Scholarlink

<p>To explore the feasibility of early, non-destructive freshness grading for kiwifruit and grapes under the present experimental conditions, this study investigated Kyoho grapes (non-climacteric) and Xuxiang kiwifruit (climacteric) stored at 5&#xa0;°C for 15 days, while additional storage temperatures of 10 and 15&#xa0;°C were used to support kinetic and Arrhenius-based quality modeling. Firmness, weight loss, respiration rate, and color parameters were measured on days 0, 3, 6, 9, 12, and 15. In parallel, eight volatile organic compounds (VOCs) selected on the basis of stable detection, dynamic change during storage, metabolic relevance, and correlation with freshness-related indicators were quantified by GC–MS using an internal standard method. Based on the integrated changes in multiple quality indicators, a five-level freshness grading scheme was established, and four machine-learning classifiers were developed using the concentrations of the eight VOCs. The results showed that pronounced changes in characteristic VOCs occurred approximately 3–6 days earlier than the observable declines in firmness and darkening in color. On the independent test set, SVM achieved the best performance for grapes (accuracy: 93.00%), whereas RF performed best for kiwifruit (accuracy: 85.36%). These results support the feasibility of combining key VOC fingerprints with fruit-specific algorithms for early freshness grading of kiwifruit and grapes and provide a basis for future validation under broader cold-chain conditions.</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

Freshness grading prediction based on volatile organic compounds and machine learning: a comparative study of kiwifruit and grapes

  • 期刊论文

  • 发表日期：

    2026年5月14日

查看全文
  • Zhiqiang Wang,
  • Yiqing Yang,
  • Saiwei Ge,
  • Lixin Chen

摘要

To explore the feasibility of early, non-destructive freshness grading for kiwifruit and grapes under the present experimental conditions, this study investigated Kyoho grapes (non-climacteric) and Xuxiang kiwifruit (climacteric) stored at 5 °C for 15 days, while additional storage temperatures of 10 and 15 °C were used to support kinetic and Arrhenius-based quality modeling. Firmness, weight loss, respiration rate, and color parameters were measured on days 0, 3, 6, 9, 12, and 15. In parallel, eight volatile organic compounds (VOCs) selected on the basis of stable detection, dynamic change during storage, metabolic relevance, and correlation with freshness-related indicators were quantified by GC–MS using an internal standard method. Based on the integrated changes in multiple quality indicators, a five-level freshness grading scheme was established, and four machine-learning classifiers were developed using the concentrations of the eight VOCs. The results showed that pronounced changes in characteristic VOCs occurred approximately 3–6 days earlier than the observable declines in firmness and darkening in color. On the independent test set, SVM achieved the best performance for grapes (accuracy: 93.00%), whereas RF performed best for kiwifruit (accuracy: 85.36%). These results support the feasibility of combining key VOC fingerprints with fruit-specific algorithms for early freshness grading of kiwifruit and grapes and provide a basis for future validation under broader cold-chain conditions.