Prediction of Soluble Solids Content in Green Plum by Using a Sparse Autoencoder
Source abstract
Abstract
The soluble solids content (SSC) affects the flavor of green plums and is an important parameter during processing. In recent years, the hyperspectral technology has been widely used in the nondestructive testing of fruit ingredients. However, the prediction accuracy of most models can hardly be improved further. The rapid development of deep learning technology has established the foundation for the improvement of building models. A new hyperspectral imaging system aimed at measuring the green plum SSC is developed, and a sparse autoencoder (SAE)–partial least squares regression (PLSR) model is combined to further improve the accuracy of component prediction. The results of the experiment show that the SAE–PLSR model, which has a correlation coefficient of 0.938 and root mean square error of 0.654 for the prediction set, can achieve better performance for the SSC prediction of green plums than the three traditional methods. In this paper, integration approaches have combined three different pretreatment methods with PLSR to predict the SSC in green plums. The SAE–PLSR model has shown good prediction performance, indicating that the proposed SAE–PLSR model can effectively detect the SSC in green plums.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Spectroscopy and Chemometric Analyses · Remote-Sensing Image Classification · Water Quality Monitoring and Analysis
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
College of Mechanical and Electronic Engineering, Nanjing Forestry University, Nanjing 210037, China
Funding
Jiangsu Agricultural Science and Technology Innovation Fund
References (36)
Show source-provided references
1. Wang, X., Matetić, M., Zhou, H., Zhang, X., and Jemrić, T. (2017). Postharvest Quality Monitoring and Variance Analysis of Peach and Nectarine Cold Chain with Multi-Sensors Technology. Appl. Sci., 7.10.31219/osf.io/cfr72 ↗
2. Xiao, H., Feng, L., Song, D., Tu, K., Peng, J., and Pan, L. (2019). Grading and Sorting of Grape Berries Using Visible-Near Infrared Spectroscopy on the Basis of Multiple Inner Quality Parameters. Sensors, 19.10.3390/s19112600 ↗
3. Assessment of Tomato Color by Spatially Resolved and Conventional Vis/NIR Spectroscopies
4. Assessment of Tomato Soluble Solids Content and pH by Spatially-Resolved and Conventional Vis/NIR Spectroscopy10.1016/j.jfoodeng.2018.05.008 ↗
5. Detection of Internal Defect of Apples by a Multichannel Vis/NIR spectroscopic system10.1016/j.postharvbio.2019.111065 ↗
6. Variable Weighted Convolutional Neural Network for the Nitrogen Content Quantization of Masson Pine Seedling Leaves with Near-Infrared Spectroscopy10.1016/j.saa.2018.10.028 ↗
7. Heterospectral Two-Dimensional Correlation Analysis with Near-Infrared Hyperspectral Imaging for Monitoring Oxidative Damage of Pork Myofibrils During Frozen Storage10.1016/j.foodchem.2017.12.050 ↗
8. Wang, X., An, S., Xu, Y., Hou, H., Chen, F., Yang, Y., Zhang, S., and Liu, R. (2020). A Back Propagation Neural Network Model Optimized by Mind Evolutionary Algorithm for Estimating Cd, Cr, and Pb Concentrations in Soils Using Vis-NIR Diffuse Reflectance Spectroscopy. Appl. Sci., 10.10.3390/app10010051 ↗
9. Zheng, X., Peng, Y., and Wang, W. (2017). A Nondestructive Real-Time Detection Method of Total Viable Count in Pork by Hyperspectral Imaging Technique. Appl. Sci., 7.10.3390/app7030213 ↗
10. Protein Content Prediction in Single Wheat Kernels Using Hyperspectral Imaging10.1016/j.foodchem.2017.07.048 ↗
11. Quantitative Determination of Rice Starch Based on Hyperspectral Imaging Technology10.1080/10942912.2017.1326058 ↗
12. Varietal Classification and Antioxidant Activity Prediction of Osmanthus Fragrans Lour. Flowers Using UPLC–PDA/QTOF–MS and Multivariable Analysis10.1016/j.foodchem.2016.08.125 ↗
