Skip to main content
SpringerLink
Log in
Springer
Real-Time Systems

The International Journal of Time-Critical Computing Systems

Publishing model:
Hybrid

Real-Time Systems - Call for Papers: Predictable Machine Learning [CLOSED]

Motivations 

In recent years, deep neural networks have achieved remarkable performance in several tasks related to perception and control. Nevertheless, their usage in safety critical systems is quite problematic due to a number or reasons. 

First, during inference, the execution time of a neural network can be subject to high variations, which may be caused by the specific computing platform, hardware accelerator, or the framework used to manage the execution of the various network nodes. Second, neural models have been shown to be prone to adversarial attacks, which can induce a wrong prediction through imperceptible perturbations applied to the input. Such adversarial attacks have been shown to be also applicable in the real world, through properly crafted patches that can be printed and placed on physical objects, so without accessing the vision system. Third, the prediction of a neural model can also be compromised by inputs that are out of the typical distribution of the data samples used during training. Detecting or neutralizing such adversarial attacks or out-of-distribution inputs may have a significant impact on the overall execution time of the neural model.

Objectives

The goal of this special issue is to collect new ideas, methodologies, and techniques for increasing the time predictability of deep neural networks and machine learning systems, to enable their usage in safety-critical cyber-physical systems with stringent timing constraints. Submissions to this special issue must address some form of timing issues, as real-time constraints and methods to guarantee them, time-sensitive applications, or timing analysis of deep learning models. Both theoretical papers and papers considering exclusively empirical validation of timing requirements are welcome. 

Authors are invited to submit original manuscripts on topics including, but not limited to:

  • Predictable software support for deep neural networks
  • Timing analysis of deep neural models or machine learning algorithms
  • Problem identification and solutions for current deep-learning frameworks
  • Problem identification and solutions for AI hardware accelerators
  • Timing issues for real-time object detection and tracking tasks
  • Balancing accuracy with real-time performance in deep neural networks
  • Real-time issues in AI-powered cyber-physical systems
  • AI methods for real-time system

Dates 

Submission deadline: November 30th, 2022

Expected notification: January 31st, 2023 

Final decision: March 31st, 2023 

Publication date: June 2023

Guest Editors 

Giorgio Buttazzo, Scuola Superiore Sant’Anna, Pisa, Italy 

Daniel Casini, Scuola Superiore Sant’Anna, Pisa, Italy

Guest Editor Bios

New Content Item

Giorgio Buttazzo is Full Professor of Computer Engineering at the Scuola Superiore Sant'Anna of Pisa. He graduated in Electronic Engineering at the University of Pisa in 1985, received a Master in Computer Science at the University of Pennsylvania in 1987, and a Ph.D. in Computer Engineering at the Scuola Superiore Sant'Anna of Pisa in 1991. He has been Chair of the IEEE Technical Committee on Real-Time Systems (2010-2012), and Program Chair and General Chair of the major international conferences on real[1]time computing. In 2013, he received the Outstanding Technical Contributions and Leadership Award from the IEEE Technical Committee on Real-Time Systems. He has been Editor-in-Chief of the Journal of Real-Time Systems, Associate Editor of the IEEE Transactions on Industrial Informatics and the ACM Transactions on Cyber-Physical Systems. He is IEEE Fellow since 2012 and has authored 6 books on real-time systems and over 300 papers in the field of real-time systems, robotics, and neural networks, receiving 13 Best Paper Awards.

New Content Item

Daniel Casini is Assistant Professor at the Real-Time Systems (ReTiS) Laboratory of the Scuola Superiore Sant'Anna of Pisa. He graduated (cum laude) in Embedded Computing Systems Engineering, a Master degree jointly offered by the Scuola Superiore Sant'Anna of Pisa and University of Pisa, and received a Ph.D. in computer engineering at the Scuola Superiore Sant'Anna of Pisa (with honors). In 2019, he has been visiting scholar at the Max Planck Institute for Software Systems (Germany). He is Associate Editor for Elsevier Microprocessors and Microsystems. He has been a technical program committee member in several international conferences including RTSS (IEEE Real Time System Symposium, 2021, 2022), ECRTS (Euromicro Conference on Real-Time Systems, 2021, 2022), RTAS (IEEE Real-Time and Embedded Technology and Applications Symposium, 2022), and ISORC (IEEE International Symposium on Real-Time Distributed Computing, 2020, 2021, 2022)

Submission Guidelines:
Authors should prepare their manuscript according to the Instructions for Authors available from the Real-Time Systems website (this opens in a new tab). Authors should submit through the online submission site at https://www.editorialmanager.com/time/default2.aspx (this opens in a new tab) and select “SI Predictable Machine Learning" when they reach the “Article Type” step in the submission process. Submitted papers should present original, unpublished work, relevant to the topics of the special issue. All submitted papers will be evaluated on the basis of relevance, significance of contribution, technical quality, scholarship, and quality of presentation, by at least three independent reviewers. It is the policy of the journal that no submission, or substantially overlapping submission, be published or be under review at another journal or conference at any time during the review process. Final decisions on all papers are made by the Editor in Chief.

Search

Navigation