Real-time moisture monitoring of edible coated apple chips during hot air drying using miniature NIR spectroscopy and chemometrics

Optimizing feature selection with gradient boosting machines in PLS regression for predicting moisture and protein in multi-country corn kernels via NIR spectroscopy

Differences in moisture and protein content impact both nutritional value and processing efficiency of corn kernels. Near-infrared (NIR) spectroscopy can be used to estimate kernel composition, but models trained on a few environments may underestimate error rates and bias. We assembled corn samples from diverse international environments and used NIR with chemometrics and partial least squares regression (PLSR) to determine moisture and protein. The potential of five feature selection methods to improve prediction accuracy was assessed by extracting sensitive wavelengths. Gradient boosting machines (GBMs), particularly CatBoost and LightGBM, were found to effectively select crucial wavelengths for moisture (1409, 1900, 1908, 1932, 1953, 2174 nm) and protein (887, 1212, 1705, 1891, 2097, 2456 nm). SHAP plots highlighted significant wavelength contributions to model prediction. These results illustrate GBMs' effectiveness in feature engineering for agricultural and food sector applications, including developing multi-country global calibration models for moisture and protein in corn kernels.

Non-thermal ultrasonic contact drying of pea protein isolate suspensions: Effects on physicochemical and functional properties

Pea protein isolate (PPI) is a popular plant-based ingredient, typically produced through alkaline-isoelectric precipitation and thermal drying. However, high temperatures and long drying times encountered in thermal drying can denature PPI and cause loss of functionality. This study investigated the use of an innovative ultrasonic dryer (US-D) at 30 °C for drying PPI suspensions, compared to conventional hot air drying (HA-D) at 60 °C. US-D led to an increase in the drying rate and correspondingly reduced the drying time by 55 %, when compared to HA-D. The average effective moisture diffusivity in the US-D process was 325 % higher than that in the HA-D process. The resulting PPI exhibited higher solubility, emulsification, and foaming properties than HA-D PPI, with a unique surface morphology and higher surface area. This study demonstrated that drying with acoustic energy is a promising approach for producing dried plant protein ingredients with improved functional properties, reduced processing time, and increased production efficiency.

Monitoring chlorophyll changes during Tencha processing using portable near-infrared spectroscopy

Monitoring chlorophyll during Tencha (the raw ingredient for matcha) processing is critical for determining the matcha's color and quality. The purpose of this study is to explore the mechanism of chlorophyll changes during Tencha processing and evaluate the viability of predicting its content by a portable near-infrared (NIR) spectrometer. The Tencha samples' spectral data were first preprocessed using various preprocessing techniques. Subsequently, iteratively variable subset optimization (IVSO), bootstrapping soft shrinkage (BOSS), and competitive adaptive reweighted sampling (CARS) were used to optimize and build partial least square (PLS) models. The CARS-PLS models achieved the best predictive accuracy, with correlation coefficients of prediction (R_p) = 0.9204 for chlorophyll a, R_p = 0.9282 for chlorophyll b, and R_p = 0.9385 for total chlorophyll. These findings suggest that NIR spectroscopy could be used as a surrogate for immediate quantification and monitoring of chlorophyll during Tencha processing.

The Application of Hyperspectral Imaging Technologies for the Prediction and Measurement of the Moisture Content of Various Agricultural Crops during the Drying Process

Drying is one of the common procedures in the food processing steps. The moisture content (MC) is also of crucial significance in the evaluation of the drying technique and quality of the final product. However, conventional MC evaluation methods suffer from several drawbacks, such as long processing time, destruction of the sample and the inability to determine the moisture of single grain samples. In this regard, the technology and knowledge of hyperspectral imaging (HSI) were addressed first. Then, the reports on the use of this technology as a rapid, non-destructive, and precise method were explored for the prediction and detection of the MC of crops during their drying process. After spectrometry, researchers have employed various pre-processing and merging data techniques to decrease and eliminate spectral noise. Then, diverse methods such as linear and multiple regressions and machine learning were used to model and predict the MC. Finally, the best wavelength capable of precise estimation of the MC was reported. Investigation of the previous studies revealed that HSI technology could be employed as a valuable technique to precisely control the drying process. Smart dryers are expected to be commercialised and industrialised soon by the development of portable systems capable of an online MC measurement.

