Artur Kazak

Mr. Artur Kazak

University Transilvania, Braşov, Romania
orcid

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

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

Representative Publications

View All Publications
24 January 2025 in Journal of Engineering Science
Verified
Journal Article
Open access
PDF file
SNSecrieru Nicolae
Secrieru Nicolae
Cărbune ViorelCărbune Viorel
Cărbune Viorel
TZTudor Zadorojneac
Tudor Zadorojneac
VMVladimir Melnic
Vladimir Melnic
Mihai IvanoviciMihai Ivanovici
Mihai Ivanovici
Artur KazakArtur Kazak
Artur Kazak
This paper is dedicated to the study of the cosmic radiation and its effects on electronics, as well as methods to measure it in order to aid the elaboration of the architecture of the satellite module with space radiation sensors for classification and real-time analysis of cosmic radiation-induced fault patterns and state predictions the of electronic systems embedded in satellites. The architecture of the satellite module with an intelligent radiation sensor based on an FPGA device is proposed, which will include as radiation sensing elements arrays of various types of electronic memories (on semiconductors), both within the circuit and external nearby this circuit. A significant part of the FPGA circuit configuration consists in the development of acquisition, processing and communication procedures using structures with majoritz voting to exclude the influence of spatial radiation.

26 June 2026 in Electronics
Verified
Journal Article
Open access
PDF file
Artur KazakArtur Kazak
Artur Kazak
Stefan PopaStefan Popa
Stefan Popa
ABAndrei Bertescu
Andrei Bertescu
Mihai IvanoviciMihai Ivanovici
Mihai Ivanovici
Radiation monitoring with SRAM-based FPGAs traditionally relies on offset-histogram analysis, which requires a chip-specific calibration campaign at an accelerator before multiple-cell upsets (MCUs) can be discriminated from coincident single-cell upsets (SCUs). The cost and complexity of such calibration restrict the approach to dedicated, beam-test-funded programs. We propose an AI-based on-board classifier that achieves MCU/SCU discrimination directly, without any chip-specific calibration. A lightweight Multi-Layer Perceptron (MLP), trained entirely on synthetic data covering five representative bit-interleaving layouts, is integrated on an AMD Artix-7 XC7A200T FPGA together with per-detection-element telemetry aggregation. The classifier achieves F1 = 0.92–0.97 on structured BRAM layouts when per-chip calibration data are available (calibrated ceiling) and, without any chip-specific calibration, retains F1 up to 0.81 ± 0.02 (held-out, mean over five seeds) on previously unseen layouts with near-perfect recall. A sensitivity analysis across a 20× range of SEU rates and a 4× range of MCU fractions confirms the robustness of the proposed approach. A feature-ablation study identifies an indispensable feature subset, while a comparative evaluation of four alternative classifier architectures (decision tree, support vector machine (SVM), two MLP variants) establishes the reference MLP as the optimal choice. Post-implementation results on the Artix-7 200T show that the MLP-enhanced and calibrated-histogram designs occupy nearly identical FPGA footprints, reframing the choice between them as an operational decision driven by calibration availability rather than by hardware cost.