Estimation Of Sugar Content Research Articles

A matter of the metric? Sugar content overestimation is less pronounced in sugar cubes versus grams

To make healthy food choices, consumers need to be aware of the sugar content of foods. Units act as an environmental cue that might influence sugar content estimation accuracy. The present study (1) tested whether estimations of sugar content are more accurate in sugar cubes vs grams, (2) compared accuracy of sugar content to estimations of the foods’ weight and energy content, and (3) investigated gender, education, and body mass index as potential correlates. A sample of 886 adults was randomly assigned to estimating the sugar content of 10 common foods in grams or cubes. Estimations of sugar content diverged considerably from actual values in both groups (0.22 ≤ Cohen's dsgrams ≤ 1.20; 0.20 ≤ Cohen's dscubes ≤ 1.10), but were more pronounced for sugar content estimations in grams in 7 out of 10 foods (ts ≥ 4.04, Ps < .001, Cohen's ds ≥ 0.14). Sugar content misestimation was somewhat more pronounced than misestimation of weight (0.05 ≤ Cohen's ds ≤ 1.43) and energy content (0.04 ≤ Cohen's ds ≤ 1.19). Relationships between sugar content misestimation and gender (0.00 ≤ Cohen's ds ≤ 0.33), education (–0.07 ≤ r ≤ 0.11), and body mass index (–0.08 ≤ r ≤ 0.06) were mostly negligible. Although sugar content estimations were somewhat more accurate in sugar cubes vs grams, estimation accuracy is generally low. In addition to promoting consumers’ knowledge through labeling and education, additional avenues for interventions might need to be explored for sizeable effects on food choices.

Evaluating the generalization ability of deep learning models: An application on sugar content estimation from hyperspectral images of wine grape berries

The assessment of grape ripeness is an extremely important factor in winemaking and has a direct impact on wine quality. This process is usually carried out with a traditional laboratory analysis, a costly procedure that destroys the grapes selected for analysis. Consequently, the research in precision viticulture has shifted focus to the development of digital processes that are fast and non-intrusive. In this context, the use of hyperspectral imaging paired with prediction models for the estimation of oenological parameters has gained wide recognition. The major drawback of these solutions is the extreme variability presented by the data, aligned with a small number of samples for training, derived from the high cost of acquiring new samples infield. Achieving a satisfactory generalization capacity while working on small data sets with such high variability is a serious challenge, and in this work we aim to provide a pipeline on how to properly build validation and test sets that allow for a correct evaluation of performance, avoiding common misconceptions such as using the R2 metric for model selection or creating models based on biased data sets. Additionally, we implement and evaluate different architectures, namely Residual Networks, InceptionTime and MiniRocket, to showcase that deep learning techniques can accurately predict sugar content from different vintages and varieties of wine grape berries, maintaining a strong generalization capacity even in a setting of high variability and small number of samples. Finally, our results also suggest that adding more relevant features to better characterize the data might be enough for the networks to adjust and produce accurate estimates of sugar content, which would eliminate the necessity to capture new samples on a yearly basis.

Advancing grape chemical analysis through machine learning and multi-sensor spectroscopy

Chemical testing of grapes is essential for wine-making, allowing informed decisions about grape composition and potential wine characteristics. However, current invasive laboratory methods to identify the key components as total soluble solid contents and acidity, present challenges in terms of time and cost. To address these issues, non-invasive techniques using Visible-Near-Infrared (Vis-NIR) and Raman spectroscopy are explored for rapid and accurate grape chemical analysis. Various machine learning methods are deployed in this study to address the challenges of grape chemical analysis and enhance estimation accuracy. The contributions of this research include pioneering a direct comparison between Vis-NIR and Raman spectroscopy, establishing a regression model benchmark, and providing an open-source dataset for grape composition analysis. We identify Gaussian Process Regression (GPR) and Support Vector Machine Regression (SVMR) as the most effective regression models, with GPR achieving an RMSE of 0.977 °Birx for sugar content estimation in French Colombard grapes and SVMR achieving 0.780 °Brix for Cabernet grapes. For pH estimations, GPR and SVMR also perform exceptionally well.

