Prediction Of Moisture Content Research Articles

Rapid and non-destructive prediction of moisture content on intact gayo coffee beans using near infrared spectroscopy

Abstract Presented work explores the potential of Near-Infrared Spectroscopy (NIRS) as a rapid, non-destructive analytical method for predicting moisture content in intact Gayo coffee beans. The moisture content is an essential parameter affecting the quality, processing, and shelf life of coffee beans. While conventional moisture determination techniques involve invasive procedures and considerable time, NIRS emanates as an innovative technique offering non-invasive, swift analysis. Using a robust representative selection of Gayo coffee bean samples, we acquired numerous spectra and employed multivariate analysis to construct a calibration model correlating the spectral data with reference moisture values. The initial results exhibit a high correlation coefficient (r) of 0.93 and ratio prediction to deviation (RPD) index of 3, suggesting that the NIRS technique can effectively predict the moisture content within the beans. This research underpins the potential usage of NIRS which, if validated through further testing, could transform quality control operations in the coffee industry by offering a real-time, non-destructive approach for moisture content determination.

Rapid assessment of vanilla (Vanilla planifolia) quality parameters using portable near-infrared spectroscopy combined with random forest

The determination of moisture and vanillin content significantly influences the quality of vanilla. Currently, conventional chemical methods employed for assessing these parameters are time-consuming, involve complex sample preparation, are expensive, and environmentally unfriendly due to the use of chemical solutions. Portable Near-Infrared (NIR) spectroscopy emerges as a promising alternative, characterized by smaller dimensions and lower costs. This study investigates the performance of two portable NIR spectrometers with distinct wavelengths at 740–1070 nm and 1350–2550 nm, in conjunction with Random Forest (RF) and Partial Least Square (PLS) regression, and preprocessing techniques including min-max normalization, 1st derivative, standard normal variate (SNV), multiplicative scatter correction (MSC), 1st derivative + SNV, and 1st derivative + MSC for predicting moisture and vanillin content. At the wavelength range of 1350–2550 nm, RF coupled with 1st derivative produced the best moisture content prediction model with an R2 of 0.971, and RF paired with 1st derivative+SNV yielded the best vanillin content prediction with an R2 of 0.983. This work highlights that the integration of portable NIR and RF allows for rapid and non-destructive detection of moisture and vanillin content. This methodology provides a novel regression method for predicting vanilla qualities.

Prediction Distribution Model of Moisture Content in Laminated Wood Components.

Shrinkage cracks are some of the most common defects in timber structures obtained from woods with an uneven distribution of moisture content and are subject to external dynamic environmental changes. To accurately predict the changes in the moisture content of wood components at any time and position, this study first applied the principles of food drying and established a moisture field model for laminated wood based on the analogy between heat and humidity transfer. A model for predicting the moisture content of wood that considers time and spatial distribution was then proposed. Second, by collecting relevant experimental data and establishing a finite element analysis model, three moisture absorption conditions (0-9.95%, 0-13.65%, and 0-17.91%) and four desorption conditions (34-5.5%, 28-8.3%, 31-11.8%, and 25.5-15.9%) were analyzed. In the moisture absorption comparison, the time needed to reach 95% equilibrium moisture content was 2.43 days, 4.07 days, and 6.32 days. The rate at which the internal components reached equilibrium moisture content exceeded 10 days. The temporal and spatial distribution of wood moisture content revealed the correctness of the proposed wood moisture field model. Finally, the moisture content prediction model was applied in the order of characteristic equation solutions, moisture content gradient difference, and laminated wood size. The results revealed that the established humidity field model can predict the wood moisture content and how it changes over time and in space. Notably, 1-2 orders for the solution of the characteristic equation are recommended when applying the prediction model. The greater the difference in moisture content, the faster the equilibrium moisture content is reached. The moisture content varies greatly based on the component size and position. Notably, the influence of moisture gradient and wood size on the average wood moisture content cannot be ignored.

