CPS

Cyber-Physical Systems

New paper on Railway Digital Twins and Artificial Intelligence

2022-09-13

We are pleased to announce that the paper entitled “Railway Digital Twins and Artificial Intelligence: Challenges and Design Guidelines“, whose main author is LNU student Ruth Dirnfeld, has been published on the Springer book of proceedings of the AI4RAILS workshop. We congratulate Ruth for her second international publication, which demonstrates her capability to develop novel and interesting contributions. The work has been carried on within the RAILS EU funded research project.

Book cover

New paper about software verification and validation of safe autonomous cars published on IEEE Access journal

2021-01-21

We are glad to announce this new paper published on a top IEEE open access journal (Impact Factor:  3.7, Scimago Journal Rank: Q1 Computer Science).

The paper is co-authored by Nijat Rajabli, Francesco Flammini, Roberto Nardone and Valeria Vittorini and it is a literature review on the software Verification and Validation (V&V) of safe autonomous cars. The paper is a result of the outstanding job done by Nijat, a Linnaeus University student, during his project work for the course of Current Topics in Computer Science.

We believe that due to its quite extensive topic coverage, the paper can serve as a useful compendium for the many engineers and researchers who are starting to investigate those extremely current and challenging subjects related to the software safety of autonomous road vehicles.

Please find below more detailed information about the paper.

N. Rajabli, F. Flammini, R. Nardone and V. Vittorini, “Software Verification and Validation of Safe Autonomous Cars: A Systematic Literature Review,” in IEEE Access, vol. 9, pp. 4797-4819, 2021, doi: 10.1109/ACCESS.2020.3048047.

Abstract: Autonomous, or self-driving, cars are emerging as the solution to several problems primarily caused by humans on roads, such as accidents and traffic congestion. However, those benefits come with great challenges in the verification and validation (V&V) for safety assessment. In fact, due to the possibly unpredictable nature of Artificial Intelligence (AI), its use in autonomous cars creates concerns that need to be addressed using appropriate V&V processes that can address trustworthy AI and safe autonomy. In this study, the relevant research literature in recent years has been systematically reviewed and classified in order to investigate the state-of-the-art in the software V&V of autonomous cars. By appropriate criteria, a subset of primary studies has been selected for more in-depth analysis. The first part of the review addresses certification issues against reference standards, challenges in assessing machine learning, as well as general V&V methodologies. The second part investigates more specific approaches, including simulation environments and mutation testing, corner cases and adversarial examples, fault injection, software safety cages, techniques for cyber-physical systems, and formal methods. Relevant approaches and related tools have been discussed and compared in order to highlight open issues and opportunities.

Keywords: Vehicles; Autonomous automobiles; Safety; Software; Accidents; Roads; Systematics; Advanced driver assistance systems; automotive engineering; autonomous vehicles; cyber-physical systems; formal verification; intelligent vehicles; machine learning; system testing; system validation; vehicle safety

URL: https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9310181&isnumber=9312710

 

RAILS Project: first deliverable and dissemination results

2020-09-23

Dear Colleagues,
I would like to inform you that the RAILS project has produced its first deliverable that can be downloaded from:
As part of project dissemination activities, we have organized the 1st International Workshop on “Artificial Intelligence for RAILwayS” (AI4RAILS):

https://sites.google.com/view/ai4rails/home-page

The Springer proceedings of AI4RAILS are available at:

https://link.springer.com/book/10.1007/978-3-030-58462-7
and can be downloaded for a limited time (until October 1st 2020) from:
http://edcc.dependability.org/EDCC2020%20WS%20Proceedings%20978-3-030-58462-7.pdf

 

Finally, the paper entitled “Low-Power Wide-Area Networks in Intelligent Transportation: Review and Opportunities for Smart-Railways”, co-authored with Linnaeus University master student Ruth Dirnfeld, has been recently presented at the 23rd IEEE International Conference on Intelligent Transportation Systems (ITSC) according to the following updated program:

https://its.papercept.net/conferences/conferences/ITSC20/program/ITSC20_ContentListWeb_3.html

Presentation slides are available on slideshare.

