The best performing color space and machine learning regression algorithm for the accurate estimation of chromium (VI) and iron (III) in aqueous samples using low-cost and portable flatbed scanner colorimetry

The study utilizes the colorimetric method (involving 1,5-diphenylcarbazide and potassium thiocyanate as complexing agents), computer vision, and machine learning (ML) regression algorithms to determine the content of Cr (VI) and Fe (III) in water samples. To process digital images of water samples,...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Journal of the Iranian Chemical Society Ročník 21; číslo 9; s. 2335 - 2349
Hlavní autoři: Ichsan, Chairul, Rodiah, Siti
Médium: Journal Article
Jazyk:angličtina
Vydáno: Berlin/Heidelberg Springer Berlin Heidelberg 01.09.2024
Springer Nature B.V
Témata:
Accuracy
Algorithms
Analytical Chemistry
Artificial intelligence
Biochemistry
Calibration
Chemistry
Chemistry and Materials Science
Chromium
Color
Colorimetry
Computer vision
Datasets
Diphenylcarbazide
Ecosystems
Environmental impact
Errors
Estimation
Flatbed
Inorganic Chemistry
Iron
Machine learning
Measurement techniques
Organic Chemistry
Original Paper
Physical Chemistry
Pollutants
Potassium
Python
Quality assessment
Regression
Scanners
Spectrometry
Thiocyanates
Water quality
Water sampling
Color spaces
Machine learning regression algorithm
Chromium (VI)
Iron (III)
Flatbed scanner colorimetry
Environmental monitoring
ISSN:1735-207X, 1735-2428
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:The study utilizes the colorimetric method (involving 1,5-diphenylcarbazide and potassium thiocyanate as complexing agents), computer vision, and machine learning (ML) regression algorithms to determine the content of Cr (VI) and Fe (III) in water samples. To process digital images of water samples, the integration technique utilized a flatbed scanner known as the CanoScan LiDE 100, operating as a digital image capture device, and its performance was compared to that of conventional instruments. The study reveals that PolyReg and SVR-Poly are the most reliable ML regression algorithms for processing color space data (G and B of RGB, c* of CIELch, and b* of CIELab) of digital images of water samples that contain Cr (VI) and Fe (III). The mean absolute percentage error (MAPE) of the ML regression algorithms PolyReg and SVR-Poly for determining the content of Cr (VI) and Fe (III) is < 10% (with 8.48% error for Cr (VI) determination using PolyReg G of RGB and 6.78% error for Fe (III) determination using PolyReg B of RGB) in the estimation algorithm model. The Mean Absolute Percentage Error (MAPE) indicates that the prediction method is highly accurate. The Limit of Detection (LOD) value of the flatbed scanner colorimetric method integrated with PolyReg G of Red–Green–Blue (RGB) for Chromium (VI) and Blue of RGB for Iron (III) is approximately 0.02 mg/L. The Limit of Detection (LOD) for Chromium (VI) and Iron (III) is 0.0209 mg/L and 0.0257 mg/L, respectively. The limit of detection (LOD) values from this technique are superior to those obtained from certain UV–vis spectrometric and colorimetric methods. The low LOD values demonstrate that this technique is suitable for estimating the concentration of Cr (VI) and Fe (III) in water samples for quality assessment purposes, as these values are below the maximum concentration levels established by various regulations, including US-EPA, ASEAN, and EECCA. Graphical abstract
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1735-207X
1735-2428
DOI:10.1007/s13738-024-03073-z