library at the following link:

https://ieeexplore.ieee.org/document/8913864

Plain text citation:

M. J. Pappaterra and F. Flammini, “A Review of Intelligent Cybersecurity with Bayesian Networks,” 2019 IEEE International Conference on Systems, Man and Cybernetics (SMC), Bari, Italy, 2019, pp. 445-452.
doi: 10.1109/SMC.2019.8913864
URL: http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8913864&isnumber=8913838

Pioneering research on Virtual Coupling published on top IEEE journal

2019-07-24

The paper entitled “ERTMS/ETCS Virtual Coupling: Proof of Concept and Numerical Analysis”, describing a pioneering research developed in cooperation between LNU and the University of Naples Federico II, has been accepted for publication on the top journal about smart-transportation, i.e. “IEEE Transactions on Intelligent Transportation Systems”.

The paper can be accessed online from the following link:

https://ieeexplore.ieee.org/document/8737771

 

Abstract:

Railway infrastructure operators need to push their network capacity up to their limits in high-traffic corridors. Virtual coupling is considered among the most relevant innovations to be studied within the European Horizon 2020 Shift2Rail Joint Undertaking as it can drastically reduce headways and thus increase the line capacity by allowing to dynamically connect two or more trains in a single convoy. This paper provides a proof of concept of Virtual coupling by introducing a specific operating mode within the European rail traffic management system/European train control system (ERTMS/ETCS) standard specification, and by defining a coupling control algorithm accounting for time-varying delays affecting the communication links. To that aim, we define one ploy to enrich the ERTMS/ETCS with Virtual coupling without changing its working principles and we borrow a numerical analysis methodology used to study platooning in the automotive field. The numerical analysis is also provided to support the proof of concept with quantitative results in a case-study simulation scenario.

Talk: Towards Secure Architectural Adaptation at SEAMS 2019

2019-05-26

A few of our researchers are now in Montreal, Canada for SEAMS 2019 (Symposium on Software Engineering for Adaptive and Self-Managing Systems 2019 conference). The objective of SEAMS is to bring together researchers and practitioners from diverse areas to investigate, discuss, and examine the fundamental principles, the state of the art, and critical challenges of engineering self-adaptive and self-managing systems.

On Sunday May 26th, Narges Khakpour will give a presentation of the paper entitled Towards Secure Architectural Adaptation (authored by: Narges Khakpour, Charilaos Skandylas, Goran Saman Nariman, and Danny Weyns), accepted for publication in the book of proceedings of the conference.

As any software system, a self-adaptive system is subject to security threats. However, applying self-adaptation may introduce additional threats. So far, little research has been devoted to this important problem. In this paper, we propose an approach for vulnerability analysis of architecture-based adaptations in self-adaptive systems using threat modeling and analysis techniques. To this end, we specify components’ vulnerabilities and the system architecture formally and generate an attack model that describes the attacker’s strategies to attack the system when adaptation is applied by exploiting different vulnerabilities. We use a set of security metrics to quantitatively assess the security risks of adaptations based on the produced attack model which enables the system to consider security aspects while choosing an adaptation to apply to the system. We automate and incorporate our approach into the Rainbow framework, allowing for secure architectural adaptations at runtime. To evaluate the effectiveness of our approach, we apply it on a simple document storage system and on the ZNN system.

For more information please click here.

Co-charing the industry/project dissemination session at CRITIS 2019

2019-05-17

The 14th International Conference on Critical Information Infrastructures Security, CRITIS 2019, will be held in Linköping on September 23-25 2019.

CRITIS 2019 aims at bringing together researchers, professionals from academia, critical (information) infrastructure operators, industry, defence sector and governmental organisations working in the field of the security of critical (information) infrastructure systems. Moreover, CRITIS aims to encourage and inspire early stage and open-minded researchers in this demanding multi-disciplinary field of research.

Francesco Flammini, Senior Lecturer at Linnaeus University, is a part of the Technical Committee of the conference and will be co-charing the industry/project dissemination session.

For more information about the conference, see the conference website.

