Search

This study focuses on the investigation and comparison of combustion characteristic parameters and combustion performance indices between fast-growing trees and agricultural residues as biomass sources. The investigation is conducted through direct combustion in an air environment using a thermogravimetric analyzer (TGA). Additionally, partial least squares regression (PLSR)-based models were developed to assess combustion performance indices via near-infrared spectroscopy (NIRS), serving as a non-destructive alternative method. The results obtained through the TGA reveal that, specifically, fast-growing trees display higher average ignition temperature (227 °C) and burnout temperature (521 °C) in comparison to agricultural residues, which exhibit the values of 218 °C and 515 °C, respectively. Therefore, fast-growing trees are comparatively difficult to ignite, but sustain combustion over extended periods, yielding higher temperatures. However, despite fast-growing trees having a high ignition index (Di) and burnout index (Df), the comprehensive combustion performance (Si) and flammability index (Ci) of agricultural residue are higher, indicating the latter possess enhanced thermal and combustion reactivity, coupled with improved combustion stability. Five distinct PLSR-based models were developed using 115 biomass samples for both chip and ground forms, spanning the wavenumber range of 3595–12,489 cm−1. The optimal model was selected by evaluating the coefficients of determination in the prediction set (R2P), root mean square error of prediction (RMSEP), and RPD values. The results suggest that the proposed model for Df, obtained through GA-PLSR using the first derivative (D1), and Si, achieved through full-PLSR with MSC, both in ground biomass, is usable for most applications, including research. The model yielded, respectively, an R2P, RMSEP, and RPD, which are 0.8426, 0.4968 wt.% min⁻4, and 2.5; and 0.8808, 0.1566 wt.%2 min⁻2 °C⁻3, and 3.1. The remaining models (Di in chip and ground, Df, and Si in chip, and Ci in chip and ground biomass) are primarily applicable only for rough screening purposes. However, including more representative samples and exploring a more suitable machine learning algorithm are essential for updating the model to achieve a better nondestructive assessment of biomass combustion behavior. [ABSTRACT FROM AUTHOR]

This study investigates the non-destructive analysis of proximate parameters (moisture content, MC; volatile matter, VM; fixed carbon, FC; ash content) in various chipped and ground biomass using a combination of destructive thermogravimetric analysis (TGA) and non-destructive near-infrared spectroscopy (NIRS) with partial least squares regression (PLSR). The thermogravimetric method determines proximate analysis data through TG and DTG curves, tracking biomass mass loss over time or temperature. NIRS scans chipped biomass in diffuse reflectance, and ground biomass in transflectance mode, covering the wavenumber range from 3595 to 12,489 cm−1. PLSR-based models (Full-PLSR, GA-PLSR, SPA-PLSR, MP PLSR 5-range method, and MP PLSR 3-range method) are developed and evaluated based on R2P, RMSEP, and RPD. MC and FC models for chip biomass exhibit satisfactory performance, making them cautiously applicable in various applications, including research. Optimal models for MC and FC in chip biomass, constructed using GA-PLSR with the second derivative and Full-PLSR with a constant offset, yield high R2P values (0.8654 and 0.8773), low RMSEP values (0.85% and 2.12%), and high RPD values (2.9 and 3.0), indicating applicative capabilities. Other parameters such as MC and FC in ground biomass, as well as VM and ash content in both chip and ground biomass, are found suitable for rough screening. Model sensitivity, assessed by calculating LOQ, indicates high sensitivity for VM in both chip and ground biomass and FC in chip biomass, as the calculated LOQ value is lower than the minimum reference values used during model development. However, for the remaining parameters, LOQ values surpass the established minimum reference value, suggesting limitations in predicting samples below the calibration range. Continuous model enhancement incorporating an ample number of representative biomass samples and consistent validation with unknown samples are imperative for ensuring accurate predictions. [ABSTRACT FROM AUTHOR]

The ultimate analysis parameters, including carbon (C), hydrogen (H), nitrogen (N), and oxygen (O) content in biomass, were rarely found to be predicted by non-destructive tests to date. In this research, we developed partial least squares regression (PLSR) models to predict the ultimate analysis parameters of chip biomass using near-infrared (NIR) raw spectra of non-wood and wood samples from fast-growing tree and agricultural residue and nine different traditional spectral preprocessing techniques. These techniques include first derivative (sd1), second derivative (sd2), constant offset, standard normal variate (SNV), multiplicative scatter correction (MSC), vector normalization, min-max normalization, mean centering, sd1 + vector normalization, and sd1 + MSC. Additionally, we employed a genetic algorithm (GA), successive projection algorithm (SPA), multi-preprocessing (MP) 5-range, and MP 3-range to develop a PLSR model for rapid prediction. A dataset consisting of 120 chip biomass samples was utilized for model development in which the samples were non-wood samples of 65–67% and wood samples of 33–35%, and the model performance was evaluated and compared. The selection of the optimum performing model was mainly based on criteria such as the coefficient of determination in the prediction set (R2P), root mean square error of the prediction set (RMSEP), and the ratio of prediction to deviation (RPD). The optimal model for weight percentage (wt.%) of C was obtained using GA–PLSR, yielding R2P, RMSEP, and RPD values of 0.6954, 1.1252 wt.%, and 1.8, respectively. Similarly, for wt.% of O, the most effective model was obtained using the multi-preprocessing PLSR–5 range method with R2P of 0.7150, RMSEP of 1.3088 wt.%, and RPD of 1.9. For wt.% of N, the optimal model was obtained using the MP PLSR-3 range method, resulting in R2P, RMSEP, and RPD values of 0.6073, 0.1008 wt.%, and 1.6, respectively. However, wt.% of the H model provided R2P, RMSEP, and RPD values of 0.5162, 0.2322 wt.%, and 1.5, respectively. Notably, the limit of quantification (LOQ) values for C, H, and O were lower than the minimum reference values used during model development, indicating a high level of sensitivity. However, the LOQ for N exceeded the minimum reference value, implying the samples to be predicted by the model must be in the range of reference range in the calibration set. By scatter plot analysis, the effect of combined non-wood and wood spectra of biomass chips on rapid prediction of ultimate analysis parameters using NIR spectroscopy was investigated. To include different species in a model, the species have to be not only in the different values of the constituents to make a wider range for a robust model, but also must provide their trend line characteristics in the scatter plot, i.e., correlation coefficient (R), slope, and intercept (same slope and slope approached to 1, and intercept is same (no gap) and approached zero, high R approached to 1). The effect of the R, slope, and intercept to obtain the better-optimized model was studied. The results show that the different species affected the model performance of each parameter prediction in a different manner, and by scatter plot analysis, which of these species were affecting the model negatively and how the model could be improved was indicated. This is the first time the effect has been studied by the principle of a scatter plot. [ABSTRACT FROM AUTHOR]

