•  
  •  
 

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: 0009-0001-2074-2007

DEVRİM 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

Creative Commons Attribution 4.0 International License
This work is licensed under a Creative Commons Attribution 4.0 International License.

Share

COinS