Machine Learning Evaluation of Fruit Ripeness with Multidimensional Sparse-Dataset Calibration

HighlightsThis article provides a machine-learning method for estimation of sugar content in target fruit using color appearance.Complex networks based on multidimensional datasets work effectively for color sensor calibration and data rebalancing.Beyond datapoint sparsity in datasets, estimation accuracy in sugar content is assured when an unsupervised-learning algorithm classifies the multidimensional datapoints composed of fruit color and relevant quantities.Abstract. In agriculture, harvests of fruits and vegetables depend on their ripeness, in which farmers should rely not only on the eye-sensed outlook but rigorously on constituents inside the targets, like sugar content. So far, detail measurements on the outlook color of fruits have been widely reported to detect suitable harvest times, where non-destructive instruments, which are costly in general agriculture fields, work well for color estimation whose resolution level is much higher than human eyes. In this study, we propose a scheme with a calibration procedure for sugar content prediction from outlook-color quantities, which is applicable even if a sensor includes systematic errors in output signals or the base dataset includes some datapoint sparsity. Most multidimensional data, which are both in agriculture and in other general cases, are imperfect in terms of several aspects, but they can be useful when we take appropriate sparsity detection and setting of rebalancing weights into account for machine learning procedures. We newly introduce a complex-network method for this purpose, and after the color calibration, we successfully obtain accurate hue and chroma, which are quantities representing a position on calibrated color coordinate, to predict °Brix sugar content in Japanese pears. Keywords: Asian pear, Color Elements, Fruit Ripening, °Brix Sugar Content, OHD.

Rapid Determination of Wine Grape Maturity Level from pH, Titratable Acidity, and Sugar Content Using Non-Destructive In Situ Infrared Spectroscopy and Multi-Head Attention Convolutional Neural Networks.

In the pursuit of enhancing the wine production process through the utilization of new technologies in viticulture, this study presents a novel approach for the rapid assessment of wine grape maturity levels using non-destructive, in situ infrared spectroscopy and artificial intelligence techniques. Building upon our previous work focused on estimating sugar content (∘Brix) from the visible and near-infrared (VNIR) and short-wave infrared (SWIR) regions, this research expands its scope to encompass pH and titratable acidity, critical parameters determining the grape maturity degree, and in turn, wine quality, offering a more representative estimation pathway. Data were collected from four grape varieties-Chardonnay, Malagouzia, Sauvignon Blanc, and Syrah-during the 2023 harvest and pre-harvest phenological stages in the vineyards of Ktima Gerovassiliou, northern Greece. A comprehensive spectral library was developed, covering the VNIR-SWIR spectrum (350-2500 nm), with measurements performed in situ. Ground truth data for pH, titratable acidity, and sugar content were obtained using conventional laboratory methods: total soluble solids (TSS) (∘Brix) by refractometry, titratable acidity by titration (expressed as mg tartaric acid per liter of must) and pH by a pH meter, analyzed at different maturation stages in the must samples. The maturity indicators were predicted from the point hyperspectral data by employing machine learning algorithms, including Partial Least Squares regression (PLS), Random Forest regression (RF), Support Vector Regression (SVR), and Convolutional Neural Networks (CNN), in conjunction with various pre-processing techniques. Multi-output models were also considered to simultaneously predict all three indicators to exploit their intercorrelations. A novel multi-input-multi-output CNN model was also proposed, incorporating a multi-head attention mechanism and enabling the identification of the spectral regions it focuses on, and thus having a higher interpretability degree. Our results indicate high accuracy in the estimation of sugar content, pH, and titratable acidity, with the best models yielding mean R2 values of 0.84, 0.76, and 0.79, respectively, across all properties. The multi-output models did not improve the prediction results compared to the best single-output models, and the proposed CNN model was on par with the next best model. The interpretability analysis highlighted that the CNN model focused on spectral regions associated with the presence of sugars (i.e., glucose and fructose) and of the carboxylic acid group. This study underscores the potential of portable spectrometry for real-time, non-destructive assessments of wine grape maturity, thereby providing valuable tools for informed decision making in the wine production industry. By integrating pH and titratable acidity into the analysis, our approach offers a holistic view of grape quality, facilitating more comprehensive and efficient viticultural practices.

