Estimation model of soluble solids content in bagged and non-bagged apple fruits based on spectral data

Abstract Response of bagged and non-bagged apple to light is different. Meanwhile, for the same variety, average sugar content of the non-bagged apple is higher than that of the bagged apple. Spectral data have been used to rapidly and quantitatively determine soluble solids content (SSC) of the bagged and non-bagged apples. First, the spectral data were acquired from four circular areas evenly distributed around the equatorial circumference of each apple, which would be used to determine the SSC value. Standard normal variable (SNV) transformation was used to pre-process the spectral data. Second, Monte Carlo cross validation (MCCV) algorithm was employed to reject abnormal samples. Sample set was divided into a training set and a test set by uniform sampling. Third, Characteristic wavelengths were extracted by principal component analysis (PCA) and ant colony optimization (ACO). Finally, regression models between the spectra and SSCs were established by back-propagation neural network (BP-ANN) and partial least squares (PLS). In this study, six non-destructive SSC estimation models were established for the bagged and non-bagged apple fruits, where optimal models were established respectively by comparing estimation accuracy. Results showed that ACO-PLS model achieved the highest SSC estimation accuracy for both bagged and non-bagged apples. The root mean square error (RMSE) and correlation coefficient (R) for the training set of the non-bagged apple fruits were 0.35 °Bx and 0.93, while that for the corresponding test set were 0.32 °Bx and 0.93, respectively. The RMSE and R for the training set of the bagged apple fruits were 0.38 °Bx and 0.94, and that for the corresponding test set were 0.31 °Bx and 0.96, respectively. It indicated the ACO-PLS estimation model is promising for grading interior apple quality because it provides a quick and non-destructive method for measuring the SSC.

[1]  Anette Kistrup Thybo,et al.  Explaining Danish children's preferences for apples using instrumental, sensory and demographic/behavioural data , 2004 .

[2]  Wouter Saeys,et al.  Measurement of optical properties of fruits and vegetables: A review , 2020 .

[3]  C. Kingston.  Maturity Indices for Apple and Pear , 2010 .

[4]  S. Gupta,et al.  Improving ant colony optimization algorithm for data clustering , 2010, ICWET.

[5]  Sara Serra,et al.  Apple fruit quality: Overview on pre-harvest factors , 2018 .

[6]  Qibing Zhu,et al.  Model fusion for prediction of apple firmness using hyperspectral scattering image , 2012 .

[7]  R. Lu,et al.  Analysis of spatially resolved hyperspectral scattering images for assessing apple fruit firmness and soluble solids content , 2008 .

[8]  A. Mahadevan-Jansen,et al.  Automated Method for Subtraction of Fluorescence from Biological Raman Spectra , 2003, Applied spectroscopy.

[9]  Umezuruike Linus Opara,et al.  Analytical methods for determination of sugars and sweetness of horticultural products—A review , 2015 .

[10]  Laijun Sun,et al.  Pixel based bruise region extraction of apple using Vis-NIR hyperspectral imaging , 2018, Comput. Electron. Agric..

[11]  A. C. Galvis-Sánchez,et al.  Effects of preharvest, harvest and postharvest factors on the quality of pear (cv. "Rocha") stored under controlled atmosphere conditions , 2004 .

[12]  A. Savitzky,et al.  Smoothing and Differentiation of Data by Simplified Least Squares Procedures. , 1964 .

[13]  Timo Mantere,et al.  A Review of Optical Nondestructive Visual and Near-Infrared Methods for Food Quality and Safety , 2013 .

[14]  M. Vázquez,et al.  Fraud detection in hen housing system declared on the eggs' label: An accuracy method based on UV-VIS-NIR spectroscopy and chemometrics. , 2019, Food chemistry.

[15]  Spectral analysis for the early detection of anthracnose in fruits of Sugar Mango (Mangifera indica) , 2020, Computers and Electronics in Agriculture.

[16]  J. Pallone,et al.  Detection and identification of açai pulp adulteration by NIR and MIR as an alternative technique: Control charts and classification models. , 2019, Food research international.

[17]  K. Peiris,et al.  Spatial variability of soluble solids or dry-matter content within individual fruits, bulbs, or tubers : Implications for the development and use of NIR spectrometric techniques , 1999 .

[18]  Oliver Kohlbacher,et al.  Food monitoring: Screening of the geographical origin of white asparagus using FT-NIR and machine learning , 2019, Food Control.

[19]  Chunjiang Zhao,et al.  A multi-region combined model for non-destructive prediction of soluble solids content in apple, based on brightness grade segmentation of hyperspectral imaging , 2019, Biosystems Engineering.

[20]  Fabíola Manhas Verbi Pereira,et al.  Robust PLS models for soluble solids content and firmness determination in low chilling peach using near-infrared spectroscopy (NIR) , 2016 .

[21]  Haitao Shi,et al.  Evaluation of near-infrared (NIR) and Fourier transform mid-infrared (ATR-FT/MIR) spectroscopy techniques combined with chemometrics for the determination of crude protein and intestinal protein digestibility of wheat. , 2019, Food chemistry.

[22]  Muhammad Zareef,et al.  Evaluation of matcha tea quality index using portable NIR spectroscopy coupled with chemometric algorithms. , 2019, Journal of the science of food and agriculture.

[23]  L. A. Stone,et al.  Computer Aided Design of Experiments , 1969 .

[24]  O. Arakawa.  Effect of temperature on anthocyanin accumulation in apple fruit as affected by cultivar, stage of fruit ripening and bagging , 1991 .

[25]  Xin Zhang,et al.  Multi-class fruit-on-plant detection for apple in SNAP system using Faster R-CNN , 2020, Comput. Electron. Agric..