Effect Of Different Pre-processing Methods Research Articles

Nondestructive intelligent detection of total viable count in pork based on miniaturized spectral sensor

Changes in the freshness of pork due to microbial action during complex transportation and storage indicate an urgent need for in-situ, real-time monitoring techniques for chemical spoilage of meat. This study reported the use of a portable detection device based on a miniaturized visible/near-infrared spectrometer, combined with data noise reduction and machine learning methods, to predict the total viable count (TVC) in pork samples. A rapid detection device for pork TVC was designed based on the miniaturized spectrometer; a spectral preprocessing method based on the resolution of the spectrometer was proposed; the effects of different preprocessing methods on the full-wavelength modeling effect were compared; and four different feature wavelength extraction algorithms were utilized for the feature wavelengths of pork TVC. The modeling effects of different simplified models were compared. The results showed that resolution interval correction combined with standard normal variation was the most effective in full-wavelength modeling, with correlation coefficients of prediction set (RP), root mean square errors in prediction set (RMSEP), and relative percent deviation (RPD) of 0.918, 0.464 (lg CFU/g), and 2.508, respectively; interval random frog − partial least squares regression (iRF-PLSR) had the best predictive ability among all simplified models, the number of wavelengths used in the simplified model was reduced by 85.45% compared with the full-wavelength model. In contrast, the model performance was improved with RP, RMSEP, and RPD of 0.948, 0.392 (lg CFU/g) and 2.970, respectively. The combination of a rational spectral acquisition setup and a data processing methodology, the miniaturized spectrometer showed competitive results with the complex detection system in predicting meat TVC.

Tracking the effect of roasting and fermentation on the metabolites of licorice root (Glycyrrhiza glabra L.) using UPLC-MS analysis combined with multivariate statistical analysis

BackgroundRoasting, honey-roasting and fermentation are the most common pre-processing procedures of licorice roots. They were shown to noticeably change the composition of extracts. In this work, the common alterations in licorice secondary metabolites by processing were interpreted. Comprehensive metabolic profiling of different studied samples was undergone.MethodsUPLC-QqQ-MS/MS analysis coupled to various chemometric analysis models was implemented to unravel the effect of different pre-processing procedures on the chemical profile of licorice samples.ResultsUPLC-QqQ-MS/MS analysis designated 133 chromatographic peaks with saponins, flavonoids, chalcones and pterocarpans being the most abundant groups. Triterpene saponins dominated the secondary metabolites in the aqueous extracts, with fermented samples showing the highest relative amounts. Meanwhile the ethanol extracts showed significant amounts of chalcones. Melanoidins were only detected in roasted and honey roasted samples. Multivariate models indicated that roasting of samples induced a greater effect on the polar metabolites rather than nonpolar ones. Variable of importance (VIP) plot indicated that glycyrrhizin and its hydrolysis product glycyrrhetinic acid, trihdroxychalcone diglycoside, glabrone and glabridin are the main chemical features responsible for the discrimination of samples.ConclusionCoupling UPLC-MS/MS to multivariate analysis was a successful tool that unveiled the significant effect of different pre-processing methods on the chemical profile of processed and unprocessed licorice samples. Moreover, such coupling unraveled the discriminatory chemical compounds among tested samples that can be employed as markers for the processing procedure of licorice.

Improving the Accuracy of Soil Organic Carbon Estimation: CWT-Random Frog-XGBoost as a Prerequisite Technique for In Situ Hyperspectral Analysis

