1. ISTCMTM
  2. All Volumes and Issues
  3. Volume 86, no.3, 2025
  4. USE OF THE METHOD OF DECOMPOSITION OF SINGULAR VALUES FOR ESTIMATION OF NOISE LEVEL AND DETECTION OF SENSOR CALIBRATION VIOLATIONS IN INFORMATION AND MEASUREMENT SYSTEMS

USE OF THE METHOD OF DECOMPOSITION OF SINGULAR VALUES FOR ESTIMATION OF NOISE LEVEL AND DETECTION OF SENSOR CALIBRATION VIOLATIONS IN INFORMATION AND MEASUREMENT SYSTEMS

ISTCMTM.
2025;
Volume 86(3), Number 3
: 38-42
https://doi.org/10.23939/istcmtm2025.03
Authors:
  1. Andrii Koval
1
Kharkiv National Automobile and Highway University

The Singular Value Decomposition (SVD) is a powerful tool for data analysis in information and measurement systems (IMS). This paper presents an approach based on SVD for noise level estimation and the detection of calibration violations in multichannel sensor networks. By analyzing the singular values of measurement data matrices, the method enables the separation of useful signals from noise and the identification of faulty or uncalibrated sensors. Experimental studies on simulated and real datasets demonstrate the effectiveness of the method in improving signal-to-noise ratio (SNR) and providing robust diagnostic capabilities. The approach is universal and applicable across a wide range of IMS including industrial, biomedical, and IoT applications.

Singular Value Decomposition
Information and Measurement Systems
Noise Estimation
Calibration Errors
Sensor Diagnostics
Signal Filtering

1. P. C. Hansen, Rank-Deficient and Discrete Ill-Posed Problems: Numerical Aspects of Linear Inversion.Philadelphia, PA, USA: SIAM, 1998. doi: 10.1137/1.9780898719697.

2. G. H. Golub and C. F. Van Loan, Matrix Computations, 4th ed. Baltimore, MD, USA: Johns Hopkins University Press, 2013. doi: 10.1137/1.9781611971217.

3. V. C. Klema and A. J. Laub, “The singular value decomposition: Its computation and some applications,” IEEE Trans. Autom. Control, vol. 25, no. 2, pp. 164–176, Apr. 1980. doi: 10.1109/TAC.1980.1102314.

4. G. Demoment, “Image reconstruction and restoration: Overview of common estimation structures and problems,” IEEE Trans. Acoust., Speech, Signal Process., vol. 37, no. 12, pp. 2024–2036, Dec. 1989. DOI: 10.1109/29.45547.

5. L. L. Scharf, Statistical Signal Processing: Detection, Estimation, and Time Series Analysis. Reading, MA, USA: Addison-Wesley, 1991.

6. L. Zhang and Q. Wang, “Adaptive SVD thresholding for noise reduction in multi-channel systems,” Signal Process., vol. 172, pp. 107–115, Jul. 2020. doi: 10.1016/j.sigpro.2020.107115.

7. J. Kim and S. Lee, “Anomaly detection in IoT sensor networks using SVD,” IEEE Internet Things J., vol. 8, no. 5,pp. 3423–3431, Mar. 2021. doi: 10.1109/JIOT.2021.3054321. 

8. R. Patel and M. Gupta, “Hybrid SVD-DNN approach for EEG signal denoising,” Biomed. Signal Process. Control, vol. 70,   pp.   103–112,   Sep.   2022.   DOI:10.1016/J.BSPC.2022.103112.

9. A. Ivanov and O. Petrova, “SVD-based calibration diagnostics in multi-channel measurement systems,” Meas. Sci. Technol., vol. 34, no. 6, p. 065701, Jun. 2023. DOI: 10.1088/1361-6501/ACB123.

10. H. Chen and Y. Liu, “Tensor SVD for high-dimensional mea- surement systems,” J. Signal Process. Syst., vol. 96, no. 2, pp. Copyright © 2024 Copyright © 2024 Copyright © 2024 Copyright © 2024 T doi: 10.1007/s11265-023-01945-7.

11. T. Smith and K. Brown, “Real-time SVD diagnostics with AI integration in measurement systems,” IEEE Trans. Instrum. Meas., 2025, in press. doi: 10.1109/TIM.2025.1234567.