In this study, partial least squares regression (PLSR) models were developed using no preprocessing, traditional preprocessing, multi-preprocessing 5-range, multi-preprocessing 3-range, a genetic algorithm (GA), and a successive projection algorithm (SPA) to assess the higher heating value (HHV) and ultimate analysis of grounded biomass for energy usage by employing near-infrared (NIR) spectroscopy. A novel approach was utilized based on the assumption that using multiple pretreatment methods across different sections in the entire NIR wavenumber range would enhance the performance of the model. The performance of the model obtained from 200 biomass samples for HHV and 120 samples for ultimate analysis were compared, and the best model was selected based on the coefficient of determination of the validation set, root mean square error of prediction, and the ratio of prediction to deviation values. Based on the model performance results, the proposed HHV model from GA-PLSR and the N models from the multi-preprocessing PLSR 5-range could be used for most applications, including research, whereas the C and H models from GA-PLSR and the O model from the multi-preprocessing PLSR 5 range method 5-range air performance and are applicable only for rough screening. The overall findings highlight that the multi-preprocessing 5-range method, which was attempted as a novel approach in this study to develop the PLSR model, demonstrated better accuracy for HHV, C, N, and O, improving these models by 4.1839%, 8.1842%, 3.7587%, and 4.0085%, respectively. Therefore, this method can be considered a reliable and non-destructive alternative method for rapidly assessing biomass properties for energy usage and can also be used effectively in biomass trading. However, due to the smaller number of samples used in the model development, more samples are needed to update the model for robust application. [ABSTRACT FROM AUTHOR]

This research proposes an artificial neural network (ANN)-based repair and maintenance (R&M) cost estimation model for agricultural machinery. The proposed ANN model can achieve high estimation accuracy with small data requirement. In the study, the proposed ANN model is implemented to estimate the R&M costs using a sample of locally-made rice combine harvesters. The model inputs are geographical regions, harvest area, and curve fitting coefficients related to historical cost data; and the ANN output is the estimated R&M cost. Multilayer feed-forward is adopted as the processing algorithm and LevenbergMarquardt backpropagation learning as the training algorithm. The R&M costs are estimated using the ANN-based model, and results are compared with those of conventional mathematical estimation model. The results reveal that the percentage error between the conventional and ANN-based estimation models is below 1%, indicating the proposed ANN model’s high predictive accuracy. The proposed ANN-based model is useful for setting the service rates of agricultural machinery, given the significance of R&M cost in profitability. The novelty of this research lies in the use of curve-fitting coefficients in the ANNbased estimation model to improve estimation accuracy. Besides, the proposed ANN model could be further developed into web-based applications using a programming language to enable ease of use and greater user accessibility. Moreover, with minor modifications, the ANN estimation model is also applicable to other geographical areas and tractors or combine harvesters of different countries of origin. [ABSTRACT FROM AUTHOR]

Biomass pellets are ideal as a source of energy because of their abundance and high energy density. This study describes the prediction of combustion properties of biomass pellets using hyperspectral near infrared (HSI) spectroscopy. The spectra were extracted from a hyperdata cube from the individual pellets. Spectra wavelength range of 860–1760 nm was used to build the calibration model with either raw spectra or spectra pre-treated by a standard normal variate (SNV), first derivative (D1) and second derivative (D2). The prediction models were established using partial least square (PLS) and deep learning (DL) regression. The calibration model which developed from DL regression has the potential to evaluate the combustion properties, which provided coefficient of determination of prediction (R2p) and root mean square error of prediction (RMSEp) of burnout time which were 0.88 and 2.01 min, ignition index were 0.76 and 0.005 %/min3, combustion index were 0.91 and 3.14 × 10−7 %2/(°C3 min2), burnout index were 0.82 and 1.75 × 10−4 %/min3, ignition temperature were 0.70 and 9.89 °C, peak temperature were 0.85 and 6.01 and the final temperature were 0.73 and 32.53 °C, respectively. Most models are suitable for screening. The prediction of combustion parameters using colour distribution mapping can be used to track, manage, and monitor pellet quality and is readily applicable to screening applications. • Investigatingcombustion properties of biomass pellets using NIR hyperspectral image. • Prediction models developed using spectral preprocessing methods with PLS and DL regression. • DL regression yielded the most accurate predictions for combustion properties. • NIRimage analysiscould beusedas monitorization tool inbiomass plants. [ABSTRACT FROM AUTHOR]

