Electronic Nose‐Based a Time‐Sensor Feature Classification Network for Adzuki Bean Origin Traceability
Journal of Food Science · 2026-04 · 91 (4)
DOI: 10.1111/1750-3841.70994 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Food Science, online erschienen am 31.03.2026. Verfasst von Junliang Han und 1 weiteren Autor:innen. Beteiligte Einrichtung: Taizhou Vocational & Technical College, Taizhou, Zhejiang Province, China. Hauptthemen laut MEDLINE: Electronic Nose, Vigna. Die Arbeit nennt 36 Literaturangaben. Gefördert von: 2024 Zhejiang Provincial College Student Science and Technology Innovation Activity Plan (New Talent Plan) Project, 2025 Science and Technology Plan Project of Taizhou, 2023 Research Launch Fund of Taizhou Vocational & Technical College.
Abstract (Originalsprache)
Establishing a technique for identifying the geographical origin of adzuki beans is crucial for combating origin fraud, protecting regional brands. To achieve rapid and non‐destructive discrimination of adzuki bean origins, this study proposes a method that integrates an electronic nose (e‐nose) with a time‐sensor feature classification network (TSFC‐Net). First, gas data from adzuki bean samples spanning six distinct geographical origins are collected using a PEN3 e‐nose system. Subsequently, a time‐sensor feature attention module (TSFAM) is proposed to collaboratively calculate temporal dynamics and sensor cross‐sensitivity features, enabling the adaptive fusion of bidirectional features via soft attention. Finally, based on TSFAM, a lightweight TSFC‐Net is designed to accomplish gas identification of adzuki beans from different origins. Experimental results demonstrate that TSFC‐Net achieves outstanding performance in the origin classification task (accuracy: 98.52%, F1‐score: 98.33%), while also exhibiting favorable lightweight characteristics in terms of parameter count (0.0152 M) and computational complexity (3.2859 M). Through ablation experiments, the rationality and effectiveness of the TSFC‐Net design have been demonstrated. Compared with state‐of‐the‐art gas classification methods, TSFC‐Net achieves the best classification results and stability. This study provides an efficient and reliable technical for the practical application of an e‐nose system in tracing the geographical origin of adzuki beans.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Taizhou Vocational & Technical College, Taizhou, Zhejiang Province, China.
ORCID-Profile: Junliang Han
Förderung
- 2024 Zhejiang Provincial College Student Science and Technology Innovation Activity Plan (New Talent Plan) Project
- 2025 Science and Technology Plan Project of Taizhou
- 2023 Research Launch Fund of Taizhou Vocational & Technical College
- 2024 Science and Technology Plan Project of Taizhou
- 2025 General Project of Chongqing Natural Science Foundation
- 2025 Science and Technology Research Program of Chongqing municipal Education Commission
Zitieren
APA
Han, J., & Tong, F. (2026). Electronic Nose‐Based a Time‐Sensor Feature Classification Network for Adzuki Bean Origin Traceability. Journal of Food Science, 91(4). https://doi.org/10.1111/1750-3841.70994
Vancouver
Han J, Tong F. Electronic Nose‐Based a Time‐Sensor Feature Classification Network for Adzuki Bean Origin Traceability. Journal of Food Science. 2026;91(4). doi:10.1111/1750-3841.70994
BibTeX
@article{Han2026,
author = {Han, Junliang and Tong, Feifei},
title = {Electronic Nose‐Based a Time‐Sensor Feature Classification Network for Adzuki Bean Origin Traceability},
journal = {Journal of Food Science},
year = {2026},
volume = {91},
number = {4},
doi = {10.1111/1750-3841.70994}
}
EUVIMED