A reliability analysis of a deep neural network

A Bosio, P Bernardi, A Ruospo… - 2019 IEEE Latin …, 2019‏ - ieeexplore.ieee.org
Deep Learning, and in particular its implementation using Convolutional Neural Networks
(CNNs), is currently one of the most intensively and widely used predictive models for safety …

Evaluating convolutional neural networks reliability depending on their data representation

A Ruospo, A Bosio, A Ianne… - 2020 23rd Euromicro …, 2020‏ - ieeexplore.ieee.org
Safety-critical applications are frequently based on deep learning algorithms. In particular,
Convolutional Neural Networks (CNNs) are commonly deployed in autonomous driving …

[HTML][HTML] A novel iso 26262-compliant test bench to assess the diagnostic coverage of software hardening techniques against digital components random hardware …

J Sini, M Violante, F Tronci - Electronics, 2022‏ - mdpi.com
This paper describes a novel approach to assess detection mechanisms and their
diagnostic coverage, implemented using embedded software, designed to identify random …

Testing permanent faults in pipeline registers of GPGPUs: A multi-kernel approach

JER Condia, MS Reorda - … Symposium on On-Line Testing and …, 2019‏ - ieeexplore.ieee.org
In the last decade, General Purpose Graphics Processing Units (GPGPUs) have been
widely employed in high demanding data processing applications including multimedia and …

An analysis of test solutions for COTS-based systems in space applications

R Cantoro, S Carbonara, A Floridia… - 2018 IFIP/IEEE …, 2018‏ - ieeexplore.ieee.org
One of the current trends in space electronics is towards considering the adoption of COTS
components, mainly to widen the spectrum of available products. When substituting space …

Fault grading techniques of software test libraries for safety-critical applications

A Floridia, E Sanchez, MS Reorda - IEEE Access, 2019‏ - ieeexplore.ieee.org
The adoption of complex and technologically advanced integrated circuits (ICs) in safety-
critical applications (eg, in automotive) forced the introduction of new solutions to guarantee …

[HTML][HTML] Automated identification of application-dependent safe faults in automotive systems-on-a-chips

AC Bagbaba, F Augusto da Silva, M Sonza Reorda… - Electronics, 2022‏ - mdpi.com
ISO 26262 requires classifying random hardware faults based on their effects (safe,
detected, or undetected) within integrated circuits used in automobiles. In general, this …

Application specific true critical paths identification in sequential circuits

L Jürimägi, R Ubar, M Jenihhin, J Raik… - 2019 IEEE 25th …, 2019‏ - ieeexplore.ieee.org
The extreme complexity of digital systems enabled by nanometer-scale implementation
technologies comes along with strengthened design requirements that are difficult to …

Untestable faults identification in GPGPUs for safety-critical applications

JER Condia, FA Da Silva, S Hamdioui… - 2019 26th IEEE …, 2019‏ - ieeexplore.ieee.org
Nowadays, General Purpose Graphics Processing Units (GPGPUs) devices are considered
as promising solutions for high-performance safety-critical applications, such as those in the …

New categories of Safe Faults in a processor-based Embedded System

C Gursoy, M Jenihhin, AS Oyeniran… - 2019 IEEE 22nd …, 2019‏ - ieeexplore.ieee.org
The identification of safe faults (ie, faults which are guaranteed not to produce any failure) in
an electronic system is a crucial step when analyzing its dependability and its test plan …