13. Determination of Fat Content in Chicken Hamburgers Using NIR Spectroscopy and the Successive Projections Algorithm for Interval Selection in PLS Regression (iSPA-PLS)10.1016/j.saa.2017.08.046 ↗
14. Clear-sky Direct Normal Irradiance Estimation Based on Adjustable Inputs and Error Correction10.1063/1.5094808 ↗
15. Rapid Detection of Adulteration of Minced Beef Using Vis/NIR Reflectance Spectroscopy with Multivariate Methods10.1016/j.saa.2019.118005 ↗
16. Deng, F., Pu, S., Chen, X., Shi, Y., Yuan, T., and Pu, S. (2018). Hyperspectral Image Classification with Capsule Network Using Limited Training Samples. Sensors, 18.10.3390/s18093153 ↗
17. Liu, L., Ji, M., and Buchroithner, M. (2018). Transfer Learning for Soil Spectroscopy Based on Convolutional Neural Networks and Its Application in Soil Clay Content Mapping Using Hyperspectral Imagery. Sensors, 18.10.3390/s18093169 ↗
18. Li, K., Wang, M., Liu, Y., Yu, N., and Lan, W. (2019). A Novel Method of Hyperspectral Data Classification Based on Transfer Learning and Deep Belief Network. Appl. Sci., 9.10.3390/app9071379 ↗
19. A Sparse Auto-encoder-Based Deep Neural Network Approach for Induction Motor Faults Classification10.1016/j.measurement.2016.04.007 ↗
20. Feature Learning Based on SAE–PCA Network for Human Gesture Recognition in RGBD Images10.1016/j.neucom.2014.06.086 ↗
21. Spatial-spectral Unsupervised Convolutional Sparse Auto-encoder Classifier for Hyperspectral Imagery10.14358/PERS.83.3.195 ↗
22. Cost-sensitive Stacked Sparse Auto-encoder Models to Detect Striped Stem Borer Infestation on Rice Based on Hyperspectral Imaging10.1016/j.knosys.2019.01.003 ↗
23. Structured AutoEncoders for Subspace Clustering10.1109/TIP.2018.2848470 ↗
24. Application of Generative Autoencoder in de Novo Molecular Design10.1002/minf.201700123 ↗
25. A New Deep Transfer Learning Based on Sparse Auto-Encoder for Fault Diagnosis10.1109/TSMC.2017.2754287 ↗
26. Towards Enhancing Stacked Extreme Learning Machine with Sparse Autoencoder by Correntropy10.1016/j.jfranklin.2017.08.014 ↗
27. Visualizing quantitatively the freshness of intact fresh pork using acousto-optical tunable filter-based visible/near-infrared spectral imagery10.1016/j.compag.2013.08.025 ↗
28. Comparison of Multivariate Methods for Estimating Selected Soil Properties from Intact Soil Cores of Paddy Fields by Vis–NIR Spectroscopy10.1016/j.geoderma.2017.09.013 ↗
29. Ni, C., Zhang, Y., and Wang, D. (2018). Moisture Content Quantization of Masson Pine Seedling Leaf Based on Stacked Autoencoder with Near-Infrared Spectroscopy. J. Electr. Comput. Eng., 1–8.10.1155/2018/8696202 ↗
30. Ni, C., Li, Z., Zhang, X., Sun, X., Huang, Y., Zhao, L., Zhu, T., and Wang, D. (2020). Online Sorting of the Film on Cotton Based on Deep Learning and Hyperspectral Imaging. IEEE Access.10.1109/ACCESS.2020.2994913 ↗
31. Estimation of Soil Salt Content (SSC) in The Ebinur Lake Wetland National Nature Reserve (ELWNNR), Northwest China, Based on a Bootstrap-BP Neural Network Model and Optimal Spectral Indices10.1016/j.scitotenv.2017.10.025 ↗
32. Determination of Total Iron-reactive Phenolics, Anthocyanins and Tannins in Wine Grapes of Skins and Seeds Based on Near-infrared Hyperspectral Imaging10.1016/j.foodchem.2017.06.007 ↗
33. Comparison of Hyperspectral Imaging and Computer Vision for Automatic Differentiation of Organically and Conventionally Farmed Salmon10.1016/j.jfoodeng.2016.10.021 ↗
34. Application of Hyperspectral Imaging for Nondestructive Measurement of Plum Quality Attributes10.1016/j.postharvbio.2018.03.008 ↗
35. A New Spectral Variable Selection Pattern Using Competitive Adaptive Reweighted Sampling Combined with Successive Projections Algorithm10.1039/C4AN00837E ↗
36. Extreme Learning Machine for Multilayer Perceptron10.1109/TNNLS.2015.2424995 ↗