Characterizing Spray-Dried Powders through NIR Spectroscopy: Effect of Two Preparation Strategies for Calibration Samples and Comparison of Two Types of NIR Spectrometers

Emerging portable near infrared (NIR) spectroscopic approaches coupled with data analysis and chemometric techniques provide opportunities for the rapid characterization of spray-dried products and process optimization. This study aimed to enhance the understanding of applying NIR spectroscopy in spray-dried samples by comparing two sample preparation strategies and two spectrometers. Two sets of whey protein-maltodextrin matrixes, one with a protein content gradient and one with a consistent protein content, were spray-dried, and the effect of the two preparation strategies on NIR calibration model development was studied. Secondly, a portable NIR spectrometer (PEAK) was compared with a benchtop NIR spectrometer (CARY) for the moisture analysis of prepared samples. When validating models with the samples with focused protein contents, the best PLS protein models established from the two sample sets had similar performances. When comparing two spectrometers, although CARY outperformed PEAK, PEAK still demonstrated reliable performance for moisture analysis, indicating that it is capable as an inline sensor.

Review of quantitative and qualitative methods for monitoring photopolymerization reactions

Authomatic in-situ monitoring and characterization of photopolymerization.

Factors affecting the biomass pellet using industrial eucalyptus bark residue

Eucalyptus is utilized in the timber and paper industries. The eucalyptus bark must be peeled off during the production process, which results in a large amount of biomass residue. The objectives of this research were (i) to study the physical properties of eucalyptus bark, (ii) to investigate the crushing process using a hammer mill, and (iii) to examine the pelletizing factors of biofuel from eucalyptus bark residue using a pellet machine. Eucalyptus bark was crushed to reduce particle size and then sieved through different screen sizes (3, 4, and 5 mm) at a drum speed of 1200 rpm. The resulting eucalyptus powder was used to study the pelletizing factors of biofuel at various levels of moisture content: 17.69, 20.21, 24.27, and 26.74% w.b. and various pelletizing speeds of 250, 275, and 300 rpm. It was found that the eucalyptus powder could be pelletized at a speed of 275 rpm. Pellets with screen sizes of 3 and 4 mm could be pelletized at a moisture content of 17.69% w.b., while a screen size of 5 mm could be sued to pelletize at a moisture content of 20.21% w.b. The specific energy consumption from the particle size reduction process to the pelletizing process ranged from 667.92 to 854.64 kJ/kg. The results of bulk density, durability, and fines were 603.20-645.73 kg/m3, 96.34-96.88%, and 1.83-2.02%, respectively. The heating value was 16.19 MJ/kg. The energy value was calculated by using a eucalyptus pellet as boiler fuel (at a boiler efficiency of 38%). Eucalyptus pellets have the potential to produce energy worth 644 million THB/year or 20.6 million USD/year.

Application of NIR spectroscopy and multivariate analysis for Non-destructive evaluation of apple moisture content during ultrasonic drying

Direct-contact ultrasonic drying is a novel approach to dehydrate fruits and vegetables to reduce microbial growth and post-harvest loss while preserving nutrients and the quality of the final product. Moisture content is a critical component for food behavior during drying, and its accurate evaluation in real-time is essential for food quality control. This study conveys the potential implementation of portable near-infrared spectroscopy (NIRS) combined with multivariate analysis for real-time assessment of moisture content in apple slices during direct-contact ultrasonic drying. Partial least squares regression (PLSR) and Gaussian process regression (GPR) models were developed, and their performances for different pre-treatments methods and data partitioning algorithms were evaluated with both internal cross-validation and an external dataset. Three wavelengths were selected by SPA (1359, 1517, and 1594 nm) which were then used to introduce a closed-form equation for moisture content prediction with R²_p = 0.99 and RMSEP = 3.32%. The results revealed that portable NIRS combined with multivariate analysis is quite promising for monitoring and evaluating the moisture content during ultrasonic drying.

Identification of informative spectral ranges for predicting major chemical constituents in corn using NIR spectroscopy

Many studies have been conducted using NIR spectroscopy to predict corn constituents; however, a systematic investigation of the spectral sub-regions under the scope of overtones and combinations has not been performed. In this study, the corn spectra were divided into second overtones (1100-1388 nm), first overtones (1390-1852 nm), and combinations (1852-2498 nm). Then, using variable importance in projection and genetic algorithm, each region was inspected sequentially to identify the most informative sub-region for each attribute to improve interpretability. The identified spectral subsets were further tuned to select the most influential bands for each attribute. The sub-regions in combinations bands was most informative for predicting water (1908-2108 nm, 2 bands), oil (2176-2304 nm, 6 bands), and protein (2130-2190 nm, 3 bands), whereas the first overtones region was the best for predicting starch (1452-1770 nm, 5 bands). Results provided valuable information for potential hardware and software improvements.