Nondestructive detection of apple crispness via optical fiber spectroscopy based on effective wavelengths

Abstract

Crispness is regarded as a significant quality index for apples. Currently, destructive sensory evaluation is the accepted method used to detect apple crispness, making it essential to develop a method that can detect apple crispness in a nondestructive manner. In this study, spectroscopy was proposed as the nondestructive technique for detecting apples' crispness, ultimately obtaining a spectral reflectance curve between 450 nm and 1,000 nm. In order to simplify and improve modeling efficiency, successive projections algorithm (SPA) and x‐loading weights (x‐LW) methods were used to select the most effective wavelengths. Partial least squares (PLS) algorithm, radial basis neural networks (RBNN), and multilayer perceptron neural networks (MLPNN) methods were used to establish the models and to predict the crispness of “Fuji” and “Qinguan” apple varieties. Based on the full wavelength (FW), the prediction accuracy of the PLS model for “Fuji” and “Qinguan” apple varieties was 92.05% and 95.87%, respectively. The effective wavelengths selected via SPA for the “Fuji” apple variety were 450.41 nm, 476.80 nm, 677.75 nm, and 750.72 nm, and the effective wavelengths selected via x‐LW for the “Qinguan” apple variety were 542.51 nm, 544.79 nm, 676.96 nm, and 718.29 nm. The prediction accuracy of the PLS model based on effective wavelengths for “Fuji” and “Qinguan” apple varieties reached 91.31% and 96.41%, respectively. Compared with the RBNN model, the MLPNN model achieved better prediction results for both “Fuji” and “Qinguan” apples, with the prediction accuracy reaching 97.8% and 99.9%, respectively. Based on the above findings, effective wavelength selection and MLPNN modeling were able to detect apple crispness with the highest accuracy. Overall, it can be concluded that the less effective wavelengths are conducive to developing an instrument for crispness detection.

Nondestructive monitoring storage quality of apples at different temperatures by near‐infrared transmittance spectroscopy

“…Previous studies were mostly focused on the detection of apple SSC, and in this study, four quality indexes of apple were tested at the same time. For SSC and firmness, the result was slightly lower than previous studies (Fan et al, 2019;Ma et al, 2018;Ni, Zhu, Gu, & Hu, 2019), the reason may be that the distribution of SSC in apple was not uniform, other studies used the diffuse reflection method to obtain the accuracy SSC content of local apple, which cannot reflect the overall SSC content of apple, while the full transmittance spectrum can collect the spectral information of the whole apple SSC content in this study. For apple TA and VC, only few studies were existed, while this research detected a large number of apple samples and provided a potential of using near-infrared transmittance spectroscopy to detect multiple quality indexes of apple.…”

Feasibility of nondestructive detection of apple crispness based on spectroscopy and machine vision

“…In addition, the evaluation results were easy to obtain, accurate, and reliable. Several studies have explored nondestructive detection of apple crispness (Liu et al, 2020;Ni et al, 2019;Sun et al, 2013). In this and difficult to extract, these features were not considered for the time being while analyzing the influence of appearance image features on crispness detection derivation.…”

“…The changes in firmness and SSC of apples during the postharvest period were studied by NIR spectroscopy (Giovanelli, Sinelli, Beghi, Guidetti, & Casiraghi, 2014). Moreover, two studies conducted nondestructive detection of apple crispness based on spectroscopy (Ni et al, 2020;Ni, Zhu, Gu, & Hu, 2019). Effective wavelength selection methods combined with a variety of modeling methods were used to conduct nondestructive detection of apple crispness (Ni et al, 2019).…”

“…Moreover, two studies conducted nondestructive detection of apple crispness based on spectroscopy (Ni et al, 2020;Ni, Zhu, Gu, & Hu, 2019). Effective wavelength selection methods combined with a variety of modeling methods were used to conduct nondestructive detection of apple crispness (Ni et al, 2019). To nondestructively detect apple crispness, a quantitative prediction model based on wavelengths of 450 to 1,000 nm was established by partial least squares (PLS), and a kinetic model was developed to determine the preservation time of the optimal freshness of apple crispness at room temperature and refrigeration temperature (Ni et al, 2020).…”

Comparison of new hyperspectral index and machine learning models for prediction of winter wheat leaf water content

“…The loading weight based on the PLSR model can establish the proportion of the influence of different dependent variables of that of the total independent variables, which is of great significance for the rapid screening of characteristic bands [ 17 ]. The peak and valley values are extremum and can reflect the influence of a specific waveband on water content.…”