Feature Variable Selection Based on VIS-NIR Spectra and Soil Moisture Content Prediction Model Construction

The hydrological cycle, surface energy balance, and the management of water resources are all significantly impacted by soil moisture. Because it governs the physical processes of evapotranspiration and rainfall penetration, surface soil moisture is a significant climatic variable. In this work, visible-near infrared (VIS-NIR) bands were used to compare and analyze the spectra of loess samples with varying moisture concentrations. The investigation looked at how changes in the soil moisture content impacted the response of the soil spectra. The researchers used a genetic algorithm (GA), interval combination optimization (ICO), and competitive adaptive reweighted sampling (CARS) to filter feature variables from full-band spectral data. To forecast the moisture content of loess on the soil surface, models like partial least squares regression (PLSR), support vector machine (SVM), and random forest (RF) were created. The findings indicate that: (1) the most reliable spectrum preprocessing technique is the first derivative (FD), which can significantly enhance the model’s prediction power and spectral characteristic information. (2) The feature band selection method’s prediction effect of soil moisture content is typically superior to that of full-spectrum data. (3) The random forest (RF) prediction model for soil moisture content with the highest accuracy was built by combining the genetic algorithm (GA) with the FD preprocessed spectra. The results may provide a new understanding on how to use VIS-NIR to measure soil moisture content.

Electrical Properties for Non-destructive Determination of Free Fatty Acid and Moisture Content in Oil Palm Fruit

FFA content is one of the essential qualities of oil palm fruit. FFA content exceeding 5% is considered unsuitable for human consumption. Commonly, FFA content is determined by chemical methods in the laboratory, but it is destructive, time-consuming, and costly. Several non-destructive methods have been investigated, but a maturity prediction approach has been primarily used with no direct relation to FFA content. Thus, there is a pressing need for a non-destructive framework to assess the FFA levels in the oil palm fruit directly. An attempt has been explored using a non-destructive palm fruit quality assessment that relied on electrical properties (impedance, admittance, resistance, and capacitance) in the frequency range from 50 Hz to 5 MHz was investigated to predict FFA and moisture content directly. Two statistical analyses were employed: stepwise multiple linear regressions (MLR) and artificial neural networks (ANN) to calibrate and validate electrical properties with FFA and moisture content. The best-performing models ANN showcased significant results: r= 0.96, R2=0.92, SEC at 0.86%, SEP at 0.97%, CV at 19.45%, consistency at 88.54, and RPD at 3.43 for FFA prediction, and r= 0.99, R2=0.98, SEC at 3.09 %, SEP at 3.46 %, CV at 5.44 %, consistency at 89.08 and RPD at 7.02 for predicting moisture content. In modeling oil palm quality determination, applying the ANN method significantly improved model performances, demonstrating its efficacy in predicting non-destructively both FFA levels based on admittance and moisture content based on impedance.

Nondestructive Detection of Sunflower Seed Vigor and Moisture Content Based on Hyperspectral Imaging and Chemometrics.

Sunflower is an important crop, and the vitality and moisture content of sunflower seeds have an important influence on the sunflower's planting and yield. By employing hyperspectral technology, the spectral characteristics of sunflower seeds within the wavelength range of 384-1034 nm were carefully analyzed with the aim of achieving effective prediction of seed vitality and moisture content. Firstly, the original hyperspectral data were subjected to preprocessing techniques such as Savitzky-Golay smoothing, standard normal variable correction (SNV), and multiplicative scatter correction (MSC) to effectively reduce noise interference, ensuring the accuracy and reliability of the data. Subsequently, principal component analysis (PCA), extreme gradient boosting (XGBoost), and stacked autoencoders (SAE) were utilized to extract key feature bands, enhancing the interpretability and predictive performance of the data. During the modeling phase, random forests (RFs) and LightGBM algorithms were separately employed to construct classification models for seed vitality and prediction models for moisture content. The experimental results demonstrated that the SG-SAE-LightGBM model exhibited outstanding performance in the classification task of sunflower seed vitality, achieving an accuracy rate of 98.65%. Meanwhile, the SNV-XGBoost-LightGBM model showed remarkable achievement in moisture content prediction, with a coefficient of determination (R2) of 0.9715 and root mean square error (RMSE) of 0.8349. In conclusion, this study confirms that the fusion of hyperspectral technology and multivariate data analysis algorithms enables the accurate and rapid assessment of sunflower seed vitality and moisture content, providing robust tools and theoretical support for seed quality evaluation and agricultural production practices. Furthermore, this research not only expands the application of hyperspectral technology in unraveling the intrinsic vitality characteristics of sunflower seeds but also possesses significant theoretical and practical value.