Cassava is an important crop for both the food and bio-energy industries, serving as a primary carbohydrate source and a staple food. Knowledge of the starch content (SC) is a key parameter index its quality. Non-destructive measurement of SC is needed to track the same tubers to study behaviours of SC accumulation in cassava tubers, which benefit for breeders in discovering a good variety and farmer to indicating harvesting period. This paper involves the prediction of cassava tuber starch content (SC) using multiple near infrared (NIR) spectrometers, aiming to measure SC in fresh cassava tuber. This study applies both portable NIR spectrometers at 570–1031nm and 860 – 1760 nm. The best results of the model which developed provided R2p and RPD were 0.69 and 1.80 for VIS-NIR region. Meanwhile, the Mid-NIR region provided poor performance with R2p and RPD of 0.46 and 1.36, respectively. Therefore, this study aims to assess whether it was better for predicting SC if the model was developed using combined selected significant wavelength from both Vis-NIR and Mid-NIR regions using machine learning. Genetics algorithm (GA) and variables important projection (VIP) were used for selecting significant wavelength. Selected wavelengths were combined and then generate calibration models via machine learning (ML). The results of the SC model developed using NIR spectra from selected wavelength with SV regression method had the highest performance, with R2c and RMSEc of 0.88 and 1.28%. Meanwhile, the R2p, RMSEp, and RPD of 0.74, 1.86% and 1.97, respectively. Then, the best calibration model was used to measure the unknown sample which corrected from a different harvest season. The external test set provided R2p, RMSEp were 0.88 and 1.38%. The results indicate that combination of NIR with different region can achieve. • Cassava starch content was determined using the VIS-NIR and NIR fusion models. • Derivative pretreatment is beneficial for constructing high-quality fusion spectra. • The prediction accuracy of the fusion models is better than individual model of the VIS-NIR and NIR models. • This work identified the featured wavelengths significant for the models developed. • Traditional regression method and MLs models were developed and compared for the prediction performance. [ABSTRACT FROM AUTHOR]

Abstract On-line measurement of activation energy (Ea) is very important in supporting the thermal conversion process. The main objective of this study was to evaluate the Ea of ground bamboo using near infrared spectroscopy in real time. 80 bamboo samples with different diameters were selected using random sampling. Ea was determined using the Coats-Redfern method, and Ea of reaction order (n) at n = 1 and n≠1 was investigated. The performance of on-line measurement predicted by PLS modelling for Ea at n = 1 and Ea at n≠1 showed coefficients of determination of 0.781 and 0.714, respectively; standard error of prediction of 5.249 and 6.858 kJ/mol, respectively; and bias values of −1.0628 and −1.871 kJ/mol, respectively. Both PLS models were found to be fair and could be applied toward screening. The results showed that the vibration bands of lignocellulosic components (CH 2 , hemicellulose, cellulose, and lignin) highly influenced model development. Moreover, internal relationships were identified among Ea, the pre-exponential factor (A), and n, such as A (1/min) = 63251 × e0.2200×Ea (at n = 1), A (1/min) = 33719 × e0.2267×Ea (at n≠1), and n = 0.008 × Ea+0.254. These relationships can be used to evaluate A and n if Ea is known. In the case of this study, Ea was forecasted using an NIR model. Highlights • NIRS on-line measurement could be an alternative method for TGA. • NIRS as real-time analysis gives a rapid and low cost for the estimation of Ea. • The models could be used in 2–3 s/sample in industrial applications. • Real time NIRS presented higher ability with R2 greater than 0.7 and could be used toward screening. [ABSTRACT FROM AUTHOR]

This paper reports the development of a rapid and low-cost method based on near-infrared spectroscopy as an alternative for thermogravimetric determination of the pyrolysis characteristics, including T onset , T sh , T peak , T offset and DTG peak , of milled bamboo. T onset is the extrapolated onset temperature that is calculated from the partial peak resulting from the decomposition of the hemicellulose component, T sh is the temperature corresponding to the overall maximum of the hemicellulose decomposition rate, DTG peak is the overall maximum of the cellulose decomposition rate, T peak is the temperature corresponding to the overall maximum of the cellulose decomposition rate and T offset is the extrapolated offset temperature of the DTG peak curves determined using thermogravimetric analysis (TGA). The models may be used to control the pyrolysis processes of bamboo to achieve the most economical and environmental conditions. 80 samples of bamboo with various circumferences of culms in the ranges of approximately 16–18, 18–20, 20–22, 22–24, 24–26, 26–28, 28–30, 30–32, 32–34, 34–36, 36–38 and 38–40 cm were randomly collected for optimization of the models. The models were optimized by partial least squares regression (PLSR) with 80% of samples for the calibration set and 20% for the validation set. For T onset , T sh , T peak , T offset and DTG peak, the models showed coefficients of determination (R 2 ) of 0.566, 0.845, 0.917, 0.973, and 0.671; root mean square errors of prediction (RMSEP) of 9.7 °C, 4.36 °C, 3.77 °C, 2.66 °C, and 0.428 wt loss %/min; ratios of prediction to deviation (RPD) of 1.52, 2.58, 3.48, 3.55, and 1.75; and biases of −0.344 °C, −0.765 °C, 0.349 °C, −5.41 °C, and 0.045 wt loss %/min, respectively. In addition, the results showed that pyrolysis characteristics did not depend on the circumference. The vibrational bands of water and CH 3 , O H stretch, first overtones of Ar–OH, CH 2 and HC CH in the cellulose and lignin structures, O H hydrogen bonds of polyvinyl alcohol and C H stretch corresponding to the first overtone of CH 2 had the highest influence on the values of T onset , T sh , T peak , and T offset , respectively. The vibrational band of the C O C asymmetrical stretches of cellulose and hemicellulose, and the combination of O H stretch and HOH bend of polysaccharides influenced the DTG peak value. These results are beneficial for studying the thermal behaviour of milled bamboo as a potential resource for producing biofuels, especially in the pyrolysis process. [ABSTRACT FROM AUTHOR]

