Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

3D-Printed Polylactide-Based Implants: Influence of Processing, Radiation Sterilization and In Vivo Bioresorption on Structural and Physicochemical Material Characteristics.

Polymers·2026

Same author

Surface Inspection and Description in Metrology and Tribology-Vol. 2.

Materials (Basel, Switzerland)·2026

Same author

The Impact of an Object's Surface Material and Preparatory Actions on the Accuracy of Optical Coordinate Measurement.

Materials (Basel, Switzerland)·2025

Same author

Verification of the performance of the experimental ionization chamber for determination of absorbed dose to water for high-energy photon beams using Monte Carlo calculation.

Reports of practical oncology and radiotherapy : journal of Greatpoland Cancer Center in Poznan and Polish Society of Radiation Oncology·2025

Same author

Identification of the Influence of IPA Rinsing Times on Surface Roughness of SLA-Printed Parts Made of Different Materials.

Materials (Basel, Switzerland)·2025

Same author

The Wear Resistance of NiCrSiB-20%CaF<sub>2</sub> Sinters in the Temperature Range 23-600 °C.

Materials (Basel, Switzerland)·2025

Same journal

RETRACTED: Zhang et al. A Novel Framework for Reconstruction and Imaging of Target Scattering Centers via Wide-Angle Incidence in Radar Networks. <i>Sensors</i> 2025, <i>25</i>, 6802.

Sensors (Basel, Switzerland)·2026

Same journal

Enhancing Unsupervised Multi-Source Domain Adaptation for Person Re-Identification via Mixture of Experts and Graph-Based Relation.

Sensors (Basel, Switzerland)·2026

Same journal

Development of an Instrumented Glove for Palmar Pressure Assessment in Kayakers.

Sensors (Basel, Switzerland)·2026

Same journal

Development and Experimental Validation of an Autonomous IoT-Based Monitoring System for Real-Time Water Quality Assessment in the Amazon River.

Sensors (Basel, Switzerland)·2026

Same journal

Semi-Supervised Adversarial Learning Framework for Controller Area Network Bus Intrusion Detection.

Sensors (Basel, Switzerland)·2026

Same journal

Smart Optimization Method for Safety Signs in Innovative Manufacturing Environments Integrating Industrial Field IoT Sensors and Knowledge Graphs.

Sensors (Basel, Switzerland)·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Jan 7, 2026

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Multi-Task Deep Learning for Surface Metrology.

Dawid Kucharski¹, Adam Gąska², Tomasz Kowaluk³

¹Division of Metrology and Measurement Systems, Institute of Mechanical Technology, Faculty of Mechanical Engineering, Poznan University of Technology, 60-965 Poznan, Poland.

Sensors (Basel, Switzerland)

|December 31, 2025

Summary

This summary is machine-generated.

A deep learning framework accurately predicts surface texture parameters and their uncertainties from tactile and optical measurements. This tool aids instrument selection and acceptance in metrology.

Keywords:

artificial intelligence conformal prediction deep learning surface metrology uncertainty quantification

More Related Videos

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

Related Experiment Videos

Last Updated: Jan 7, 2026

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

Area of Science:

Metrology
Machine Learning
Surface Science

Background:

Surface texture parameters are crucial for product performance and quality control.
Accurate prediction of surface parameters and their uncertainties is essential for reliable metrological workflows.
Existing methods often struggle to integrate data from diverse measurement systems and provide reliable uncertainty estimations.

Purpose of the Study:

To develop a reproducible deep learning framework for predicting surface texture parameters and their standard uncertainties.
To jointly classify measurement system types and regress key surface parameters (Ra, Rz, RONt) and their uncertainties.
To provide calibrated predictions for informed instrument selection and acceptance decisions.

Main Methods:

Utilized a multi-instrument dataset encompassing tactile and optical measurement systems.
Developed a deep learning framework with separate regression heads for surface parameters and their uncertainties.
Employed quantile and heteroscedastic regression for uncertainty modeling, with post hoc conformal calibration.
Implemented single-target regressors and a classifier for measurement system type.

Main Results:

High prediction fidelity for surface parameters (Ra, Rz, RONt) and their standard uncertainties (Ra, Rz).
Achieved 92.85% accuracy in classifying measurement system types.
Demonstrated that single-target models outperform naive multi-output models, avoiding negative transfer.
Identified challenges in learning the standard uncertainty of RONt.

Conclusions:

The developed deep learning framework offers a reproducible and accurate method for surface metrology.
Calibrated predictions enhance the reliability of surface parameter and uncertainty estimations.
The framework supports informed decision-making in instrument selection and acceptance within metrological workflows.