Electro-Optics Properties of Intact Cocoa Beans based on Near Infrared Technology

This study encapsulates the efficient prediction of moisture content in cocoa beans through Near Infrared Spectroscopy (NIRS) and Partial Least Squares (PLS) regression, showcasing a strong model fit with a high R square value of 0.92 and low Root Mean Square Error (RMSE) of 0.36% in calibration; these values underscore the model's accurate estimation of moisture levels. In the realm of electro-optics properties, this success highlights NIRS's capability in assessing key attributes like moisture content in cocoa beans based on their unique spectral signatures, emphasizing the technology's role in quality control for chocolate production. Furthermore, the precise predictions align with the broader objective of leveraging NIRS to evaluate and optimize the electro- optics properties of cocoa beans, fostering informed decision-making for enhanced processing and quality assurance in the cocoa industry.

Visualisation of moisture content distribution maps and classification of freshness level of loquats

Moisture content (MC) and freshness undergo evident changes during the storage of loquat fruits and thus are important indices of loquat fruit quality. Conventional methods for assessing MC and freshness are typically destructive and time-consuming, and cannot provide distribution maps of MC in the whole loquats. In this study, the use of hyperspectral imaging (HSI) was investigated for rapid and non-destructive prediction of MC in loquats, and for the visualisation of their MC distribution maps. Furthermore, freshness level discrimination models for loquats at different storage times were established using partial least squares discriminant analysis (PLS-DA), multinomial logistic regression (MLogR), and back-propagation neural network (BPNN) classification models. MC was well-predicted, with the best residual predictive deviation (RPD) of 2.40. Using the best prediction model, the distribution maps of MC in loquats were visualised. Additionally, the competitive adaptive reweighted sampling (CARS)-BPNN model obtained superior discrimination performance, with 95.56 % and 93.33 % accuracy for the calibration and prediction sets. Our results show that HSI is a promising fast and non-destructive method for determining MC and freshness of loquats.

Enhancing precision of root-zone soil moisture content prediction in a kiwifruit orchard using UAV multi-spectral image features and ensemble learning

Accurate and real-time monitoring of soil moisture content (SMC) is of utmost importance for effective field irrigation and maximizing crop water productivity. However, a comprehensive investigation into the inversion study for determining suitable combinations of unmanned aerial vehicle (UAV) image features and enhancing the precision of SMC model prediction has yet to be fully validated within a kiwifruit orchard setting. This study addresses this gap by employing a pre-processing method and an optimal band combination algorithm to assess the impact of various combinations of kiwifruit canopy reflectance and fraction vegetation coverage (FVC) features on the sensitivity of root-zone SMC. Furthermore, an optimal ensemble learning (EL) framework was developed to monitor SMC at various root-zone depths (0–10 cm [SMC10], 0–20 cm [SMC20], 0–30 cm [SMC30], 0–40 cm [SMC40], 0–50 cm [SMC50], 0–60 cm [SMC60]). The key findings of this research highlight the successful derivation of 10 wavebands and FVC features, exhibiting a strong correlation with SMC at different root depths. The gradient boosting (GBDT) model demonstrated the exceptional accuracy in estimating SMC10, with an impressive R2 value of 0.963 ± 0.030 and low RMSE values of 0.238 ± 0.111. Similarly, the eXtreme Gradient Boosting (XGBoost) model outperformed in estimating SMC20 to SMC60, with R2 and RMSE values of 0.963 ± 0.024 and 0.117 ± 0.053, respectively. Additionally, the utilization of the optimal EL model allows for digital mapping of SMC at different depths across fruit growth stages, showcasing superior adaptability for SMC30 to SMC60 (with R2 and RMSE of 0.782 ± 0.090 and 0.037 ± 0.011) compared to SMC10 and SMC20 (with R2 and RMSE of 0.765 ± 0.097 and 0.056 ± 0.024). These results underscore the potential of the EL estimation framework in characterizing the spatial distribution of root-zone SMC at the individual kiwifruit plant level.