This study was to optimize models using near infrared spectroscopy for evaluation of lower heating value, carbon, hydrogen, nitrogen, sulfur and oxygen content of bamboo. Partial least squares regression was performed using 80 samples of bamboo where 64 samples was randomly assigned for calibration and 16 samples for validation. The result was that lower heating value and element composition did not depend on circumference size. The models showed the coefficient of determination of validation set and ratio of standard error of prediction to standard deviation of reference value of 0.934 and 3.96 for lower heating value, 0.803 and 2.31 for carbon; 0.856 and 2.65 for hydrogen; 0.973 and 6.6 for nitrogen; 0.785 and 2.19 for sulfur and 0.522 and 1.46 for oxygen, respectively. Models for lower heating value, nitrogen and hydrogen content prediction provided the highest performance, which could be used for most application. The carbon and sulfur models were fair and oxygen model was poor. The result could be a guide for applying in bamboo trading as biomass, in design and operation control of energy conversion and in predicting flue gas flow rate, air requirement, and flue gas compositions in combustion, gasification or pyrolysis. [ABSTRACT FROM AUTHOR]

The MC (moisture content) and HHV (higher heating value) of Leucaena leucocephala pellets using NIR (near infrared) spectroscopy was investigated in this study. The MC of the pellets was adjusted by subjecting the samples to different relative humidity environments. The samples were scanned in diffuse reflection mode at wavenumbers of 12,500–4000 cm −1 . Partial least squares regression models correlating the MC and HHV with the NIR spectra were developed and validated by full cross validation. The model for MC and HHV provided coefficients of determination (R 2 ) of 0.995 and 0.964, a root mean square error of cross validation (RMSECV) of 0.187%wb and 79.2 J g −1 , bias of −0.0008%wb and 1.29 J g −1 and a RPD (ratio of prediction to deviation) of 13.9 and 5.30, respectively. The models had excellent accuracy. This rapid quality evaluation method may be used for trading of biomass pellets. An equation related MC and HHV was also developed. [ABSTRACT FROM AUTHOR]

The use of near-infrared spectroscopy for evaluation of moisture content of Jatropha curcas kernels and heating value of its residue after oil extraction were studied. In total, 100 samples of whole kernels from green, yellow and black fruits and oven-dried kernels scanned in diffuse reflection mode using a Fourier transform NIR spectrometer at wave numbers of 1,250,000–400,000 m −1 were used to develop moisture-predicting models. The corresponding residues after the oil extraction of the samples scanned in transflection mode using the same spectrometer and wave number range were used to develop the heating-value-predicting models. The models correlating the spectral data and the corresponding values measured using the reference method were developed by partial least squares regression and were validated using a test set. For the moisture content and heating value, coefficients of determination ( R 2 ) were 0.969 and 0.860, root mean square errors of prediction (RMSEP) were 4.0% wb and 360 J g −1 , biases were −0.7% wb and −17 J g −1 and ratios of prediction to deviation (RPD) were 5.7 and 2.6, respectively. In addition, vibration bands of fibre and cellulose had important effects on the prediction of the heating value. [ABSTRACT FROM AUTHOR]

The determination of the thermal properties, including thermal diffusivity, thermal conductivity, and specific heat, of Jatropha curcas L. kernels was conducted using near-infrared (NIR) spectroscopy. A total of 100 samples of whole kernels from green, yellow and black fruits and oven dried kernels were scanned using a Fourier transform NIR spectrometry over the range of 1,250,000-400,000 m-1. Models correlating the spectral data and the thermal properties measured by a reference method were developed by partial least squares regression and validated by test set validation. The results showed that for thermal diffusivity, thermal conductivity at 40 °C and 100 °C and specific heat at 40 °C and 100 °C, the coefficients of determination (R2) were 0.5968, 0.7592, 0.7509, 0.4211 and 0.6396%, respectively; the root mean square errors of prediction (RMSEP) were 1.1 × 10-6 m2 s-1, 0.0169 W m-1 °C-1, 0.0685 W m-1 °C-1, 5.88 kJ kg-1 °C-1 and 15.8 kJ kg-1 °C-1; the biases were -2.52 × 10-7 m2 s-1, 2.85 × 10-3 W m-1 °C-1, 2.52 × 10-2 W m-1 °C-1, 1.83 kJ kg-1 °C-1 and 4.69 kJ kg-1 °C-1; and the ratios of prediction to deviation (RPD) were 1.57, 2.04, 1.98, 1.28 and 1.64, respectively. These show the possibility of using NIR spectroscopy as an alternative method to estimate the properties of Jatropha kernels, especially the thermal conductivity at 40 °C and 100 °C. [ABSTRACT FROM AUTHOR]