In situ grape ripeness estimation via hyperspectral imaging and deep autoencoders

The estimation of the grapes’ maturity in the field using non-destructive techniques is of high interest for the high-valued vinified grapes, particularly towards the development of fully automated agrobots that perform selective harvesting operations. Whereas infrared spectroscopy has been employed using point spectrometers in the laboratory and in the field, imaging spectrometers have mainly been tested in controlled laboratory conditions due to issues with varying illumination. In this paper, the application of the autoencoder framework is proposed, which is employed to transform the raw recorded spectra, regardless of illumination conditions, into standardized reflectance spectra; thus addressing the inherent difficulties which hamper the direct application of hyperspectral imaging in the field. To validate the methodology, the sugar content (∘Brix) of four grape varieties, namely Chardonnay, Malagouzia, Sauvignon-Blanc, and Syrah, is estimated. Two different autoencoder architectures are examined: deep fully-connected (DAE) and deep convolutional autoencoders (DCAE), while the estimation of sugar content takes place using as input both from the encoded (latent) space and from the autoencoders’ output, i.e., the transformed standardized spectra. The use of multiple spectral pre-treatments is further examined to enhance the accuracy of prediction. Despite that DAE and DCAE showcase comparable similarity metrics, DCAE statistically outperforms DAE when using both the encoded space and the autoencoders’ output, attesting to the suitability of the convolutional autoencoder framework. On the other hand, there is no statistical significant difference when employing multiple input pre-treatments. The accuracy of estimation (mean RMSE 1.83 ∘Brix, R2 0.70, RPIQ 2.43) is comparable to other studies that directly work with standardized reflectance spectra in laboratory conditions.

Estimation of sugar content in sugar beet root based on UAV multi-sensor data

Sugar beet (Beta vulgaris L.) is the second largest sugar source crop in the world. Sugar content in its beetroot is an important quality index of sugar beet. Rapid and accurate estimation of sugar content in beetroot is helpful to high-throughput phenotype and genotype breeding. The purpose of the current study is to explore the potential of UAV-based multimodal remote sensing data in sugar content estimation. Multimodal data were collected by different UAV-platform carried with RGB, multi-spectral, thermal infrared, hyperspectral and LiDAR. Spectral, structure and thermal features of canopy were extracted from different sensor combinations to estimate sugar content during sugar accumulation period of beetroot by using Partial Least Squares Regression (PLSR), Bayesian Ridge Regression (BRR) and Support Vector Regression (SVR). The main results are as follows: (i) In estimating sugar content, published vegetation indices (PBI, NDVI, TCARI, etc.) calculated from hyperspectral as spectral features outperformed these of multispectral. Structure features calculated from LiDAR outperformed those from RGB. (ii) Eight newly developed vegetation indices presented better performance than published vegetation indices. Among them (R730-R734)/(R730 + R734) index using two bands and (R694-R714)/(R710-R714) using three bands presented the best performance. (iii) Multimodal data combination from different sensors improved estimation accuracy of sugar content than data from individual sensors. PLSR based multimodal data from LiDAR, hyperspectral, thermal infrared sensor presented the best accuracy with R2 = 0.64 and relative root mean square error (rRMSE) = 7.2 %. These results showed that UAV-based canopy features from multimodal data can be used to quickly and accurately obtain sugar content of beetroot. This study provides a basic reference for estimating bioactive substances in roots of root tuber crops based on multimodal canopy remote sensing data.

Design of an Integrated Near-Infrared Spectroscopy Module for Sugar Content Estimation of Apples.

An integrated near-infrared (NIR) spectroscopy prototype module for sugar content estimation of apples is presented. Since this is the first attempt to design an integrated NIR spectroscopy module, we followed the design process as follows. First, we estimated the sugar content of apples using a tungsten halogen light source and a 700 nm–1000 nm NIR spectrometer with a 10 nm wavelength resolution and a 16b analog-to-digital converter (ADC) resolution. Second, we determined the most effective wavelengths among 31 evenly distributed wavelengths while observing the correlation coefficient, R2, and then we reduced the ADC resolution 1b by 1b starting from 16b while also observing the R2. Lastly, we designed an integrated NIR spectroscopy module with the selected eight wavelengths and a 13 ADC resolution. The module implemented in a 0.18 μm 1P6M CMOS process occupies a die area of 0.84 mm2. By utilizing this module with eight off-chip light emitting diodes (LED) and one photo diode (PD), the measured R2 and the standard error of calibration (SEC) were 0.365 and 0.686 brix, respectively.

