Proceedings of the 2nd International Conference on Recent Advancement and Modernization in Sustainable Intelligent Technologies & Applications (RAMSITA-2026)

<Previous Article In Volume

A Noise-Aware KPI Consistency Framework for Reliable Metadata Processing in Unstructured Databases

Authors
Anita Verma1, *, Jitendra Saxena2
1Research Scholar, Department of Research, Sage University, Indore, India
2Professor, Institute of Advanced Computing, Sage University, Indore, India
*Corresponding author. Email: anitaverma@acropolis.in
Corresponding Author
Anita Verma
Available Online 28 May 2026.
DOI
10.2991/978-94-6239-678-4_47How to use a DOI?
Keywords
Unstructured Database; Image Noise Modelling; Adaptive De-noising; KPI Stabilization; Metadata Drift Control; NAI; Statistical Validation; Multi-Metric Consistency Framework
Abstract

The random changes in pixel values in digital images can be presented during image transmission, compression, storage or image capturing. The undesirable changes in image are defined as noise that reduces image clarity and can be the cause of instability in quality measurements. Furthermore, the instability in quality measurement affects the metadata extracted from it and further influences the downstream data analytics. A Noise-Aware Key Performance Indicator (KPI) Consistency Framework is suggested in this work to ensure reliability through consistent metadata in unstructured database environment. The impact of noise is systematically modelled through controlled noise injection and applying adaptive de-noising. Furthermore, the KPI stability is using Noise Awareness Index (NAI), Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index (SSIM), and edge preservation metrics. A statistically significant improvement in KPI is observed after de-noising (p<0.05), across multiple noise variances (0.001-0.1) from study conducted on 10 different images (5 colour and 5 grayscale). Statistical results shows that rise in image noise brings significant increase in metadata drift that is both consistent and predictable. The proposed framework provides a reproducible and modality-independent method to maintain metadata reliability in large-scale unstructured image databases.

Copyright
© 2026 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

<Previous Article In Volume
Volume Title
Proceedings of the 2nd International Conference on Recent Advancement and Modernization in Sustainable Intelligent Technologies & Applications (RAMSITA-2026)
Series
Advances in Intelligent Systems Research
Publication Date
28 May 2026
ISBN
978-94-6239-678-4
ISSN
1951-6851
DOI
10.2991/978-94-6239-678-4_47How to use a DOI?
Copyright
© 2026 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Cite this article

risenwbib
TY  - CONF
AU  - Anita Verma
AU  - Jitendra Saxena
PY  - 2026
DA  - 2026/05/28
TI  - A Noise-Aware KPI Consistency Framework for Reliable Metadata Processing in Unstructured Databases
BT  - Proceedings of the 2nd International Conference on Recent Advancement and Modernization in Sustainable Intelligent Technologies & Applications (RAMSITA-2026)
PB  - Atlantis Press
SP  - 595
EP  - 605
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6239-678-4_47
DO  - 10.2991/978-94-6239-678-4_47
ID  - Verma2026
ER  -