Scholarlink

<p>Methylene blue (MB) residues in aquaculture products pose significant food safety risks due to their toxicity, necessitating rapid and precise detection methods. Conventional chemical analysis methods for MB residues are often cumbersome and time consuming. This study addresses these limitations by developing a rapid, accurate, and non-destructive method for MB residue detection in perch, utilizing visible–near infrared (Vis–NIR) spectroscopy combined with advanced machine learning. Standard normal variate (SNV) was identified as the optimal spectral preprocessing technique. Subsequently, a novel model integrating SNV, monarch butterfly optimization (MBO), and a gated recurrent unit (GRU) network was established, which significantly enhanced the predictive accuracy of the GRU through optimized hyperparameters. The proposed SNV–MBO–GRU model achieved a validation <i>R</i><sup>2</sup> of 0.930, outperforming the particle swarm optimization (PSO)–optimized SNV–GRU model by substantially reducing the root mean square error (RMSE), mean squared error (MSE), and mean absolute error (MAE) by 16.1%, 29.8%, and 21.9%, respectively. This study demonstrates that Vis–NIR spectroscopy combined with the SNV–MBO–GRU algorithm is a high-throughput and chemical-free alternative to traditional chromatography. Despite the need for initial sample preparation, this approach achieves rapid laboratory screening (&lt; 10&#xa0;s/scan) with high precision, significantly improving the efficiency of aquatic food safety monitoring.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Rapid Screening of Methylene Blue Residues in Perch Muscle Using Visible–Near Infrared Spectroscopy Coupled with SNV–MBO–GRU Algorithm

  • 期刊论文

  • 发表日期：

    2026年4月23日

查看全文
  • Juan Zou,
  • Wan Yi Li,
  • Xue Ni Lai,
  • Jun Quan Lin,
  • Qiu Xian Wu,
  • Zi Heng Liao,
  • Ting Wu,
  • Li Lin,
  • Ling Yang

摘要

Methylene blue (MB) residues in aquaculture products pose significant food safety risks due to their toxicity, necessitating rapid and precise detection methods. Conventional chemical analysis methods for MB residues are often cumbersome and time consuming. This study addresses these limitations by developing a rapid, accurate, and non-destructive method for MB residue detection in perch, utilizing visible–near infrared (Vis–NIR) spectroscopy combined with advanced machine learning. Standard normal variate (SNV) was identified as the optimal spectral preprocessing technique. Subsequently, a novel model integrating SNV, monarch butterfly optimization (MBO), and a gated recurrent unit (GRU) network was established, which significantly enhanced the predictive accuracy of the GRU through optimized hyperparameters. The proposed SNV–MBO–GRU model achieved a validation R2 of 0.930, outperforming the particle swarm optimization (PSO)–optimized SNV–GRU model by substantially reducing the root mean square error (RMSE), mean squared error (MSE), and mean absolute error (MAE) by 16.1%, 29.8%, and 21.9%, respectively. This study demonstrates that Vis–NIR spectroscopy combined with the SNV–MBO–GRU algorithm is a high-throughput and chemical-free alternative to traditional chromatography. Despite the need for initial sample preparation, this approach achieves rapid laboratory screening (< 10 s/scan) with high precision, significantly improving the efficiency of aquatic food safety monitoring.