Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

A Novel Method to Determine Total Oxidant Concentration Produced by Non-Thermal Plasma Based on Image Processing and Machine Learning

Mirkan Emir Sancak, Unal Sen, Ulker Diler Keris-Sen

TL;DR

A color based computer analysis method that integrates advanced image processing with machine learning to quantify colorimetric changes in potassium iodide solutions during oxidation and predicts total oxidant concentration in potassium iodide solution with very high accuracy.

Abstract

Accurate determination of total oxidant concentration [Ox]tot in nonthermal plasma treated aqueous systems remains a critical challenge due to the transient nature of reactive oxygen and nitrogen species and the subjectivity of conventional titration methods used for [Ox]tot determination. This study introduces a color based computer analysis method that integrates advanced image processing with machine learning to quantify colorimetric changes in potassium iodide solutions during oxidation. A custom built visual acquisition system recorded high resolution video of the color transitions occurring during plasma treatment while the change in oxidant concentration was simultaneously monitored using a standard titrimetric method. Extracted image frames were processed through a structured pipeline to obtain RGB, HSV, and Lab color features. Statistical analysis revealed strong linear relationships between selected color features and measured oxidant concentrations, particularly for HSV saturation, Lab a and b channels, and the blue component of RGB. These features were subsequently used to train and validate multiple machine learning models including linear regression, ridge regression, random forest, gradient boosting, and neural networks. Linear regression and gradient boosting demonstrated the highest predictive accuracy with R2 values exceeding 0.99. Dimensionality reduction from nine features to smaller feature subsets preserved predictive performance while improving computational efficiency. Comparison with experimental titration measurements showed that the proposed system predicts total oxidant concentration in potassium iodide solution with very high accuracy, achieving R2 values above 0.998 even under reduced feature conditions.

A Novel Method to Determine Total Oxidant Concentration Produced by Non-Thermal Plasma Based on Image Processing and Machine Learning

TL;DR

A color based computer analysis method that integrates advanced image processing with machine learning to quantify colorimetric changes in potassium iodide solutions during oxidation and predicts total oxidant concentration in potassium iodide solution with very high accuracy.

Abstract

Accurate determination of total oxidant concentration [Ox]tot in nonthermal plasma treated aqueous systems remains a critical challenge due to the transient nature of reactive oxygen and nitrogen species and the subjectivity of conventional titration methods used for [Ox]tot determination. This study introduces a color based computer analysis method that integrates advanced image processing with machine learning to quantify colorimetric changes in potassium iodide solutions during oxidation. A custom built visual acquisition system recorded high resolution video of the color transitions occurring during plasma treatment while the change in oxidant concentration was simultaneously monitored using a standard titrimetric method. Extracted image frames were processed through a structured pipeline to obtain RGB, HSV, and Lab color features. Statistical analysis revealed strong linear relationships between selected color features and measured oxidant concentrations, particularly for HSV saturation, Lab a and b channels, and the blue component of RGB. These features were subsequently used to train and validate multiple machine learning models including linear regression, ridge regression, random forest, gradient boosting, and neural networks. Linear regression and gradient boosting demonstrated the highest predictive accuracy with R2 values exceeding 0.99. Dimensionality reduction from nine features to smaller feature subsets preserved predictive performance while improving computational efficiency. Comparison with experimental titration measurements showed that the proposed system predicts total oxidant concentration in potassium iodide solution with very high accuracy, achieving R2 values above 0.998 even under reduced feature conditions.

Paper Structure

This paper contains 22 sections, 1 equation, 12 figures, 5 tables.

Table of Contents

  1. Introduction
  2. Materials and Method
  3. Experimental Procedure
  4. Chemical analysis
  5. Image Processing
  6. Data analysis
  7. Model training and evaluation
  8. Method validation
  9. Results and Discussion
  10. Determination of total oxidant concentration in KI solution during the experiments
  11. Extracting color features by image processing
  12. Assessing the distribution of extracted color features
  13. Analyzing the correlation between the color features and the oxidant concentrations
  14. Performance evaluation of machine learning models
  15. Evaluation of models trained with 9-features
  16. ...and 7 more sections

Figures (12)

  • Figure 1: Experimental, analytical and data processing steps
  • Figure 2: The Genesis visual data acquisition chamber for image capture
  • Figure 3: Relationship between the gathered $[\text{Ox}]_{\text{tot}}$ data by titration versus time
  • Figure 4: Image processing pipeline for video frames at two concentration levels ((1) low and (2) high concentration) including (a) the raw images showing the color gradient post-reaction, (b) the cropped region of interest (ROI) based on YOLOv8 detection, (c) the HSV-masked images highlighting the reactive zones, and (d) the final image after artifact removal via Telea inpainting for enhancing analysis accuracy
  • Figure 5: Image processing steps applied to the reactive ROI for both (1) lower and (2) higher KI concentrations including (a) CLAHE-enhanced images with improved local contrast in the oxidant zone, (b) the images after bilateral filtering, (c) the images after near-black pixel removal, ensuring histogram accuracy, and (d) the final RGB histograms reflect pixel intensity distributions
  • ...and 7 more figures