Rapid and accurate measurement of the soil organic carbon (SOC) content is a pre-condition for sustainable grain production and land development, and contributes to carbon neutrality in the agricultural industry. To provide technical support for the development and utilization of land resources, the SOC content can be estimated using Vis-NIR diffuse reflectance spectroscopy. However, the spectral redundancy and co-linearity issues of Vis-NIR spectra pose extreme challenges for spectral analysis and model construction. This study compared the effects of different pre-processing methods and feature variable algorithms on the estimation of the SOC content. To this end, in situ hyperspectral data and soil samples were collected from the lakeside oasis of Bosten Lake in Xinjiang, China. The results showed that the combination of continuous wavelet transform (CWT)-random frog could rapidly estimate the SOC content with excellent estimation accuracy (R2 of 0.65–0.86). The feature variable selection algorithm effectively improved the estimation accuracy (average improvement of (0.30–0.48); based on their ability to improve model estimation on average, the algorithms can be ranked as follows: particle swarm optimization (PSO) > ant colony optimization (ACO) > random frog > Boruta > simulated annealing (SA) > successive projections algorithm (SPA). The CWT-XGBoost model based on random frog showed the best results, with R2 = 0.86, RMSE = 2.44, and RPD = 2.78. The feature bands accounted for only 0.57% of the Vis-NIR bands, and the most important sensitive bands were distributed at 755–1195 nm, 1602 nm, 1673 nm, and 2213 nm. These findings are of significance for the extraction of precise information on lakeside oases in arid areas, which would aid in achieving human–land sustainability.

Non-destructive recognition of copy paper based on advanced spectral fusion and feature optimization

In order to provide more clues for ongoing investigations and case handling, as well as achieve fast, non-destructive, and accurate identification of copy paper found at crime scenes, this study aims to utilize advanced spectral fusion technology to characterize and identify the three-dimensional features of the “origin-manufacturer-brand” of copy paper. Confocal Raman Microscopic and Fourier transform infrared spectroscopy were employed to collect spectral data from 200 samples from four regions (Shandong, Henan, Shaanxi, Jiangsu). The effects of different preprocessing methods, such as Hilbert transformation and deconvolution, on the model's ability to distinguish were compared. Feature variables were extracted using principal component analysis, and Bayesian discriminant classification models were constructed based on single infrared spectroscopy, Raman spectroscopy, and three types of spectral fusion datasets. By comparing the classification accuracy of different models, the primary fusion based on the full spectrum dataset was selected as the optimal model for the three-dimensional feature classification of copy paper. The accuracy achieved for origin (96%), manufacturer (100%), and brand (100%) was satisfactory, and the classification results were highly accurate. This study provides valuable insights and serves as a reference for its application in forensic science research.

Nondestructive detection of nutritional parameters of pork based on NIR hyperspectral imaging technique

Nondestructive detection of the nutritional parameters of pork is of great importance. This study aimed to investigate the feasibility of applying hyperspectral image technology to detect the nutrient content and distribution of pork nondestructively. Hyperspectral cubes of 100 pork samples were collected using a line-scan hyperspectral system, the effects of different preprocessing methods on the modeling effects were compared and analyzed, the feature wavelengths of fat and protein were extracted, and the full-wavelength model was optimized using the regressor chains (RC) algorithm. Finally, pork's fat, protein, and energy value distributions were visualized using the best prediction model. The results showed that standard normal variate was more effective than other preprocessing methods, the feature wavelengths extracted by the competitive adaptive reweighted sampling algorithm had better prediction performance, and the protein model prediction performance was optimized after using the RC algorithm. The best prediction models were developed, with the correlation coefficient of prediction (RP) = 0.929, the root mean square error in prediction (RMSEP) = 0.699% and residual prediction deviation (RPD) = 2.669 for fat, and RP = 0.934, RMSEP = 0.603% and RPD = 2.586 for protein. The pseudo-color maps were helpful for the analysis of nutrient distribution in pork. Hyperspectral image technology can be a fast, nondestructive, and accurate tool for quantifying the composition and assessing the distribution of nutrients in pork.