 

Any feedback on all those initiatives and preliminary results is very much appreciated!

 

Prof. Francesco Flammini

RAILS Technical Manager, AI4RAILS Co-Chair

 

 

Paper on Self-Adaptive Trust-Aware Decentralized Information Flow Control accepted at 1st IEEE International Conference on Autonomic Computing and Self-Organizing Systems

2020-07-11

Congratulations to Charilaos, Narges and Jesper for their paper being accepted at the 1st IEEE International Conference on Autonomic Computing and Self-Organizing Systems (ACSOS 2020)!

Please find below additional information about their research.

Title: Self-Adaptive Trust-Aware Decentralized Information Flow Control
Authors: Charilaos Skandylas, Narges Khakpour, Jesper Andersson

Abstract:
Modern software systems and their corresponding
architectures are decentralized, distributed, and dynamic. As
a consequence, decentralized mechanisms are also required to
ensure security in such architectures. Decentralized Information
Flow Control (DIFC) is a mechanism to control information
flow in distributed systems. However, DIFC mechanisms require
the resolution of specific centralized control and trust issues. In
this paper, we propose an adaptive, trust-aware, decentralized
information flow approach that incorporates trust in DIFC for
decentralized systems. We employ decentralized feedback loops
to enable decentralized control and adaptive trust assignments.
In our approach, adaptivity mitigates two aspects of systems
dynamics that cause uncertainty: the ever-changing nature of
trust and the system openness. We formalize our trust-aware
DIFC model and instantiate two decentralized feedback loop
architectures to implement it. We discuss the design and implementation
considerations and evaluate the effectiveness of
adaptive trust-aware DIFC on a set of decentralized architectures
and a microservices-based system.

Link to full text

Chapter on Artificial Intelligence and Cybersecurity accepted for inclusion in upcoming Springer book

2020-06-05

I am glad that our students continue to collaborate with us and succeed years after their graduation. I would like to congratulate Mauro José Pappaterra – whom I have supervised at Linnaeus University and is now studying at Uppsala University – for this recent achievement: the chapter entitled “Bayesian Networks for online threat detection” (co-authored by Mauro and myself) has been accepted for inclusion in the upcoming book entitled “Machine Intelligence and Big Data Analytics For Cybersecurity Applications” to be published by Springer Nature in book series “STUDIES IN COMPUTATIONAL INTELLIGENCE”. The chapter extends the research started with:
https://lnkd.in/eSvVeHX
Mauro is also involved in the #railsproject contributing to deliverable D1.1 about AI and railway taxonomy with materials developed in its master’s thesis.
#artificialintelligence #cybersecurity #bayesnetworks

UPDATE DECEMBER 21ST 2020

Paper now available at:

https://link.springer.com/chapter/10.1007/978-3-030-57024-8_6

 

Two CPS-group papers accepted for publication by a prestigious Elsevier journal and a top IEEE conference

2020-05-22

In the last few weeks, we started to reap the benefits of our hard work with two good news. The paper entitled “Safety Integrity Through Self-Adaptation for Multi-Sensor Event Detection: Methodology and Case-Study” (with Stefano Marrone, Roberto Nardone, Mauro Caporuscio and Mirko D’Angelo) has been accepted with minor revisions by Future Generation Computer Systems (Elsevier, IF: 5.768), while the paper entitled “Low-Power Wide-Area Networks in Intelligent Transportation: Review and Opportunities for Smart-Railways” (with Ruth Dirnfeld, Stefano Marrone, Roberto Nardone and Valeria Vittorini) has been accepted for presentation at the 23rd IEEE International Conference on Intelligent Transportation Systems, i.e., the top event on intelligent transportation.