 

CALL FOR CONTRIBUTIONS — Industrial/practical experience reports

https://critis2019.on.liu.se/CFP-CRITIS2019-IndExp.pdf

Critical infrastructures must fulfil dependability requirements that impose the use of rigorous techniques during procurement, development, commissioning and training/preparedness, as well as in regulatory audits of the operational systems.

In this CRITIS special session we solicit short presentations from an industrial perspective addressing any aspect of such processes and of the supervision of critical operations. Reports of actual cases are welcome including success stories or failure/emergency management operations with the aim of sharing lessons learnt. Contributions to this session are also welcome by academics working on research projects with industrial partners who have driven experimental evaluations of research outcomes and prototypes with the help of real-world data, or have validated hypotheses by performing surveys and interviews.

The submissions in this session have the following characteristics:

  • Papers of 1-2 pages in length (including references and figures), using the Springer format.
  • The submissions are NOT anonymised
  • The title of the submission must include the words “Industry/Experience report”

The submissions in this session will be evaluated by the two session chairs:

  • Sokratis K. Katsikas (NTNU, Norway & Open University of Cyprus, Cyprus)
  • Francesco Flammini (Linnaeus University, Sweden)

The final versions of the contributions (reflecting the comments by the session chairs and necessary improvements) will be shown on the conference web page and presented during the conference, and can be later extended and published in other venues.

Important dates:

  • Submission deadline: 9th June 2019
  • Notification of acceptance: 20th June 2019
  • Final version submission: 9th September 2019

UPDATE SEPTEMBER 23rd 2019

Final program

CRITIS 2019_Smart-Troubleshooting_POSTER

 

UPDATE DECEMBER 22nd 2019

The industry session white paper has been published in CRITIS’19 conference proceedings and it is now accessible here.

 

DisCoRail 2019 – International Workshop on Distributed Computing in Future Railway Systems

2019-04-17

DisCoRail 2019 is a satellite workshop of DisCoTec 2019, held on June 17, 2019 in Lyngby, Denmark. Francesco Flammini, Linnæus University, is invited as a speaker and will give a talk on Towards Railway Virtual Coupling.

DisCoTec gathers several conferences and workshops that cover a broad spectrum of distributed computing subjects, ranging from theoretical foundations and formal description techniques to systems research issues. The aim of the DisCoRail’19 workshop is to discuss the following topics

  • how distributed computing has changed, and will even more change, the particular domain of railway signaling and train control systems
  • how formal techniques can help to address problems arising from this change.

For more information about DisCoRail 2019, see the conference website.

The final technical program is now available at this link.

//Diana Unander

 

Update June 17th

Abstracts:

https://www.discotec.org/2019/DisCoRailAbstracts.pdf

Slides of the presentation:

Flammini_DISCORAIL

Picture from the talk:

IEEE SMC’19 October 6-9, 2019 – Bari, Italy

2019-03-06

IEEE SMC 2019 is the annual premier conference of the IEEE Systems, Man, and Cybernetics Society. It represents an international forum for researchers and practitioners to report up-to-the-minute innovation and development, summarize state-of-the-art, and exchange ideas and advances in all aspects of systems science and engineering, human machine systems, and cybernetics.

The theme of the conference is Industry 4.0 and we would like to pay attention to two of the events that Francesco Flammini is the co-organizer for. More information about all the special sessions.

“Symbiotic Autonomous Systems in Smart-Cities and Industry 4.0”, one-day tutorial

Read more on: SMC2019_T8

“Homeland Security: Tools and Methodologies” This special session will bring experts, practitioners and researchers together with the aim to present and discuss all type of innovation related to Homeland Security applications. Expected contributions for this special session will range from the analysis and modelling of all-hazard threats to risk prevention/mitigation strategies and intelligence solutions based on Big Data and OSINT analysis, and from cyber-security of IT, IoT and OT systems to consequence analyses based on simulations or serious games.

You can read more about papers that are particularly welcome here

Important deadlines:
March 31, 2019: deadline for paper submission
June 7, 2019: notification of paper acceptance/rejection
July 7, 2019: deadline for final camera-ready papers.

UPDATE OCTOBER 7th 2019

Pictures taken from the Tutorial on Symbiotic Autonomous Systems

Pictures taken from the Special Session on Homeland Security