Scholarlink

<p>Firmness can be used as one of the important indexes to indicate the quality of apples, usually predicted non-destructively by acoustic-vibrational signal detection, for the high correlation between acoustic-vibrational signal features and firmness. In this paper, acoustic-vibrational signal features with high temporal correlation are selected as the independent variable of the model. The acoustic-vibrational signal and quality of apples were measured, and then 32&#xa0;time-dependent signal features were selected by MATLAB analysis data, and the firmness of the apple was predicted by a&#xa0;ridge regression model. Using this method, the accuracy of the training set and verification set is 84.7 and 82.4%, respectively. The actual change in apples is consistent with the prediction trend. Because of its more characteristics and more accurate model, this method has better fault tolerance for data, reduces the environmental requirements for acoustic-vibrational signal detection, and paves the way for the firmness prediction of other apple varieties.</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

Non-destructive Prediction of Apple Firmness by Acoustic-Vibrational Signal Ridge Regression Analysis

  • 期刊论文

  • 发表日期：

    2025年8月27日

查看全文
  • Ranran Wang,
  • Xianglu Kong,
  • Bohua Zhang,
  • Qi Fan,
  • Dong Wang,
  • Dongdong Cui

摘要

Firmness can be used as one of the important indexes to indicate the quality of apples, usually predicted non-destructively by acoustic-vibrational signal detection, for the high correlation between acoustic-vibrational signal features and firmness. In this paper, acoustic-vibrational signal features with high temporal correlation are selected as the independent variable of the model. The acoustic-vibrational signal and quality of apples were measured, and then 32 time-dependent signal features were selected by MATLAB analysis data, and the firmness of the apple was predicted by a ridge regression model. Using this method, the accuracy of the training set and verification set is 84.7 and 82.4%, respectively. The actual change in apples is consistent with the prediction trend. Because of its more characteristics and more accurate model, this method has better fault tolerance for data, reduces the environmental requirements for acoustic-vibrational signal detection, and paves the way for the firmness prediction of other apple varieties.