Development of a calibration model for near infrared spectroscopy using a convolutional neural network

Development of qualitative or quantitative models is essential to exploit the full potential of near infrared (NIR) spectroscopy. In tandem with one-dimensional convolutional neural network (1D-CNN), a data-driven model is developed using NIR spectroscopy to estimate organic contents. First, the 1D-CNN model is designed to capture the features of the NIR spectra by means of several convolutional and pooling operations. Then, the suitable hyper-parameters of 1D-CNN are obtained by using the grid search algorithm to achieve the optimal performance. Furthermore, the dropout operation is added into the 1D-CNN to suppress the overfitting problem by means of removing some neurons, and the probability distribution of throwing follows the Bernoulli distribution. The developed framework is validated by the application in the sugar content estimation of Huangshan Maofeng tea. The experimental results demonstrate that the key features of the NIR spectra are successfully extracted by the proposed strategy; thereby, a new effective scheme for analyzing NIR spectra is provided for food analysis.

Automated hyperspectral vegetation index derivation using a hyperparameter optimisation framework for high-throughput plant phenotyping.

Summary Hyperspectral vegetation indices (VIs) are widely deployed in agriculture remote sensing and plant phenotyping to estimate plant biophysical and biochemical traits. However, existing VIs consist mainly of simple two‐band indices that limit the net performance and often do not generalise well for traits other than those for which they were originally designed.We present an automated hyperspectral vegetation index (AutoVI) system for the rapid generation of novel two‐ to six‐band trait‐specific indices in a streamlined process covering model selection, optimisation and evaluation, driven by the tree parzen estimator algorithm. Its performance was tested in generating novel indices to estimate chlorophyll and sugar contents in wheat.Results showed that AutoVI can rapidly generate complex novel VIs (at least a four‐band index) that correlated strongly (R 2 > 0.8) with measured chlorophyll and sugar contents in wheat. Automated hyperspectral vegetation index‐derived indices were used as features in simple and stepwise multiple linear regressions for chlorophyll and sugar content estimation, and outperformed the results achieved with the existing 47 VIs and those provided using partial least squares regression.The AutoVI system can deliver novel trait‐specific VIs readily adoptable to high‐throughput plant phenotyping platforms and should appeal to plant scientists and breeders. A graphical user interface for the AutoVI is provided here.

Estimation of Sugar Content in Sugarcane (Saccharum spp.) Variety Lumpang 92-11 (LK 92-11) and Khon Kaen 3 (KK 3) by Near Infrared Spectroscopy

Estimation of Sugar Content in Sugarcane (Saccharum spp.) Variety Lumpang 92-11 (LK 92-11) and Khon Kaen 3 (KK 3) by Near Infrared Spectroscopy

How good are the models available for estimating sugar content in sugarcane?

Abstract While sugarcane growth models could assist farmers in harvesting fields as close as possible to peak maturity, few of them are available to the industry. Even in those that are available, either there is room for improvement in sugar content estimation, or they were not properly assessed as to how they would perform given weather variability. In this work, we show that when developed with a dataset comprised of typical weather patterns, the outputs of empirical models that have been recently developed are qualitatively analogous to those of a process-based model and have smaller errors. However, when the training data is not representative, the same doesn’t happen and they are not consistent with known responses from sugarcane and with the output of mechanistic models. We used data from three years of harvests of a sugarcane mill to develop and evaluate the performance of machine learning models, as well as to evaluate an empirical model recently developed and DSSAT/Canegro. All models’ performances were evaluated in each of the three years separately, as well as through sensitivity analysis, to observe the effects of unknown weather in the estimates obtained by the model. This evaluation suggests that while machine learning techniques applied to industry data may be a promising tool for decision-makers, by themselves they are not capable of capturing all the effects that influence sucrose accumulation in sugarcane stalks.

Effect of the Architecture of Fiber-Optic Probes Designed for Soluble Solid Content Prediction in Intact Sugar Beet Slices.

