An Emerging Machine Learning Strategy for the Fabrication of Nanozyme Sensor and Voltametric Determination of Benomyl In Agro-Products

Abstract

An emerging machine learning (ML) strategy for the fabrication of a nanozyme sensor based on multi-walled carbon nanotubes (MWCNTs)/graphene oxide (GO)/dendritic silver nanoparticles (AgNPs) nanohybrid and the voltametric determination of benomyl (BN) residues in tea and cucumber samples is proposed. Nanohybrid is prepared by the electrodeposition of dendritic AgNPs on the surface of MWCNTs/GO obtained by a simple mixed-strategy. The orthogonal experiment design combined with back propagation artificial neural network with genetic algorithm is used to solve multi-factor problems caused by the fabrication of nanohybrid sensor for BN. Both support vector machine (SVM) algorithm and least square support vector machine (LS-SVM) algorithm are used to realize the intelligent sensing of BN compared with the traditional method. The as-fabricated electrochemical sensor displays high electrocatalytic capacity (excellent voltammetric response), unique oxidase-like characteristic (nanozyme), wide working range (0.2 - 122.2 μM), good practicability (satisfactory recovery). It is feasible and practical that ML guides the fabrication of nanozyme sensor and the intelligent sensing of BN compared with the traditional method. This work will open a new avenue for guiding the synthesis of sensing materials, the fabrication of sensing devices and the intelligent sensing of target analytes in the future.

Machine learning in nanozymes: from design to application

“…Xu et al employed an orthogonal experimental design in combination with the BP artificial neural network-genetic algorithm (BP–ANN–GA) to assess the impact of four factors (volume ratio of graphene oxide (GO) and multi-walled carbon nanotubes (MWCNTs), silver nitrate concentration, CV deposition cycle, and pH of phosphate buffer) on the peak current value (I) of benzyl (BN). 60 This approach aimed to optimize the preparation technique for the nanozyme-based sensor and determine the optimal experimental conditions. Under these conditions, the nanozymes catalysed a BN reaction on the working electrode, generating an electrical signal.…”

Rational Integration of Nanozyme Probe and Smartphone Device for On‐Site Analysis

“…[79][80][81] Recently, multiple machine learning algorithms have been exploited to help constructing nanozyme-based sensors. [82][83][84] By virtue of machine learning, nanozyme sensors with polytype of output signals, meanwhile the signals could be processed simultaneously within one smartphone, are highly expected, yet underdeveloped. It is due to machine learning algorithms rely on huge computing data, which is still difficult to be undertaken by smartphones at present.…”

“…In fact, to achieve better selectivity and accuracy, nanozyme‐smartphone integrated sensing platforms with dual‐signal output modes instead of only one output signal were proposed, in which colorimetric‐electrochemical, colorimetric‐fluorescence and colorimetric‐Raman scattering have been reported [79–81] . Recently, multiple machine learning algorithms have been exploited to help constructing nanozyme‐based sensors [82–84] . By virtue of machine learning, nanozyme sensors with polytype of output signals, meanwhile the signals could be processed simultaneously within one smartphone, are highly expected, yet underdeveloped.…”

Intelligent analysis of carbendazim in agricultural products based on a ZSHPC/MWCNT/SPE portable nanosensor combined with machine learning methods

“…In previous studies, we found that assembled multi-walled carbon nanotubes (MWCNTs) could improve the electrocatalytic performance and stability of their composites. 26 Therefore, in this study, the ZSHPC/MWCNT/SPE sensor was prepared using the characteristics of MWCNT and ZSHPC materials for the detection of CBZ in agricultural products.…”