1. ISTCMTM
  2. All Volumes and Issues
  3. Volume 85, no.3, 2024
  4. METHODS FOR OUTLIER DETECTION IN METROLOGICAL STUDIES

METHODS FOR OUTLIER DETECTION IN METROLOGICAL STUDIES

ISTCMTM.
2024;
Volume 85(3), Number 3
: pp.25-29
https://doi.org/10.23939/istcmtm2024.03.025
Authors:
  1. Valeriy Aschepkov
1
Kharkiv National University of Radio Electronics, Ukraine

The article addresses the issue of outliers in metrological measurements, which can significantly distort research results and affect measurement accuracy. Outliers that substantially differ from other data points in a sample seriously threaten the reliability of metrological processes. In previous studies, the Isolation Forest model was applied to detect such outliers, demonstrating its effectiveness under certain conditions. For a deeper understanding and validation of the results, it is necessary to compare this approach with traditional robust methods, such as the Interquartile Range (IQR) and Median Absolute Deviation (MAD), already widely used in metrology.

metrology
outliers
anomalies
uncertainty
error
Isolation Forest method
robust methods.
  1. V.O. Ashchepkov "Application of the Isolation Forest Model for Anomaly Detection in Measurement Data" in Innovative Technologies and Scientific Solutions for Industries 2024, No. 1 (27), doi:10.30837/ITSSI.2024.27.236.
  2. T. V. Potanina, I. V. Mikhaylenko, "Investigation of Experimental Data Samples for Outliers: Comparison of Methods" in Integrated Technologies and Energy Saving, No. 3, 2023, doi: 10.20998/2078-5364.2023.3.07
  3. Wada K. “Outliers in official statistics” in Japanese Journal of Statistics and Data Science, 2020. No 3.pp. 669–691. doi:10.1007/s42081-020-00091-y
  4. M. Orellana and P. Cedillo, "Outlier Detection with Data Mining Techniques and Statistical Methods," 2019 International Conference on Information Systems and Computer Science (INCISCOS), Quito, Ecuador, 2019, pp. 51-56, doi: 10.1109/INCISCOS49368.2019.00017
  5. V.O. Aschepkov «Research of metrological characteristics of the state primary standard of unit of volume and mass flow rate of liquid during preparation for participation in international comparisons» in Ukrainian Metrological Journal. 2024.  No.1  (77)  doi:  10.24027/2306-7039.1.2024.300937.
  6. Batista E., Lau P. EURAMET regional key comparison EURAMET.M.FF-K4.b: Volume intercomparison at 20 L. Metrologia, 2009, vol. 46(1A):07013.doi: 10.1088/0026-1394/46/1A/07013
  7. Malengo A., Batista E., Arias R., Mićić L., Bošnjaković A., Mirjana M., Piluri E., Svendsen G., Huu M., Sarevska A. and others. Final report on EURAMET  project  1395/EURAMET.M.FF-K4.1.2016: volume comparison at 20 L. Metrologia, 2020. vol. 57(1A):07021. doi: 10.1088/0026-1394/57/1A/07021
  8. Huovinen M., Frahm E. EURAMET.M.FF-S13final report. Metrologia, 2022, vol. 59(1A):07010. doi: 10.1088/0026-1394/59/1A/07010
  9. Geršl J., Lojek L. Final report on EURAMET project No. 1046: Intercomparison of water flow standards using electromagnetic flowmeters. Metrologia, 2013, vol. 50(1A):07002. doi: 10.1088/0026-1394/50/1A/07002
  10. Batista E. Final report on EUROMET key comparison EUROMET.M.FF-K4 for volume intercomparison of 100 ml Gay-Lussac pycnometer. Metrologia, 2006, vol. 43(1A):07009. doi: 10.1088/0026-1394/43/1A/07009
  11. Benkova M., Frahm E., Romieu K., Warnecke H., Büker O., Haack S., Akselli B., Mazur V., Berkmann C., Zygmantas G. Comparisons of standards for liquid flow rates under static load changes. Metrologia, 2024, vol. 61(1A):07003. doi: 10.1088/0026-1394/61/1A/07003