Sugar beet is the second biggest world contributor to sugar production and the only one grown in Europe. One of the main limitations for its competitiveness is the lack of effective tools for assessing sugar content in unprocessed sugar beet roots, especially in breeding programs. In this context, a dedicated near infrared (NIR) fiber-optic probe based approach is proposed. NIR technology is widely used for the estimation of sugar content in vegetable products, while optic fibers allow a wide choice of technical properties and configurations. The objective of this research was to study the best architecture through different technical choices for the estimation of sugar content in intact sugar beet roots. NIR spectral measurements were taken on unprocessed sugar beet samples using two types of geometries, single and multiple fiber-probes. Sugar content estimates were more accurate when using multiple fiber-probes (up to R2 = 0.93) due to a lesser disruption of light specular reflection. In turn, on this configuration, the best estimations were observed for the smallest distances between emitting and collecting fibers, reducing the proportion of multiply scattered light in the spectra. Error of prediction (RPD) values of 3.95, 3.27 and 3.09 were obtained for distances between emitting and collecting fibers of 0.6, 1.2 and 1.8 µm respectively. These high RPD values highlight the good predictions capacities of the multi-fiber probes. Finally, this study contributes to a better understanding of the effects of the technical properties of optical fiber-probes on the quality of spectral models. In addition, and beyond this specificity related to sugar beet, these findings could be extended to other turbid media for quantitative optical spectroscopy and eventually to validate considered fiber-optic probe design obtained in this experimental study.

An LED-based spectrally tuneable light source for visible and near-infrared spectroscopy analysis: A case study for sugar content estimation of citrus

Light source plays an important role in visible and near-infrared (Vis–NIR) spectroscopy detection systems. Traditionally, halogen tungsten lamps are used in most studies and applications. However, halogen tungsten lamps have two main shortcomings: generation of large amount of heat and limited operational lifetime. In this study, a light emitting diode (LED)-based spectrally tuneable light source in a broad Vis–NIR wavelength range (400–1070 nm) using an integrating sphere was designed and developed, as well as the control circuit to control the LEDs conveniently and easily for obtaining tuneable spectra. The Vis–NIR spectroscopy detection system equipped with this LED-based spectrally tuneable light source was applied for estimating sugar content of citrus. Based on stepwise multiple linear regression (SMLR) modelling in the spectral region of 500–900 nm, the calibration results using the LED light source (correlation coefficient ( r c ) = 0.78, root mean square error of calibration (RMSEC) = 0.74 Brix%) were better than those using the halogen tungsten lamp ( r c = 0.74, RMSEC = 0.80 Brix%), while the prediction result was a bit worse (root mean square error of prediction (RMSEP) = 1.09 and 0.95 Brix%, respectively). Generally, the performances of the two kinds of light sources for sugar content estimation of citrus samples were similar, but the energy consumption and heat generation of the LED light source were much lower. Besides, the LED light source could warm up to a stable status much faster than the halogen tungsten lamp. For further research, the method proposed in this study can be applied to online sugar content estimation of citrus and be expanded to other applications.

Estimation and Visualization of Soluble Sugar Content in Oilseed Rape Leaves Using Hyperspectral Imaging

Abstract. A novel technology for hyperspectral imaging was used to estimate the soluble sugar content of rape leaves. Rape leaves collected at four different growth stages (seedling stage, bolting stage, florescence stage, and pod stage) were analyzed. Sample regions in the hyperspectral images were extracted by removing the background, and spectral data of all pixels in the sample region were extracted and averaged as the spectrum of the sample. Eleven of 128 samples were defined as outliers. The remaining samples were split into a calibration set and a prediction set in a 3:1 ratio using two methods: considering the difference in growth stage (method 1) and not considering the growth stage (method 2). Eight and seven sensitive wavelengths were selected by a successive projections algorithm (SPA) for methods 1 and 2, respectively. Partial least squares (PLS) was applied to build calibration models using full spectra and sensitive wavelengths, and multiple linear regression (MLR) and back-propagation neural network (BPNN) models were built using selected wavelengths. The calibration models for method 1 performed better than the models for method 2. The BPNN for method 1 using sensitive wavelengths obtained the optimal prediction result, with a correlation coefficient of prediction (rp) of 0.885, root mean square error of prediction (RMSEP) of 2.010 mg g-1, and residual prediction deviation (RPD) of 2.177. The overall results indicated that hyperspectral imaging could be used for detection of soluble sugar content in rape leaves. In addition to building calibration models for soluble sugar content estimation, visualization of soluble sugar distribution in rape leaves was achieved by predicting the soluble sugar content of each pixel within the image using the optimal SPA-BPNN model.