CT Lung Nodule Segmentation: A Comparative Study of Data Preprocessing and Deep Learning Models

The number of deaths from lung cancer reached 1.8 million in 2020, ranking first among all cancers. Early diagnosis has been found to improve the survival rate of lung cancer patients after treatment in clinical care. Computed tomography (CT) is a technique commonly used in the early detection of lung cancer to determine the benignity or malignancy of lung nodules. Manual analysis of CT results is less efficient and its accuracy is affected by physicians’ experience levels. Segmenting lung nodules in a computer-aided diagnosis (CAD) system can effectively improve the efficiency and accuracy of the diagnosis. In this paper, we evaluate several deep learning segmentation models (including UNet, SegNet, GCN, FCN, DeepLabV3+, PspNet TransUNet, SwinNet) and examine the effects of different preprocessing methods on the models to explore the best preprocessing and training strategies for lung nodule segmentation. Specifically, we investigate the effects of two different data preprocessing methods (adding a lung mask and croping the region of interest) on the segmentation results, where better segmentation results are achieved by including the nodal data of the region of interest without the lung mask. Through a comprehensive comparison, TransUNet achieves the best segmentation accuracy, with DICE indices of 0.887, 0.871, 0.75, and 0.744 tested on four datasets, respectively.

Rapid nondestructive detecting of sorghum varieties based on hyperspectral imaging and convolutional neural network.

The purity of sorghum varieties is an important indicator of the quality of raw materials used in the distillation of liquors. Different varieties of sorghum may be mixed during the acquisition process, which will affect the flavor and quality of liquor. To facilitate the rapid identification of sorghum varieties, this study proposes a sorghum variety identification model using hyperspectral imaging (HSI) technology combined with convolutional neural network (AlexNet). First, the watershed algorithm, which was modified with the extended-maxim transform, was used to segment the hyperspectral images of a single sorghum grain. The isolated forest algorithm was used to eliminate abnormal spectral data from the complete spectral data. Secondly, the AlexNet model of sorghum variety identification was established based on the two-dimensional gray image data of sorghum grain in group 1. The effects of different preprocessing methods and different convolution kernel sizes on the performance of the AlexNet model were discussed. The eigenvalues of the last layer of the AlexNet model were visualized using the t-distributed random neighborhood embedding method, which is used to evaluate the separability of features extracted by the AlexNet model. The performance differences between the optimal AlexNet model and traditional machine learning models for sorghum variety identification were compared. Finally, the varieties of sorghum grains in groups 2 and 3 were identified based on the optimal AlexNet model, and the average accuracy values of the test set reached 95.62% and 95.91% respectively. The results in this study demonstrated that HSI combined with the AlexNet model could provide a feasible technical approach for the detection of sorghum varieties. © 2022 Society of Chemical Industry.

How to Decide the Number of Gait Cycles in Different Low-Pass Filters to Extract Motor Modules by Non-negative Matrix Factorization During Walking in Chronic Post-stroke Patients.

The motor modules during human walking are identified using non-negative matrix factorization (NNMF) from surface electromyography (EMG) signals. The extraction of motor modules in healthy participants is affected by the change in pre-processing of EMG signals, such as low-pass filters (LPFs); however, the effect of different pre-processing methods, such as the number of necessary gait cycles (GCs) in post-stroke patients with varying steps, remains unknown. We aimed to specify that the number of GCs influenced the motor modules extracted in the consideration of LPFs in post-stroke patients. In total, 10 chronic post-stroke patients walked at a self-selected speed on an overground walkway, while EMG signals were recorded from the eight muscles of paretic lower limb. To verify the number of GCs, five GC conditions were set, namely, 25 (reference condition), 20, 15, 10, and 5 gate cycles with three LPFs (4, 10, and 15 Hz). First, the number of modules, variability accounted for (VAF), and muscle weightings extracted by the NNMF algorithm were compared between the conditions. Next, a modified NNMF algorithm, in which the activation timing profiles among different GCs were unified, was performed to compare the muscle weightings more robustly between GCs. The number of motor modules was not significantly different, regardless of the GCs. The difference in VAF and muscle weightings in the different GCs decreased with the LPF of 4 Hz. Muscle weightings in 15 GCs or less were significantly different from those in 25 GCs using the modified NNMF. Therefore, we concluded that the variability extracted motor modules by different GCs was suppressed with lower LPFs; however, 20 GCs were needed for more representative extraction of motor modules during walking in post-stroke patients.