#railsproject #safety #its #iot #autonomousvehicles #smart #railways

https://lnkd.in/dvyX4CZ

https://lnkd.in/dH-8c7G

 

UPDATE JUNE 27th 2020

FGCS paper finally online at:

https://www.sciencedirect.com/science/article/abs/pii/S0167739X19333734

Paper on IoT Self-Healing accepted at 30th European Safety and Reliability Conference

2020-04-06

The paper entitled “Towards Self-Healing in the Internet of Things by Log Analytics and Process Mining” (Singh PJ. Flammini F, Caporuscio M, Saman Azari M, Thornadtsson J) has been accepted for presentation at the 30th European Safety and Reliability Conference and 15th Probabilistic Safety Assessment and Management Conference (ESREL2020-PSAM15), to be held in Venice, Italy on June 21-26 2020, and publication in the conference book of proceedings.

Link to the paper on Researchgate:

https://www.researchgate.net/publication/340463720_Towards_Self-Healing_in_the_Internet_of_Things_by_Log_Analytics_and_Process_Mining

UPDATE November 2020:

https://www.linkedin.com/posts/fflammini_internetofthingsiot-selfhealing-processmining-activity-6729761917826547712-_ZHk

 

New workshop on Artificial Intelligence for RAILwayS (AI4RAILS) accepted at European Dependable Computing Conference

2020-03-19

AI4RAILS – 1st International Workshop on Artificial Intelligence for RAILwayS

Organizers:
Workshop chairs: Stefano Marrone (University of Naples Federico II, Naples, Italy), Roberto Nardone (Mediterranean University of Reggio Calabria, Reggio Calabria, Italy)
Workshop series steering committee chairs: Francesco Flammini (Mälardalen University and Linnaeus University, Sweden), Valeria Vittorini (University of Naples Federico II, Naples, Italy)

The impact of Artificial Intelligence (AI) techniques on industry has been so disruptive that it gave rise to a new wave of research and applications. Several industries, mainly in logistics and manufacturing, have benefited significantly from AI adoption and this positive trend is planned to be kept in the future. Modern and future railways represent one of the fields in which AI is expected to have a significant impact in a medium to long term perspective, in order to get higher levels of automation. On the one hand, this opens for unprecedented scenarios for railway systems, but on the other hand, it also raises concerns regarding system dependability and new threats associated with a high level of autonomy. Therefore, the first step towards the adoption of AI in the railway sector is understanding to what extent AI can be considered reliable, safe and secure. In such a context, building upon the ongoing Shift2Rail project RAILS (Roadmaps for the AI integration in the raiL Sector), the aim of the 1st AI4RAILS workshop is to provide a forum for researchers, practitioners and business leaders to discuss and share new perspectives, ideas, technologies and solutions for an effective and dependable integration of AI techniques in rail-based transportation systems.

Co-located with 16th European Dependable Computing Conference, 7-10 September 2020, Munich, Germany:

http://edcc.dependability.org/workshops.html

Seminar on Performance Engineering Cyber-Physical Systems

2019-12-06

We would like to thank our new research assistant Lorenzo Pagliari for the seminar he held this morning (December 6th 2019, 9.00-10.00) in Växjö campus about “Performance Engineering Cyber-Physical Systems“.

Please find below the abstract and the slides of his talk.

 

Abstract:

Cyber-Physical Systems (CPS) are the consequence of today’s technology progression. They were born as natural evolution of a very large family of systems such as embedded systems, complex systems and system of systems and many others. Technology improvements give us more computational power, more powerful telecommunication architectures and more efficient software and algorithms that characterize the smart feature that is so widespread and used in the last few years. New terms such as “smart robots”, “smart industry”, “smart automotive” are becoming more popular and widespread used. Besides that, all these new type of systems are attracting more and more attention of the respective research communities. Therefore, with a new type of system that is strongly impacting many different realities, the importance of performance engineering them properly is rising.

SLIDES: Pagliari_PerformanceEngineering_CPS

 

If you have any questions, please feel free to contact him or Mauro Caporuscio.