The thermal properties of Jatropha curcas L. kernels, including thermal diffusivity and conductivity were studied where kernels in 3 different forms were investigated, i.e. whole kernels, ¼ kernels and kernel powder. The specific heat of kernels in 2 different forms was also assessed (i.e. small piece of kernel and powdered kernel). The experiments were undertaken using kernels obtained at 2 different harvesting periods, a mature, ripe stage (yellow fruit) and a fully ripe stage (black fruit). The thermal diffusivity of whole kernels, ¼ kernels and kernel powder obtained from yellow fruit were 9.303 × 10−6, 8.370 × 10−6 and 7.456 × 10−6 m2 s−1, respectively, while those obtained from black fruit were 8.792 × 10−6, 7.723 × 10−6 and 6.652 × 10−6 m2 s−1, respectively. The thermal conductivity of whole kernels, ¼ kernels and powdered kernels increased with increasing temperature from 25 to 100 °C, ranged from 0.0663 to 0.1181, 0.0593 to 0.1087 and from 0.0536 to 0.1015 W m−1 °C−1 for the 3 kernel forms derived from yellow fruit, respectively. For the different kernel forms obtained from the black fruit the corresponding values were 0.0608–0.0977, 0.0527–0.0841 and 0.0452–0.0740 W m−1 °C−1, respectively. The specific heat of the small piece kernel and powder obtained from yellow fruit, ranged from 0.7852 to 1.3929 and from 1.3823 to 2.4510 kJ kg−1 °C−1, respectively. For black fruit, the values ranged from 0.6258 to 0.9933 and from 0.8930 to 1.7810 kJ kg−1 °C−1, respectively. Linear relationships between thermal conductivity and specific heat with temperature are reported. [Copyright &y& Elsevier]

Classification of the crosslink density level of para rubber medical gloves by using near-infrared spectral data combined with machine learning is the first time reported in this paper. The spectra of medical glove samples with different crosslink densities acquired by an ultra-compact portable MicroNIR spectrometer were correlated with their crosslink density levels, which were referencely evaluated by the toluene swell index (TSI). The machine learning protocols used to classify the 3 groups of TSI were specified as less than 80% TSI, 80–88% TSI, and more than 88% TSI. The 80–88% TSI group was the group in which the compounded latex was suitable for medical glove production, which made the glove specification comply with the requirements of customers as indicated by the tensile test. The results show that when comparing the algorithms used for modeling, the linear discriminant analysis (LDA) developed by 2nd derivative spectra with 15 k-best selected wavelengths fairly accurately predicted the class but was most reliable among other algorithms, i.e., artificial neural networks (ANN), support vector machines (SVM), and k-nearest neighbors (kNN), due to higher prediction accuracy, precision, recall, and F1-score of the same value of 0.76 and no overfitting or underfitting prediction. This developed model can be implemented in the glove factory for screening purposes in the production line. However, deep learning modeling should be explored with a larger sample number required for better model performance. [ABSTRACT FROM AUTHOR]

The efficient selection of sugarcane varieties with enhanced sugar content requires simple, rapid, accurate and cost-effective assays. The objective of this research was to develop spectroscopic models for non-destructive evaluation of Commercial Cane Sugar (CCS) in growing cane stalks. A portable visible-shortwave near-infrared (Vis/SWNIR) spectrometer with a wavelength range of 570–1031 nm was applied to cane stalks grown under normal field conditions. The CCS models were developed by partial least squares (PLS) regression using spectra sets obtained at three different times (i.e. morning, afternoon and evening), based on both individual spectra and a combined set. During the in-field measurements, it was found that model performance could be affected by varying sample and instrument temperatures, especially for the combined set. The models had coefficients of determination of the prediction set (r2) of 0.76, 0.76, 0.78 and 0.69 and root mean square errors of prediction (RMSEP) of 1.01, 1.05, 0.99 and 1.17 CCS for the models constructed with the spectra sets of the morning, afternoon, evening and combined, respectively. These results indicate that the CCS models could be used for the monitoring and screening of sugarcane clone selection, except for the model obtained from the combined spectra set, which was influenced by varying instrument temperature. Thus, heat protection for the portable Vis/SWNIR instrument, allowing it to maintain a constant instrument temperature, should be considered if data collection across different periods of the day is necessary. • NIR has potential for CCS monitoring of growing cane in breeding programmes. • Variation in sample temperatures (25–45 °C) did not affect spectral reproducibility. • PLS models provided good accuracy and could be used for screening. • Instrument temperature, which varied in field application, caused model error. • Modelling should be performed based on individual measurement periods of the day. [ABSTRACT FROM AUTHOR]

In a previous study, a near infrared (NIR) spectroscopy model was developed using a spectra of ground bamboo samples. Although the previous report on ground bamboo described a good performance, operation in the power plant was found to be inconvenient due to preparation costs and labour required for the necessary preparation of ground samples. Thus, this study presents the comparison of the performance of an NIR model that was developed by direct scanning of bamboo chips to the previously developed model for ground samples. Special emphasis is put on the comparison of the spectral reproducibility. Bamboo chip models were developed based on PLS regression with variable selection methods in order to achieve the optimal model. The moisture content (MC) and ash content (A) of the developed bamboo chip models could be applied toward quality assurance. The volatile matter (VM) and fixed carbon (FC) models could be used for approximating predictions. The gross and net calorific value (GCV and NCV) models could be used for most applications. The root mean square (RMS) value of pre-treated spectra of different particle size had no statistically significant differences. The study's findings indicate that the model developed using NIR spectroscopy protocol with wood chips spectra can be used as a classification tool and is an effective method for estimating bamboo chip energy quality. The big particle size of wood chips affect negatively the prediction model, however, it could be solved through spectral pre-processing technique, thus eliminating the need for grinding feedstock samples. • Proximate data and calorific value were evaluated by directly scanning bamboo chips. • Models benefit the commercial use of pelletization and thermal conversion plants. • The effect of different particle sizes can be eliminated by spectra pre-treatment. • No significant difference between bamboo chips model and ground bamboo model. • Bamboo chips model should be used because of no preparation time, labour and cost. [ABSTRACT FROM AUTHOR]

