Petr Dobiáš

Dr. Petr Dobiáš

orcid

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
25 April 2021
Verified
Conference Paper
Closed access
ECEmmanuel Casseau
Emmanuel Casseau
PDPetr Dobiáš
Petr Dobiáš
OSOliver Sinnen
Oliver Sinnen
GRGennaro Rodrigues
Gennaro Rodrigues
FKFernanda Kastensmidt
Fernanda Kastensmidt
Alberto BosioAlberto Bosio
Alberto Bosio
The computing continuum’s actual trend is facing a growth in terms of devices with any degree of computational capability. Those devices may or may not include a full-stack, including the Operating System layer and the Application layer, or just facing pure bare-metal solutions. In either case, the reliability of the full system stack has to be guaranteed. It is crucial to provide data regarding the impact of faults at all system stack levels and potential hardening solutions to design highly resilient systems. While most of the work usually concentrates on the application reliability, the special session aims to provide a deep comprehension of the impact on the reliability of an embedded system when faults in the hardware substrate of the system stack surface at the Operating System layer. For this reason, we will cover a comparison from an application perspective when hardware faults happen in bare metal vs. real-time OS vs. general-purpose OS. Then we will go deeper within a FreeRTOS to evaluate the contribution of all parts of the OS. Eventually, the Special Session will propose some hardening techniques at the Operating System level by exploiting the scheduling capabilities.

30 July 2025 in IEEE Transactions on Radar Systems
Verified
Journal Article
Closed access
ABAlexandre Bordat
Alexandre Bordat
CBClaire Béranger
Claire Béranger
MCMichel Chapron
Michel Chapron
PDPetr Dobiáš
Petr Dobiáš
Julien Le KernecJulien Le Kernec
Julien Le Kernec
OROlivier Romain
Olivier Romain
Falls among the elderly present a significant healthcare and socioeconomic challenge. The Timed Up and Go (TUG) test is a widely used tool for assessing mobility and fall risk. However, traditional methods are limited in terms of objectivity and scalability. This study introduces a radar-based approach to automating the TUG test using Frequency Modulated Continuous Wave (FMCW) radar. The main objective is to provide an automated, non-intrusive, and privacy-preserving system for fall risk assessment through precise segmentation of TUG test phases (standing up, walking, turning around, and sitting down) and extraction of key gait parameters, such as walking speed, distance traveled, and phase durations. Validated against a cohort of 100 participants, the system achieved a mean relative velocity error of 8.89% and a mean absolute time error of 0.159 seconds. These results demonstrate high accuracy and robustness, making it a promising tool for fall risk assessment in both clinical and home environments. The strong correlation agreement for studied metrics (asymmetry and cadence) is confirmed by the Intraclass Correlation Coefficient (ICC) between Motion Capture (MoCap) and radar, with ICCasymmetry = 81.7% and ICCcadence = 76.2%. Additionally, the Bland-Altman analysis further supports this agreement, showing a strong concordance between the radar and MoCap measurements for both metrics.

1 September 2021 in Microprocessors and Microsystems
Verified
Journal Article
Closed access
PDPetr Dobiáš
Petr Dobiáš
ECEmmanuel Casseau
Emmanuel Casseau
OSOliver Sinnen
Oliver Sinnen

9 March 2023 in Sustainable Computing: Informatics and Systems
Verified
Journal Article
Closed access
PDPetr Dobiáš
Petr Dobiáš
ECEmmanuel Casseau
Emmanuel Casseau
OSOliver Sinnen
Oliver Sinnen

30 July 2022
Verified
Book Chapter
Closed access
PDF file
PDPetr Dobiáš
Petr Dobiáš
TGThomas Garbay
Thomas Garbay
BGBertrand Granado
Bertrand Granado
KHKhalil Hachicha
Khalil Hachicha
APAndrea Pinna
Andrea Pinna

26 September 2024 in ACM Transactions on Embedded Computing Systems
Verified
Journal Article
Open access
TGThomas Garbay
Thomas Garbay
KHKhalil Hachicha
Khalil Hachicha
PDPetr Dobiáš
Petr Dobiáš
APAndrea Pinna
Andrea Pinna
KHKarim Hocine
Karim Hocine
BGBertrand Granado
Bertrand Granado
Embedded systems based on Microcontroller Units (MCUs) often gather significant quantities of data and solve various issues. Convolutional Neural Networks (CNNs) have proven their effectiveness in solving computer vision and natural language processing tasks. However, implementing CNNs within MCUs is challenging due to their high inference costs, which varies widely depending on hardware targets and CNN topologies. Despite state-of-the-art advancements, no efficient design space exploration solutions handle the wide variety of implementation solutions. In this article, we introduce the ZIP-CNN design space exploration methodology, which facilitates CNN implementation within MCUs. We developed a model that quantitatively estimates the latency, energy consumption, and memory space required to run a CNN within an MCU. This model accounts for algorithmic reductions such as knowledge distillation, pruning, or quantization and applies to any CNN topology. To demonstrate the efficiency of our methodology, we investigated LeNet5, ResNet8, and ResNet26 within three different MCUs. We made materials and supplementary results available in a GitHub repository: https://github.com/ThGbay/ZIP-CNN . The proposed method was empirically verified on three hardware targets running at 14 different operating frequencies. The three CNN topologies investigated were implemented in their default configuration in FP32, and also reduced with INT8 quantization, pruning at five different rates and with knowledge distillation. The estimates of our model are very reliable with an error of 3.29% to 15.23% for latency, 3.12% to 10.34% for energy consumption, and 1.95% to 6.31% for memory space. These results are based on on-device measurements.