| Abstrakt: |
Introduction1 The development of portable devices for real-time quality assessment of sugarcane is an essential necessity in the agricultural and industrial technology of sugarcane production and processing. Attributes of sugarcane such as sugar concentration and water content can be utilized for this purpose. Near infrared (NIR) spectroscopy has been one of the most widely applied techniques for quality evaluation of sugarcane. However, NIR spectrophotometers in the full NIR wavelength range (up to 2500 nm) are expensive devices that are not readily available for portable applications. Short-wave NIR devices in the range of 1100 nm are available at lower costs but need to be evaluated for specific applications. On the other hand, dielectric spectroscopy has attracted the attention of researchers for quality evaluation of agricultural and food products. In a previous study, a parallelplate capacitance sensor was developed and evaluated for non-destructive measurement of sugarcane Brix (total soluble solids) and Pol (sucrose concentration) as well as water content, in the frequency range of 0-10 MHz. The results showed excellent prediction models with root mean square errors smaller than 0.3 for Brix and Pol. This study aimed to develop and evaluate a dielectric sensor that can be extended for portable measurements on standing sugarcane stalk in comparison with short-wave NIR (SWNIR) spectroscopy to address how the fusion of the two methods may improve the accuracy of models for predicting sugarcane Brix. Materials and Methods A dielectric sensor in the form of a gadget was developed with metallic electrodes to encompass the sugarcane stalk samples. The dielectric sensor was excited with a sinusoidal voltage within 0-150 MHz frequency range by a function generator, and the conductive power through the electrodes was measured using a spectrum analyzer. 105 sugarcane stalk samples were prepared from seven sugarcane varieties and scanned with the dielectric sensor. The samples were also subjected to Vis-SWNIR radiation in the wavelength range of 400-1100 nm, and the reflectance spectra were captured. Reference Brix and water content of the samples were determined using a portable refractometer and oven-drying method, respectively. Regression analyses and artificial neural networks were performed on independent and combined data from dielectric and Vis-SWNIR spectroscopy to develop prediction models for Brix and water content. Results and Discussion Partial least squares regression on independent data sets of each instrument resulted in RMSEP = 1.14 and RMSEP = 1.88 for Brix using Vis-SWNIR and dielectric spectroscopy, respectively. Moreover, data fusion of dielectric and Vis-SWNIR spectroscopy at a low level for the prediction of Brix significantly improved the prediction accuracy to R²P = 0.94 and RMSEP= 0.74. The medium-level data fusion resulted in R²P = 0.89 and RMSEP = 0.93 for prediction of water content. Conclusion In this study, the accuracy of using Vis-SWNIR and dielectric spectroscopy data for predicting Brix and water content in sugarcane stalk samples was evaluated. To develop the prediction models, partial least squares (PLS) regression and artificial neural network (ANN) were compared. First, the prediction models were developed based on Vis-SWNIR and dielectric spectroscopy independently. Then, the two techniques were fused and the improvement in the prediction accuracy was investigated. Fusing the two methods at an intermediate level lowered the RMSE of Brix to 0.74, showing noticeable improvement compared to previous studies. Based on the achieved results, developing a fusion probe for SWNIR and dielectric spectroscopy and designing the measuring system could be the aim of future studies for in-situ evaluation of sugarcane quality parameters. Due to the importance of sugarcane quality evaluation, during growth and maturity, the results of this study can have a significant role in the development of a portable device that combines NIR and dielectric spectroscopy methods for fast and non-destructive evaluation of sugarcane quality parameters. [ABSTRACT FROM AUTHOR] |