Abstract Knowledge of the fibre content in sugarcane stalks is important for breeding programmes and non-destructive measurements for its applications. This study aimed to use portable visible-shortwave near infrared (Vis/SWNIR) with a wavelength range of 570–1031 nm to evaluate the fibre contents of cane stalks. Fibre models were established by partial least squares (PLS) regression using spectra obtained from interactance mode with an absorbance unit of log (1/R). The models were constructed using a sample set of three sample sections (i.e., bottom, middle, and top of the sugarcane stalk). The samples were scanned with different integration times (200, 300, and 400 ms), and the spectra were pre-treated using different pre-processing techniques. The fibre content models were established based on both combined sample sections (CSS model) and individual sample sections (ISS model) obtained from the combination of three sample sections and an individual sample section, respectively. The results showed that the models that were developed using raw spectra with integration time of 300 ms had the best performance. This model had coefficients of determination of the prediction set (r2) of 0.75, 0.81, 0.81 and 0.71 and root mean square errors of prediction (RMSEP) of 0.81, 0.63, 0.80 and 0.73%fibre for the CSS model and bottom section, middle section, and top section of the ISS model, respectively. These results indicated that the models could be used for screening. Moreover, it was observed that the bottom section model had the lowest RMSEP. The model can be used as a rapid protocol for predicting the fibre content of sugarcane stalks, making it a useful method for a breeder to screen the fibre content in the field when monitoring during breeding programmes. [ABSTRACT FROM AUTHOR]

The aim of this study was to evaluate and compare the performance of multivariate classification algorithms, specifically Partial Least Squares Discriminant Analysis (PLS-DA) and machine learning algorithms, in the classification of Monthong durian pulp based on its dry matter content (DMC) and soluble solid content (SSC), using the inline acquisition of near-infrared (NIR) spectra. A total of 415 durian pulp samples were collected and analyzed. Raw spectra were preprocessed using five different combinations of spectral preprocessing techniques: Moving Average with Standard Normal Variate (MA+SNV), Savitzky–Golay Smoothing with Standard Normal Variate (SG+SNV), Mean Normalization (SG+MN), Baseline Correction (SG+BC), and Multiplicative Scatter Correction (SG+MSC). The results revealed that the SG+SNV preprocessing technique produced the best performance with both the PLS-DA and machine learning algorithms. The optimized wide neural network algorithm of machine learning achieved the highest overall classification accuracy of 85.3%, outperforming the PLS-DA model, with overall classification accuracy of 81.4%. Additionally, evaluation metrics such as recall, precision, specificity, F1-score, AUC ROC, and kappa were calculated and compared between the two models. The findings of this study demonstrate the potential of machine learning algorithms to provide similar or better performance compared to PLS-DA in classifying Monthong durian pulp based on DMC and SSC using NIR spectroscopy, and they can be applied in the quality control and management of durian pulp production and storage. [ABSTRACT FROM AUTHOR]

The quality of fresh cassava roots can be increased through the use of precision equipment. As a first step towards developing an automatic cassava root cutting system, this study demonstrates the use of a computer vision system with deep learning for cassava stalk detection. An RGB image of a cassava tree mounted on a cassava-pulling machine was captured, and the YOLO v4 model and two Mask R-CNN models with ResNet 101 and ResNet 50 base architectures were employed to train the weights to predict the position of the cassava stalk. One hundred test images of stalks of various shapes and sizes were used to determine the grasping point and inclination, and the results from manual annotation were compared with the predicted results. Regarding localisation, Mask R-CNN with ResNet 101 gave a significantly higher performance than the other models, with an F1 score and a mean IoU of 0.81 and 0.70, respectively. YOLO v4 showed the highest correlation for the x- and y-coordinates for the prediction of the grasping point, with values for R2 of 0.89 and 0.53, respectively. For inclination prediction, Mask R-CNN with ResNet 101 and Mask R-CNN with ResNet 50 gave the same level of correlation, with values for R2 of 0.50 and 0.61, respectively. These results were acceptable for use as design criteria for developing a cassava rootcutting robot. [ABSTRACT FROM AUTHOR]

The quality of cassava in this study was indexed according to the starch content (SC) and dry matter content (DM). The NIR spectroscopy had the potential to measure changes in SC and DM of field-grown cassava. However, due to the non-homogenous nature of cassava root and its unpredictable shape, measuring it using NIR spectroscopy presents a challenge. Therefore, the model developed from different scanning method (horizontal and vertical lines) and surface (original surface, removed brownish outer layer, and fresh surface) were compared. To demonstrate that the model performance could improve by using a few significant wavelengths, its accuracy was compared using either the full wavelength or individual wavelengths selected by bootstrapping soft shrinkage analysis (BOSS) and competitive adaptive reweighted sampling (CARS) methods. Finally, the impact of physical properties (sample sections, peel thickness, varieties, and ages) on model error were determined. The prediction accuracy was found to depend on the scanning method. Since the model developed using horizontal spectra obviously obtained highest accuracy. The difference in surface had no effect on accuracy based on the horizontal spectra. Therefore, original surface scanning was chosen due to its non-destructive performance. The prediction model using the CARS-PLSR method was considered appropriate for predicting SC and BOSS-PLSR for predicting DM, providing R2 cal , r2 val , SEP, and ratio of prediction to standard deviation (RPD) of 0.69, 0.66, 3.18%, and 1.81, respectively; and 0.63, 0.54, 4.15%, and 1.50, respectively. In addition, the sample section, variety and peel thickness of the cassava root were not effected in the error of prediction. • Effective measurement technique of intact tuber was investigated. • Accuracy of different scanning method and surface were compared. • Horizontal scanning was recommended, gave similar accuracy of different surfaces. • Wavelength selection by BOSS and CARS was applied to improve prediction model. • Age, variety, peel thickness and scan position no clearly impact on model ability. [ABSTRACT FROM AUTHOR]