Simple and rapid method for evaluating stickiness of cotton using thermogravimetric analysis

Thermogravimetric analysis (TGA) with nitrogen and oxygen as carrier gas is used for the analysis of cotton lint samples for evaluating their stickiness. The advantage of the low melting point of trehalulose, a commonly found sugar, in the presence of oxygen as carrier gas is used for the evaluation. The oxidation of sugar present in the cotton lint results in increased weight around the melting point, which is proportional to the sugar content. The decomposition of the sugar further results in weight loss. This method is compared with the sticky cotton thermodetector and viscosity method for the estimation of sugar content. Good agreement between the methods suggests the usefulness and simplicity of TGA for estimation of stickiness in cotton.

QUALITY ASSURANCE OF HARVESTED HORTICULTURAL PERISHABLES

An effective quality assurance (QA) system throughout the handling steps between harvest and retail display is essential to provide a consistently good-quality supply of fresh horticultural crops to the consumers and to protect the reputation of a given marketing label. QA starts with the selection of the genotype and its proper time to harvest for the best appearance, textural, flavor (taste and aroma), and nutritional (including phytonutrients) quality. Careful harvesting and handling are required to minimize physical injuries. Each postharvest handling step has the potential to either maintain or reduce quality and in a few cases (such as ripening of climacteric fruits) improve eating quality. The availability of low-cost microcomputers and solid-state imaging systems have resulted in increased use of computer-aided video inspection to sort many products into two or more quality grades before marketing. Objective and nondestructive methods of differentiating horticultural perishables on the basis of their flavor and nutritional quality are being tested and will become excellent QA tools as they become more reliable and efficient. Safety assurance can be part of QA and its focus is on minimizing chemical and microbial contamination during production, harvesting, and postharvest handling of intact and fresh-cut fruits and vegetables. Future research and development efforts should focus on developing better methods of monitoring quality and safety attributes of fresh produce as part of a QA system. 1. Quality attributes Quality of fresh produce includes appearance (size, shape, color, gloss, and freedom from defects and decay), texture (firmness, crispness, juiciness, mealiness, and toughness, depending on the commodity), flavor (sweetness, sourness (acidity), astringency, aroma, and off-flavors), and nutritive value (vitamins, minerals, dietary fiber, phytonutrients). The relative importance of each quality component depends on the commodity and the individual’s interest (Kader, 1992). Most postharvest researchers, producers, and handlers are product-oriented in that quality is described by specific attributes of the product itself, such as sugar content, color, or firmness. In contrast, consumers, marketers, and economists are more likely to be consumer-oriented in that quality is described by consumer wants and needs (Shewfelt, 1999). Although consumers purchase fresh produce based on appearance and textural quality, their repeat purchases depend upon their satisfaction with flavor (taste and aroma). They are also interested in the health-promoting attributes and nutritional quality of fresh fruits and vegetables (Kader, 1988). Several attempts have been made to develop portable instruments with sensors that detect volatile production by fruits as a way to detect maturity and quality. Other strategies include the removal of a very small amount of fruit tissue and measurement of total sugars or soluble solids content. Near-infrared detectors have great potential for nondestructive estimation of sugar content in fruits (Abbott, 1999). Until such methods become widely available, we will continue to depend on destructive techniques, such as soluble solids determination by a refractometer and titratable acidity measurement by titration, to evaluate flavor quality of fruits. Table 1 summarizes the proposed minimum

Methodology of sugar‐beet analysis

AbstractThe various estimates of different methods of sampling beet for sugar content and quality assessment parameters are determined. Alternative procedures to clarified juice purity measurements for quality assessment are the estimation of the major individual impurity components on either clarified juice or on the extract used for sugar content estimation.