Prediction of moisture content for a single maize kernel based on viscoelastic properties.

The rapid and accurate detection of moisture content is important to ensure maize quality. However, existing technologies for rapidly detecting moisture content often suffer from the use of costly equipment, stringent environmental requirements, or limited accuracy. This study proposes a simple and effective method for detecting the moisture content of single maize kernels based on viscoelastic properties. Two types of viscoelastic experiments were conducted involving three different parameters: relaxation tests (initial loads: 60, 80, 100 N) and frequency-sweep tests (frequencies: 0.6, 0.8, 1 Hz). These experiments generated corresponding force-time graphs and viscoelastic parameters were extracted based on the four-element Maxwell model. Then, viscoelastic parameters and data of force-time graphs were employed as input variables to explore the relationships with moisture content separately. The impact of different preprocessing methods and featuretime variables on model accuracy was explored based on force-time graphs. The results indicate that models utilizing the force-time data were more accurate than those utilizing viscoelastic parameters. The best model was established by partial least squares regression based on S-G smoothing data from relaxation tests conducted with initial force of 100 N. The correlation coefficient and the root mean square error of the calibration set were 0.954 and 0.021, respectively. The corresponding values of the prediction set were 0.905 and 0.029, respectively. This study confirms the potential for accurate and fast detection of moisture content in single maize kernels using viscoelastic properties, which provides a novel approach for the detection of various components in cereals. © 2024 Society of Chemical Industry.

A Real-Time Prediction Approach to Deep Soil Moisture Combining GNSS-R Data and a Water Movement Model in Unsaturated Soil

Deep soil moisture data have wide applications in fields such as engineering construction and agricultural production. Therefore, achieving the real-time monitoring of deep soil moisture is of significant importance. Current soil monitoring methods face challenges in conducting the large-scale, real-time monitoring of deep soil moisture. This paper innovatively proposes a real-time prediction approach to deep soil moisture combining GNSS-R data and a water movement model in unsaturated soil. This approach, built upon surface soil moisture data retrieved from GNSS-R signal inversion, integrates soil–water characteristics and soil moisture values at a depth of 1 m. By employing a deep soil moisture content prediction model, it provides predictions of soil moisture at depths from 0 to 1 m, thus realizing the large-scale, real-time dynamic monitoring of deep soil moisture. The proposed approach was validated in a study area in Goodwell, Texas County, Oklahoma, USA. Predicted values of soil moisture at a randomly selected location in the study area at depths of 0.1 m, 0.2 m, 0.5 m, and 1 m were compared with ground truth values for the period from 25 October to 19 November 2023. The results indicated that the relative error (δ) was controlled within the range of ±14%. The mean square error (MSE) ranged from 2.90 × 10−5 to 1.88 × 10−4, and the coefficient of determination (R2) ranged from 82.45% to 89.88%, indicating an overall high level of fitting between the predicted values and ground truth data. This validates the feasibility of the proposed approach, which has the potential to play a crucial role in agricultural production, geological disaster management, engineering construction, and heritage site preservation.