The DM and TSS of durian pulp moving on a conveyor belt were measured for their rapid and non-destructive qualities based on quantitative and qualitative measurements. The calibration set and prediction set equaled 209 and 69 pulps, respectively. The quantitative test compared the performance of PLS regression for DM and TSS prediction developed from full wavelength (860–1754 nm) and a few significant variables using SPA, GA, and VIP methods. The qualitative test identified the possibility of maturity stage classification by comparing three supervised machine learning classifiers, namely SVM, random forest (RF), and LDA. Effective models for DM and TSS prediction were developed from second derivatives spectra combined with the GA method, exhibiting r2, SEP, and RPD of 0.85, 4.50%, and 2.64, respectively for DM, and 0.66, 5.15%, and 1.60, respectively, for TSS. The model classifying samples into two distinct groups, namely "reject" and "pass," utilizing the LDA algorithm, exhibited an impressive accuracy rate of 94.20%, making it a suitable choice for quality assurance purposes. This result indicates that the few effective variables were more efficient than full wavelength and improved model accuracy with greater model stability. Enhancing the classification model could involve data sample balancing in each group, leading to further improvements. • NIR applied for predicting DM and TTS in durian pulp. • NIR applied for durian pulp maturity classification based on DM and TTS content. • PLSR coupled with variable selection of SPA, GA, and VIP methods were developed. • Classification ability of SVM, LDA and random forest (RF) was compared. • NIR could classify the quality stage with on line measurement. [ABSTRACT FROM AUTHOR]

• Rapid classification of levels of N, P, and K in durian leaves via NIR spectroscopy was investigated. • Models developed regarding fresh and dried ground leaf spectra were compared. • The classification model based on ANN was optimum compared with those involving PLS and kNN. • The SMOTE to balance data could increase classification accuracy. For durian growth to produce high-quality fruit, plants should receive sufficient nutrients. Currently, farmers apply various fertilisers to produce a large quantity and quality of durian fruit, irrespective of the actual nutrients that the plant requires. Accordingly, the production cost is high and non-renewable resources. Therefore, this study focused on rapid classification primary macronutrient levels in durian (Durio zibethinus Murray CV. Mon Thong) leaves using Fourier transform near-infrared (FT-NIR) spectroscopy and investigated the effect of imbalanced data on efficient classification models. Contents of N, P, and K in durian leaves were measured via NIR with the wavelength range of 800–2,500 nm. Classification models were developed using partial least squares, k-nearest neighbour, and artificial neural networks (ANNs) with imbalanced and balanced data. The imbalanced data were balanced using a synthetic minority oversampling technique (SMOTE). In this study, the model regarding the fresh leaf sample performed better than that for the dried ground leaf sample. Moreover, the ANN was the best algorithm, exhibiting validation accuracies of classified levels corresponding to N = 0.99 and P = 0.97 when the data were analysed with SMOTE and K = 1.00 from the original balanced data. The imbalanced data affected biased classification when the models could increase the classification accuracy by applying balanced data for modelling. [ABSTRACT FROM AUTHOR]

A rapid measurement method of total soluble solids content (TSC) and dry rubber content (DRC) of para rubber latex (PRL) is required for trading and production control purposes. The objective of this study was to develop the TSC and DRC prediction model of a PRL sample based on the near-infrared (NIR) spectroscopy method. The samples were scanned using the transflectance method, wherein the effect of the pathlength to model accuracy and precision were investigated. NIR spectra were collected, incorporating a wavelength region of 860–1760 nm. The models were developed using partial least squares (PLS) regression with either raw spectra or spectra pre-treated by a baseline offset, a standard normal variate (SNV), multiplicative scatter correction (MSC), and a fractional order derivative (FOD). The results of the TSC model developed using NIR spectra from a 8 mm pathlength had the highest performance, with R2p, RMSEp, Bias, and RPD of 0.97, 1.15%, 0.43% and 6.17, respectively. Meanwhile, the NIR spectra from a 4 mm pathlength developed with a FOD at 0.25 gave the best performance in DRC prediction, whose R2p, RMSEp, Bias, and RPD were 0.96, 1.20%, − 0.52% and 5.40, respectively. Therefore, the author concluded that the developed models could be used to evaluate the TSC and DRC of a PRL sample as a real-time method in factory. • The TSC and DRC NIR models for fresh para rubber latex were optimised. • Best prediction models of TSC and DRC of PRL sample provided R2p were of 0.97 and 0.96. • The TSC and DRC models were evaluated for bias which acceptable for using in production control. • Fractional order derivatives methods improved the model's accuracy. • Models ability for future sample was validated by unknown spectra, providing RMSE P of 2.01% for TSC and 1.44% for DRC. [ABSTRACT FROM AUTHOR]

