Research on prediction of yellow flesh peach firmness using a novel acoustic real-time detection device and Vis/NIR technology

Abstract

Firmness is a critical indicator for predicting fruit ripeness, optimal harvest date, and shelf life. In this study, a novel fruit acoustic real-time detection prototype device and a conventional visible near-infrared (Vis/NIR) spectroscopy real-time detection device were used to collect acoustic and spectral signals from yellow flesh peaches to jointly predict their firmness. The acoustic and optical signals were generated into one- and two-dimensional feature data by complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN), continuous wavelet transform (CWT) and Gramian angular field (GAF) data processing methods. Based on these data, a variety of yellow flesh peach firmness prediction models were constructed in this study, including partial least square (PLS), support vector regression (SVR), Swin Transformer (SwinT), and SwinT-PLS/SVR. The experimental results showed that the SwinT-PLS model based on the fusion of competitive adaptive re-weighted sampling (CARS)-acoustic image features and CARS-Vis/NIR spectral features showed the best prediction performance (R²P = 0.951, the RMSEP = 0.443 N/mm, RPDP = 4.339), and the prediction performance is significantly higher than that of the prediction model based on single acoustic and Vis/NIR spectral data. The method proposed can fast, non-destructively, accurately predict fruit firmness and has excellent prospects for commercial real-time fruit sorting applications.

Plant phenotyping relevance

桃果実の硬度という植物器官形質を、音響・Vis/NIRセンサーと画像化・機械学習で非破壊推定する新規リアルタイム手法の開発が中心であり、性能評価も行っている。

Code and data availability

公開状態または取得可能な本文経路を確認できませんでした。

No evidence-backed public reproduction asset is currently recorded.