PSPiotr Sosinowski

Piotr Sosinowski

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Piotr Sosinowski has a total of 31 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Multi-Task Deep Learning for Surface Metrology

    by Dawid Kucharski, Adam Gąska, Tomasz Kowaluk, Krzysztof Stępień, Marta Rępalska, Bartosz Gapiński, Michal Wieczorowski, Michal Nawotka, Piotr Sobecki, Piotr Sosinowski, et al.

    A reproducible deep learning framework is presented for surface metrology to predict surface texture parameters together with their reported standard uncertainties. Using a multi-instrument dataset spanning tactile and optical systems, we jointly address measurement system type classification and regression of key surface parameters—arithmetic mean roughness (Ra), mean peak-to-valley roughness (Rz), and total roundness deviation (RONt)—alongside their reported standard uncertainties. Uncertainty is modelled via quantile and heteroscedastic regression heads, with post hoc conformal calibration used to obtain calibrated prediction intervals. On a held-out test set, high fidelity was achieved by single-target regressors (coefficients of determination: Ra 0.9824, Rz 0.9847, RONt 0.9918), with two uncertainty targets also well modelled (standard uncertainty of Ra 0.9899, standard uncertainty of Rz 0.9955); the standard uncertainty of RONt remained more difficult to learn (0.4934). The classifier reached 92.85% accuracy, and probability calibration was essentially unchanged after temperature scaling (expected calibration error 0.00504 → 0.00503 on the test split). Negative transfer was observed for naive multi-output trunks, with single-target models performing better. These results provide calibrated predictions suitable for informing instrument selection and acceptance decisions in metrological workflows.


  • Report on EURAMET supplementary comparison on measurement of a 1 mm stage micrometer

    by M Matus, M del Mar Pérez, E Prieto, A Germak, D Czułek, P Sosinowski, A Duță, E Dugheanu, S Zelenika, M Äremann, et al.

    Main text: The results of the EURAMET supplementary comparison on the calibration of a 1 mm stage micrometer are reported. 13 NMIs from 4 RMOs participated in the comparison. Originally, the comparison was planned to use a single artefact. Because it was destroyed during the duration of the comparison, it was necessary to carry out the test in two loops using a new artefact. Artefact circulation started in August 2020 and was completed in September 2022. Both artefacts were the same make and kind. The two artefacts are standard stage micrometers as used in optical microscopy on a transparent, low thermal expansion substrate. The scale length is 1 mm divided in 100 parts. The distances of all 100 scale marks from the zero mark have been measured by each participant. The results with associated uncertainties of all participating NMIs were in good agreement. All En values were smaller than 1 already from the pre-draft A state on. Therefore, no separate analysis of a largest consistent subset was necessary. With 1400 values without a single outlier, it is tempting to assume that uncertainty contributions are somehow overestimated. To reach the main text of this paper, click on Final Report. Note that this text is that which appears in Appendix B of the BIPM key comparison database https://www.bipm.org/kcdb/. The final report has been peer-reviewed and approved for publication by the CCL, according to the provisions of the CIPM Mutual Recognition Arrangement (CIPM MRA).

  • Open Access

    Feasibility Study of a Piezo Actuator as a Potential Standard in Calibration for Roundness Instruments

    by Anna Trych-Wildner, Krzysztof Wildner, Piotr Sosinowski

    The paper presents experimental data that show the possible application of a piezo actuator in the role of calibration standard that can serve as an alternative route to currently available methods like gauge blocks or flick standards. First, the experimental setups for interferometric and roundness instruments measurements were described. Next, the experiments using an interferometer for calibration of the piezo actuator were shown. Finally, the application of a piezo actuator to calibrate the roundness instrument, to state the correction factor for the roundness probe, and to relate it to the unit of metre, assuring the traceability of future measurements was performed. Detailed procedures of simulating grooves and then processing the data were described and the calibration curve was obtained using regression analysis. The estimation of uncertainty provided by different factors during the measurements was given to fulfil as closely as possible real calibration procedures taken up in the measurement laboratories. Finally, the limitations of the presented procedures were presented and discussed.