Can We Transfer Noise Patterns? A Multi-environment Spectrum Analysis Model Using Generated Cases

TL;DR

This paper introduces a novel noise pattern transfer model for spectrum analysis in water quality testing, enabling better environmental adaptability by generating high-quality cases to transfer noise patterns across different environments.

Contribution

The study proposes a new noise pattern transferring model that uses generated cases to improve spectrum analysis across diverse environments, addressing sample-level noise interference.

Findings

The method effectively transfers noise patterns between environments.

It outperforms baseline denoising and generative models.

Generated cases improve deep learning model robustness.

Abstract

Spectrum analysis systems in online water quality testing are designed to detect types and concentrations of pollutants and enable regulatory agencies to respond promptly to pollution incidents. However, spectral data-based testing devices suffer from complex noise patterns when deployed in non-laboratory environments. To make the analysis model applicable to more environments, we propose a noise patterns transferring model, which takes the spectrum of standard water samples in different environments as cases and learns the differences in their noise patterns, thus enabling noise patterns to transfer to unknown samples. Unfortunately, the inevitable sample-level baseline noise makes the model unable to obtain the paired data that only differ in dataset-level environmental noise. To address the problem, we generate a sample-to-sample case-base to exclude the interference of sample-level noise on dataset-level noise learning, enhancing the system's learning performance. Experiments on spectral data with different background noises demonstrate the good noise-transferring ability of the proposed method against baseline systems ranging from wavelet denoising, deep neural networks, and generative models. From this research, we posit that our method can enhance the performance of DL models by generating high-quality cases. The source code is made publicly available online at https://github.com/Magnomic/CNST.