Showing papers by "Cristiana Bolchini published in 2020"

A Neural Network Based Fault Management Scheme for Reliable Image Processing

Abstract: Traditional reliability approaches introduce relevant costs to achieve unconditional correctness during data processing. However, many application environments are inherently tolerant to a certain degree of inexactness or inaccuracy. In this article, we focus on the practical scenario of image processing in space, a domain where faults are a threat, while the applications are inherently tolerant to a certain degree of errors. We first introduce the concept of usability of the processed image to relax the traditional requirement of unconditional correctness, and to limit the computational overheads related to reliability. We then introduce our new flexible and lightweight fault management methodology for inaccurate application environments. A key novelty of our scheme is the utilization of neural networks to reduce the costs associated with the occurrence and the detection of faults. Experiments on two aerospace image processing case studies show overall time savings of 14.89 and 34.72 percent for the two applications, respectively, as compared with the baseline classical Duplication with Comparison scheme.

Fault Impact Estimation for Lightweight Fault Detection in Image Filtering

Abstract: Classical redundancy-based fault detection techniques, such as Duplication with Comparison (DWC), rely on replicating thecomputation and comparing the replicas' output at a bit-wise granularity. In many application environments these costs are prohibitive,especially when applications are characterized by an intrinsic level of tolerance. This paper presents a novel fault-detection approachfor the specific context of image filtering. Peculiarity of the proposed approach is that it estimates the impact of the fault on the processed output,inorderto determine whether the image is usable or should be re-processed. Tolimit overheads, the proposed solution exploits Approximate Computing (AC), allowing the definition of disciplined AC strategies totrade-off between accuracy and costs. Core of our solution is the successful combination of Image Quality Assessment metrics and Machine Learning models to assess the visual impact of the fault in a lightweight manner. Extensive experimentalcampaigns demonstrate the effectiveness of the solution, achieving achieving a reduction in terms of execution time up to 44% with respect to the classical DWC, with a fault detection precision ranging from 94.58% to 96.70%, and recall ranging from 88.2% to 97.8% depending on the adopted level of approximation.

Error Modeling for Image Processing Filters accelerated onto SRAM-based FPGAs

Abstract: Image processing is today employed in a variety of application fields, including safety- and mission-critical ones. In these scenarios it is vital to carefully analyse the reliability of the designed system before deployment and, if necessary, to adopt specific hardening techniques. Two are the techniques generally employed: circuit-level fault injection and application-level functional error simulation. In this paper we present a set of functional error models specific for a number of convolution-based filters that are the basic building blocks for a wide range of image processing applications. The presented error models, derived through a number of circuit-level fault injection experiments, may be integrated into application-level functional error simulators, bridging the gap between the two strategies. The presented error models are the first step towards combining the accuracy of fault injection and the flexibility of error simulation into a widely adopted reliability analysis tool.

Holding Conferences Online due to COVID-19: The DATE Experience

Abstract: The Design, Automation , and Test in Europe (DATE) Conference and Exhibition is an annual event, scheduled in 2020 to be held March 9–13, 2020, at the Alpexpo Congress Centre in Grenoble Because of the COVID-19 outbreak, the conference took place in a virtual environment, in April and May 2020

Lightweight Fault Detection and Management for Image Restoration

Abstract: Image restoration is generally employed to recover an image that has been blurred, for example, for noise suppression purposes. The Richardson-Lucy (RL) algorithm is a widely used iterative approach for image restoration. In this paper we propose a lightweight application-specific fault detection and management scheme for RL that exploits two specific characteristics of such algorithm: i) there is a strong correlation between the input and output images of each iteration, and ii) the algorithm is often able to produce a final output that is very similar to the expected one although the output of an intermediate iteration has been corrupted by a fault. The proposed scheme exploits these characteristics to detect the occurrence of a fault without requiring duplication and to determine whether the error in the output of an intermediate iteration of the algorithm would be absorbed (thus avoiding image dropping and algorithm reexecution) or whether the image has to be discarded and the overall elaboration to be re-executed. An experimental campaign demonstrated that our scheme allows for an execution time reduction of about 54% w.r.t. the classical Duplication with Comparison (DWC), still providing about 99% fault detection.