Stem moisture content prediction model for Larix olgensis based on beta regression.

To investigate the longitudinal variation patterns of sapwood, heartwood, bark and stem moisture content along the trunk of artificial Larix olgensis, we constructed mixed effect models of moisture content based on beta regression by combining the effects of sampling plot and sample trees. We used two sampling schemes to calibrate the model, without limiting the relative height (Scheme Ⅰ) and with a limiting height of less than 2 m (Scheme II). The results showed that sapwood and stem moisture content increased gradually along the trunk, heartwood moisture content decreased slightly and then increased along the trunk, and bark moisture content increased along the trunk and then levelled off before increasing. Relative height, height to crown base, stand area at breast height per hectare, age, and stand dominant height were main factors driving moisture content of L. olgensis. Scheme Ⅰ showed the stable prediction accuracy when randomly sampling moisture content measurements from 2-3 discs to calibrate the model, with the mean absolute percentage error (MAPE) of up to 7.2% for stem moisture content (randomly selected 2 discs), and the MAPE of up to 7.4%, 10.5% and 10.5% for sapwood, heartwood and bark moisture content (randomly selected 3 discs), respectively. Scheme Ⅱ was appropriate when sampling moisture content measurements from discs of 1.3 and 2 m height and the MAPE of sapwood, heartwood, bark and stem moisture content reached 7.8%, 11.0%, 10.4% and 7.1%, respectively. The prediction accuracies of all mixed effect beta regression models were better than the base model. The two-level mixed effect beta regression models, considering both plot effect and tree effect, would be suitable for predicting moisture content of each part of L. olgensis well.

Drone-Based Multispectral Remote Sensing Inversion for Typical Crop Soil Moisture under Dry Farming Conditions

Drone multispectral technology enables the real-time monitoring and analysis of soil moisture across vast agricultural lands. overcoming the time-consuming, labor-intensive, and spatial discontinuity constraints of traditional methods. This study establishes a rapid inversion model for deep soil moisture (0–200 cm) in dryland agriculture using data from drone-based multispectral remote sensing. Maize, millet, sorghum, and potatoes were selected for this study, with multispectral data, canopy leaf, and soil moisture content at various depths collected every 3 to 6 days. Vegetation indices highly correlated with crop canopy leaf moisture content (p < 0.01) and were identified using Pearson correlation analysis, leading to the development of linear and nonlinear regression models for predicting moisture content in canopy leaves and soil. The results show a significant linear correlation between the predicted and actual canopy leaf moisture levels for the four crops, according to the chosen vegetation indices. The use of canopy leaf moisture content to predict surface soil moisture (0–20 cm) demonstrated enhanced accuracy. The models designed for the top 20 cm of soil moisture successfully estimated deep soil moisture levels (up to 200 cm) for all four crops. The 20 cm range soil moisture model showed improvements over the 10 cm range model, with increases in Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Coefficient of Determination (R2), and Nash–Sutcliffe Efficiency Coefficient (NSE) by 0.4, 0.8, 0.73, and 0.34, respectively, in the corn area; 0.28, 0.69, 0.48, and 0.25 in the millet area; 0.4, 0.48, 0.22, and 0.52 in the sorghum area; and 1.14, 0.81, 0.73, and 0.56 in the potato area, all with an average Relative Error (RE) of less than 10% across the crops. Using drone-based multispectral technology, this study forecasts leaf water content via vegetation index analysis, facilitating swift and effective soil moisture inversion. This research introduces a novel method for monitoring and managing agricultural water resources, providing a scientific basis for precision farming and moisture variation monitoring in dryland areas.