• Starch content and dry matter content models for fresh cassava tubers were optimized. • NIR spectroscopy was used to predict starch and dry matter content in fresh cassava roots under field conditions. • Spectral variable selection was carried out using SPA and GA methods. • The starch and dry matter content was evaluated under field conditions for breeding purposes. • New spectral processing methods improved the model's accuracy. This study used a portable near-infrared (NIR) spectrometer at wavelengths of 570–1031 nm to evaluate starch content (SC) and dry matter content (DMC) in fresh cassava tubers. An improved model was developed for the prediction of cassava tuber quality. The cassava samples were taken from four main varieties: CMR38-125-77, KU50, RY11, and RY9. The samples were obtained 4–12 months after planting (MAP). Partial least squares (PLR) regression was combined with different variable selection methods and spectral pre-treatment. Their accuracies were then compared. Variable selection methods included the successive projections algorithm (SPA) and the genetic algorithm (GA). The NIR spectra were obtained in the interactance mode under field conditions. The GA wavelengths combined with sequential pre-processing by orthogonalization (SPORT) pre-processing provided the optimum model for predicting both the SC and the DMC of cassava. The R2p, RMSEp, and RPD of SC were 0.91, 1.76%, and 3.26, respectively, and those of DMC were 0.75, 2.00%, and 2.00, respectively. The most effective model was tested against unknown samples of newly developed varieties obtained from different harvest seasons, yielding RMSEp and bias values of 2.37% and −9.178 × 10-6%, respectively, for SC. For DMC, the RMSEp and bias values were 2.67% and 4.16 × 10-14%, respectively. The results suggest that the calibration model could be used to monitor the internal quality of cassava tubers in the field. The variety, age, position, and section of the tubers had a slight influence on the prediction performance; however, the prediction accuracy was acceptable for in-field applications. The in-field portable NIR spectrometer could become a new tool for breeders, saving time and costs. Breeders could evaluate SC without destroying the cassava roots or stalks and could correct and inspect the behaviour of the SC and DMC accumulation. [ABSTRACT FROM AUTHOR]

• DMC and SSC analysis of durian pulp using in-line conveying system. • Scanning in different orientation of durian affects the prediction model. • PLSR model was suitable for the prediction of DMC and SSC. The prediction of dry matter content (DMC) and soluble solids content (SSC) in durian pulp were performed using a small laboratory scale in-line visible and short wave near infrared (Vis-SWNIR) spectroscopic system. The fiber optic diode array spectrometer with a charged coupled device (CCD) detector in a wavelength range of 450−1000 nm was used for spectral data acquisition. The spectra of the sample were acquired on the moving conveyor belt in two different orientations, including scanning in the upright position of pulps collected in 2018 and the stable position by scanning on the side of the pulps collected in 2019. Partial least squares regression (PLSR) was used to establish the relationship between the spectra and observed DMC and SSC values using the different wavelength ranges, including 450−1000, 700−1000, and 800−1000 nm for the comparison. The results showed that the durian pulp should be scanned in the upright position at the center of the pulp. Moving average smoothing preprocessing combined with the standard normal variate (SNV) for DMC and multiple scatter correction (MSC) for SSC gave the best result. The suitable wavelength range for model development to predict the DMC and SSC was 700−1000 nm and 800−1000 nm, respectively. After comparing the results, the optimum model showed the coefficient of determination of calibration (R C 2), and prediction (R P 2), root mean square error of prediction (RMSEP), bias, and the ratio of performance to interquartile distance (RPIQ) of 0.88, 0.83, 4.32 %, 1.25 %, and 3.52 for DMC and 0.70, 0.70, 4.0 %, 0.4 %, and 2.2 for SSC prediction. [ABSTRACT FROM AUTHOR]

The use of biomass pellets as a renewable energy source is increasing, leading to the need for rapid assessment of biofuel pellet quality for production monitoring. The purpose of this work was to use line-scan near-infrared (NIR) hyperspectral image technology coupled with chemometric tools to assess the elemental components of biomass pellets. The parameters influencing model performance were investigated, i.e. wavelength and spectral pretreatment technique. Either full wavelength or partial wavelength selected using interval successive projections algorithm (iSPA) and interval genetic algorithm (iGA) were investigated. Either raw spectra or pretreated spectra were used for model development. The models were developed using partial least squares regression (PLSR). The most effective model for the prediction of carbon (C), hydrogen (H), and nitrogen (N) content was developed using iGA wavelength selection and standard normal variate (SNV) spectral pretreatment and provided the highest accuracy with a coefficient of determination of prediction set (r2 p) and standard error of prediction (SEP) of 0.83 and 1.33%; 0.84 and 0.17%; and 0.90 and 0.098%, respectively. The model could be used for quality assurance. The S content model was poor and not recommended. The relationship between pellet chemical parameters and reflectance characteristics could be used for predicting C, H, and N of biomass pellets. • NIR HSI was applied to monitor elemental component of biofuel pellets. • The model performance could be improved using wavelength selection and spectral pretreatment. • The most effect model could be developed using iGA wavelength and SNV spectra. • Image analysis ensures quality of biomass pellets during production. [ABSTRACT FROM AUTHOR]

• NIR spectroscopy has potential for measuring starch content of on-field fresh tuber. • Effect of measurement position (head, middle and tail) was examined. • Model of mixed sample was recommended in real situation measurement. • Model ability for future sample was validated by unknown in-field spectra, providing RMSEP < 1.87%. This paper involves the prediction of cassava tuber starch content (SC) using near-infrared (NIR) spectroscopy, aiming to follow the change of SC in individual tubers utilised for a breeding programme. This study applies a portable NIR spectrometer at wavelengths of 570–1031 nm in the evaluation of SC in fresh cassava tubers. The prediction models are established using partial least squares (PLS) regression with NIR spectra obtained in the interactance mode. The effective model was developed from the wavelength region of 600–1000 nm with spectral pre-processing of the second derivative, giving the coefficient of determination of prediction set (r2) and root mean square error of prediction (RMSEP) of 0.62 and 2.21%, respectively. The effect of tuber section (including head, middle and tail) on the performance of the SC model was investigated. The individual head, middle and tail models were acceptable for screening. However, the performances of the combined model (which is the model developed a mix of all individual section samples) and the individual section model were not significantly different. Therefore, the combined model was suitable in real application because of the ease of in-field scanning. The result demonstrates that the SCs of cassava tubers can be measured by a NIR spectroscopy method. Furthermore, it can be used as an alternative tool which is appropriate for breeders to use to follow the behaviour of SC during breeding. [ABSTRACT FROM AUTHOR]