Determination of four pesticides in honeysuckle by Echo State Network based on excitation-emission matrix fluorescence spectroscopy technique

Honeysuckle is widely known for its effective chemical components and extensive pharmacological effects as a traditional medicinal material in China. Echo State Network (ESN) combined with excitation-emission fluorescence spectroscopy was proposed to detect multiple pesticides in honeysuckle and perform quantitative analysis accurately. Three different models including ESN, RNN, and BPNN were validated by comparing root mean square error, mean absolute error, and mean absolute percentage error. Results revealed that ESN outperformed other two models. For quantitative analysis, the results of three models in terms of recovery rate and average recovery rate were relatively better by ESN training, which were closer to 100% for each pesticide. Therefore, ESN model was considered as the optimal training method for detecting pesticides in honeysuckle and performing better quantitative analysis on account of its effective and accuracy predicting performance, which could provide scientific basis and theoretical reference in future research.