Comparison of hyperspectral imaging and spectrometers for prediction of cheeses composition

Artisanal cheeses are part of the heritage and identity of different countries or regions. In this work, we investigated the spectral variability of a wide range of traditional Brazilian cheeses and compared the performance of different spectrometers to discriminate cheese types and predict compositional parameters. Spectra in the visible (vis) and near infrared (NIR) region were collected, using imaging (vis/NIR-HSI and NIR-HSI) and conventional (NIRS) spectrometers, and it was determined the chemical composition of seven types of cheeses produced in Brazil. Principal component analysis (PCA) showed that spectral variability in the vis/NIR spectrum is related to differences in color (yellowness index) and fat content, while in NIR there is a greater influence of productive steps and fat content. Partial least squares discriminant analysis (PLSDA) models based on spectral information showed greater accuracy than the model based on chemical composition to discriminate types of traditional Brazilian cheeses. Partial least squares (PLS) regression models based on vis/NIR-HSI, NIRS, NIR-HSI data and HSI spectroscopic data fusion (vis/NIR + NIR) demonstrated excellent performance to predict moisture content (RPD > 2.5), good ability to predict fat content (2.0 < RPD < 2.5) and can be used to discriminate between high and low protein values (∼1.5 < RPD < 2.0). The results obtained for imaging and conventional equipment are comparable and sufficiently accurate, so that both can be adapted to predict the chemical composition of the Brazilian traditional cheeses used in this study according to the needs of the industry.

Rapid and Non-Destructive Prediction of Moisture Content in Maize Seeds Using Hyperspectral Imaging.

The moisture content of corn seeds is a crucial indicator for evaluating seed quality and is also a fundamental aspect of grain testing. In this experiment, 80 corn samples of various varieties were selected and their moisture content was determined using the direct drying method. The hyperspectral imaging system was employed to capture the spectral images of corn seeds within the wavelength range of 1100-2498 nm. By utilizing seven preprocessing techniques, including moving average, S-G smoothing, baseline, normalization, SNV, MSC, and detrending, we preprocessed the spectral data and then established a PLSR model for comparison. The results show that the model established using the normalization preprocessing method has the best prediction performance. To remove spectral redundancy and simplify the prediction model, we utilized SPA, CASR, and UVE algorithms to extract feature wavelengths. Based on three algorithms (PLSR, PCR, and SVM), we constructed 12 predictive models. Upon evaluating these models, it was determined that the normalization-SPA-PLSR algorithm produced the most accurate prediction. This model boasts high RC2 and RP2 values of 0.9917 and 0.9914, respectively, along with low RMSEP and RMSECV values of 0.0343 and 0.0257, respectively, indicating its exceptional stability and predictive capabilities. This suggests that the model can precisely estimate the moisture content of maize seeds. The results showed that hyperspectral imaging technology provides technical support for rapid and non-destructive prediction of corn seed moisture content and new methods in seed quality evaluation.

Control of multi-energy drying system: Optimal weighted combination prediction of moisture content and fuzzy compensation of wind speed

In order to monitor the moisture content accurately and improve the drying uniformity of the same batch of materials, an online moisture monitoring approach based on optimal weighted combination model (OWCM) was developed, and a fuzzy control strategy of wind speed compensation was established for multi-field coexistence. The Human Machine Interface (HMI) and remote monitoring modules are designed, which can automatically obtain, view and store environmental parameters on site and mobile devices. The system was loaded into a kelp drying equipment, and moisture content prediction and drying uniformity verification tests were conducted respectively. The results showed that Root Mean Square Error (RMSE) and Mean Absolute Error (MAE) of the OWCM are 0.022 and 0.019, the prediction accuracy was better than that of single model and average weighted combined model (AWCM). The drying time difference between the front and back of the same batch of kelp was shortened from 1 ∼ 1.5 h to 0 ∼ 0.5 h. This study provides theoretical and technical support for the synergistic utilization of multiple energies and the research and development of aquatic products processing equipment.

