Turkish Journal of Electrical Engineering and Computer Sciences
Author ORCID Identifier
SÜLEYMAN AŞIR: 0000-0002-6672-6862
NEMAH ABU SHAMA: 0000-0002-3290-152X
NAJYA MAROOF SALEEM: 0009-0001-2074-2007DEVRİM KAYALI: 0000-0002-0307-8538
KAMİL DİMİLİLER: 0000-0002-2751-0479
Abstract
Most common electrochemical analysis techniques used to evaluate enzymes, proteins, and heavy metals over a wide potential range include electrochemical impedance EIS, differential pulse voltammetry DPV, and square wave voltammetry SQWV. Machine leaning algorithms MLA are employed to classify the Potassium ferricyaniyde K3Fe(CN)6 concentrations using a modified carbon paste electrode CPE embedded with iron (II, III) oxide (Fe3O4) NPs. The CV, DPV, and SQWV voltametric data collected from all K3Fe(CN)6 concentrations were used as input data to the machine learning algorithms. Signaling current of K3Fe(CN)6 concentrations improved at Fe3O4 modified with nanoparticles NPs CPE in a comparison with the unmodified CPE from the results of the CV, DPV, and SQWV experiments. The high conductivity of Fe3O4 NPs led to an increase in their electrical signals in CV, DPV, and SQWV measurements. The findings demonstrated that K3Fe(CN)6 provided a linear relationship for CV, DPV, and SQWV throughout the concentrations variety of 2.0 to 10.0 mM (R2 = 0.9898, 0.9932, and 0.9937, respectively). For CV, DPV, and SQWV, the limit of detection LOD was determined to be 0.380, 0.320, and 0.300 mM, respectively. Machine learning techniques are often employed for categorization once the machine learning ML methodology has been applied to the CV, DPV, and SQWV data. To categorize the variants, various machine learning techniques have been taken into consideration. The results demonstrated that for CV, DPV, and SQWV, respectively, the ratio of analyte’s classification accuracy at CPE was determined to be 100%, 100%, and 86.7%. For CV, DPV, and SQWV, individually, the classification accuracy of analyte at modified CPE was found to be 100%, 82.5%, and 100%. The results demonstrate that ML is capable of analyzing a broad spectrum of voltammetric data, enabling the rapid and precise determination of various of redox reactions during the data processing method.
DOI
10.55730/1300-0632.4111
Keywords
Potassium Ferricyanide, Iron (II, III) oxide NPs, oxidation reduction reaction, Machine learning, Voltammetric techniques
First Page
15
Last Page
31
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.
Recommended Citation
AŞIR, SÜLEYMAN; SHAMA, NEMAH ABU; SALEEM, NAJYA MAROOF; KAYALI, DEVRİM; and DİMİLİLER, KAMİL
(2025)
"Machine Learning Models Approach for the Quantitative Classification of Ferricyanide Compound Using Electrochemical Detection with CPE-Fe3O4NPs,"
Turkish Journal of Electrical Engineering and Computer Sciences: Vol. 33:
No.
1, Article 3.
https://doi.org/10.55730/1300-0632.4111
Available at:
https://journals.tubitak.gov.tr/elektrik/vol33/iss1/3
Included in
Computer Engineering Commons, Computer Sciences Commons, Electrical and Computer Engineering Commons