@article{LI2025, 
author = {Anna LI and Yifang ZENG and Yangping WEN and Weiqiang LI and Dan WANG and Wuying YANG and Kaijie TANG},
title = {Portable Electrochemical Sensors Coupled with Machine Learning for Intelligent Analysis of Sulfamethoxazole},
year = {2025},
journal = {Food Science},
volume = {46},
number = {24},
pages = {29-43},
keywords = {sulfamethoxazole, food safety, electrochemical sensing, machine learning, food contaminants},
url = {https://www.sciopen.com/article/10.7506/spkx1002-6630-20250803-008},
doi = {10.7506/spkx1002-6630-20250803-008},
abstract = {In this work, a portable sensor based on ionic liquids-carboxylated carbon nanotubes/screen-printed carbon electrodes (IL-COOH-CNTs/SPCE) was constructed and coupled with machine learning for sensitive sulfamethoxazole (SMZ) detection. The IL-COOH-CNTs/SPCE exhibited low impedance, a large effective surface area, and excellent stability. The sensor displayed a wide linear range from 1.04 to 233.00 μmol/L, with a limit of detection (LOD) of 0.009 μmol/L and a limit of quantification (LOQ) of 0.030 μmol/L. The sensor coupled with least square support vector machine (LS-SVM) achieved superior predictive performance than when coupled with artificial neural network (ANN). Furthermore, the recoveries for spiked food samples using this method showed no significant difference from those obtained using high-performance liquid chromatography (HPLC), confirming the high accuracy and practicality of the developed method. In summary, the IL-COOH-CNTs/SPCE sensor provides a reliable, portable, and efficient alternative for SMZ detection in aquatic and livestock products.}
}