Construction of a sustainable model to predict the moisture content of porang powder (Amorphophallus oncophyllus) based on pointed-scan visible near-infrared spectroscopy

Abstract The moisture content of porang powder (PP) is an inherent quality parameter. Therefore, several analytical methods, such as oven drying and Karl–Fischer titration, were applied to determine the content. However, these techniques are noted to have various disadvantages, such as being time-consuming, requiring sample preparation, being labor-intensive, and producing chemical waste. This study aims to investigate the potential of visible near-infrared (Vis-NIR) spectroscopy as a nondestructive and sustainable analytical technology to predict moisture content in PP. In this study, we developed a traditional machine learning algorithm, a partial least squares regression (PLSR), in tandem with two spectral bands, which are Vis-NIR (400–1,000 nm) and NIR (954–1,700 nm). To upgrade the performance of PLSR, we applied seven preprocessing techniques: mean normalization, maximum normalization, range normalization, multiplicative scatter correction, standard normal variate (SNV), and Savitzky–Golay first and second derivatives. We found that PLSR using NIR spectral bands was more effective; the preprocessed mean normalization exhibited the best results with a coefficient of determination ( R p 2 ) \left({R}_{p}^{2}) of 0.96 and a standard error prediction (SEP) of 0.56 using five latent variables. Furthermore, we also extracted 39 optimum wavelengths using variable importance in projection and achieved better performance ( R p 2 {R}_{p}^{2} = 0.95, SEP = 0.56%wb, and 5 LVs) via SNV preprocessed NIR spectra.

Thermo-Hydric Study of Wood-Based Materials under Thermal Comfort Conditions.

This paper tackles the issue of moisture variation in wood-based materials, explicitly focusing on melamine-coated particleboard (hereafter referred to as melamine) and medium-density fiberboard (MDF) used in the third phase of wood industry transformation. The approach involves a comprehensive strategy for predicting moisture content variation, incorporating numerical simulation, experimental testing, and the application of artificial neural network (ANN) technology to enhance accuracy in furniture manufacturing. The developed ANN models are tailored to predict moisture content changes under specific thermal comfort conditions. Remarkably, these models demonstrate high precision, with an average error margin of only 1.40% for 8% moisture content (MC) and 2.85% for 12% MC in melamine, as well as 1.42% for 8% MC and 2.25% for 12% MC in MDF. These levels of precision surpass traditional models, emphasizing this study's novelty and practical relevance to the industrial context. The findings indicate that ANN models adapt to diverse environmental conditions, presenting a robust tool for optimizing moisture management in wood-based materials. This research contributes valuable insights for improving the reliability and efficiency of moisture content predictions in the wood industry.

Non-Destructive Prediction of Moisture and Fat Content in Cocoa Beans Using Near-Infrared Spectroscopy and Multivariate Regression Models

Non-Destructive Prediction of Moisture and Fat Content in Cocoa Beans Using Near-Infrared Spectroscopy and Multivariate Regression Models

Prediction and visualization of moisture content in Tencha drying processes by computer vision and deep learning.

It is important to monitor and control the moisture content throughout the Tencha drying processing procedure so that its quality is ensured. Workers often rely on their senses to perceive the moisture content, leading to relative subjectivity and low reproducibility. Traditional drying methods, which are used for measuring moisture content, are destructive to samples. This research was conducted using computer vision combined with deep learning to detect moisture content during the Tencha drying process. Different color space components of Tencha drying sample images were first extracted by computer vision. The color components were preprocessed using MinMax and Z score. Subsequently, one-dimensional convolutional neural networks (1D-CNN), partial least squares, and backpropagation artificial neural networks models were built and compared. The 1D-CNN model and Z scorepreprocessing achieved superior predictive accuracy, with correlation coefficient of prediction (Rp) = 0.9548 for moisture content. The migration of moisture content during the Tencha drying process was eventually visualized by mapping its spatial and temporal distributions. The results indicated that computer vision combined with 1D-CNN was feasible for moisture prediction during the Tencha drying process. This study provides technical support for the industrial and intelligent production of Tencha. © 2024 Society of Chemical Industry.