SCIENCE@home

A multi-task deep attention network for simultaneous rapid quantification of sucrose, glucose, and fructose contents in pumpkin using FT-NIR spectroscopy.

Yingchao Xu,Jiayu Luo,Shudan Xue,Huihui Han,Wenlong Luo,Wenjun Liu,Q. Jin,Hui-Chin Lin,Baoling Chen,Yingyin Lin,Rong-Xiang Zhang,Yujuan Zhong

Published 2025 in Food Chemistry

ABSTRACT

Sugars critically influence pumpkin quality, however, quantifying them using Fourier transform near-infrared (FT-NIR) spectroscopy remains challenging due to spectral overlap. This study developed a Multi-Task Deep Attention Network (MTDAN) integrating deep architecture, attention mechanisms, and multi-task learning for simultaneous quantification of three major soluble sugars. Pumpkin FT-NIR analysis showed MTDAN outperformed partial least squares regression, Ridge regression, and random forest. MTDNA achieved superior prediction accuracy (coefficient of determination of prediction R2p = 0.91-0.93 and a root mean square error of prediction RMSEP = 8.38-10.30 mg/g DW), and wide concentration ranges of fructose (20.18-139.68 mg/g DW), glucose (16.52-157.73 mg/g DW), and sucrose (13.54-209.64 mg/g DW), along with robustness to spectral overlap. Band-specific experiments revealed that localized spectral regions (4000-4800 nm for fructose and glucose, 5600-6400 nm for sucrose) contained actionable signals. This study established MTDAN as a versatile tool for accurate quality assessment of sugars in pumpkins.

PUBLICATION RECORD

CITATION MAP

EXTRACTION MAP

CLAIMS

  • No claims are published for this paper.

CONCEPTS

  • No concepts are published for this paper.

REFERENCES

Showing 1-68 of 68 references · Page 1 of 1

CITED BY

  • No citing papers are available for this paper.

Showing 0-0 of 0 citing papers · Page 1 of 1