Rapid and nondestructive prediction of amylose and amylopectin contents in sorghum based on hyperspectral imaging

The contents of amylose and amylopectin in sorghum directly affects the quality and yield of liquor. Hyperspectral imaging (HSI) is an emerging technology widely applied in the content analysis of food ingredients. In this study, the effects of different preprocessing methods on visible-light and near-infrared spectral data were analyzed, and the prediction accuracies of these spectral data were compared. Principal components analysis (PCA) and successive projections algorithm (SPA) were combined to extract the characteristic wavelengths. Using both the full and characteristic wavelengths, partial least square regression (PLSR) and cascade forest (CF) models were developed to predict the contents of amylose and amylopectin in different varieties of sorghum. The average RPD values of the CF models established by the characteristic wavelengths were 4.7622 and 5.5889, respectively. These results corroborated the utility of HSI in achieving the rapid and nondestructive prediction of amylose and amylopectin contents in different varieties of sorghum.

Driven by machine learning to intelligent damage recognition of terminal optical components

In order to realize the terminal optical element online detection system in the Shenguang III system, each optical element in each terminal optical component in the target room is detected. The research on the optical damage of terminal optical components focuses on the search for damage points, the extraction of damage information, and the classification of damage types. In addition, damage classification and identification of terminal optical components are performed through machine learning, and infrared nondestructive testing is used as technical support to improve the identification model and reduce the complexity of the spectral model. After studying the preprocessing and dimensionality reduction methods of near-infrared spectroscopy, this paper compares the effects of different preprocessing methods and screening feature methods and combines different modeling methods to conduct experiments. The research results show that the method proposed in this paper has certain effects.

Determination of water content in corn stover silage using near-infrared spectroscopy

The aim of this study was to evaluate the feasibility of utilizing near-infrared spectroscopy to determine the water content of corn stover silage across a wide range. The water contents of 208 samples were measured, and their corresponding near-infrared spectra were simultaneously collected. The effects of different preprocessing methods, such as derivation, standard normal variety (SNV), multiplicative scatter correction (MSC), and non-preprocessing methods for the obtained near-infrared spectra on the performance of calibration models were compared. The calibration models were established by modified partial least squares (MPLS) regression. The results showed that the calibration model developed from the successive preprocessing of MSC and first-order derivation (1-D) achieved the optimal performance. The correlation coefficients of the calibration and validation subset were 0.974 and 0.949, respectively, and the standard errors of the calibration and cross validation were 4.249% and 4.256%, respectively. External validation was performed on 60 samples. The correlation coefficient between the measured and predicted values of the calibration model was 0.973 and the prediction model’s relative percent deviation was 4.317. This indicated that the mathematical model of near-infrared spectroscopy predicted the water content in corn stover silage with high accuracy. The study showed that the near-infrared spectroscopy technology can be used for rapid and non-destructive testing across a wide range of water contents in the corn stover silage. Keywords: near-infrared spectroscopy, water, non-destructive measurement, corn stover silage DOI: 10.25165/j.ijabe.20191206.4914 Citation: Zhang M Q, Zhao C, Shao Q J, Yang Z D, Zhang X F, Xu X F, et al. Determination of water content in corn stover silage using near-infrared spectroscopy. Int J Agric & Biol Eng, 2019; 12(6): 143–148.

Determination of water content in corn stover silage using near-infrared spectroscopy

The aim of this study was to evaluate the feasibility of utilizing near-infrared spectroscopy to determine the water content of corn stover silage across a wide range. The water contents of 208 samples were measured, and their corresponding near-infrared spectra were simultaneously collected. The effects of different preprocessing methods, such as derivation, standard normal variety (SNV), multiplicative scatter correction (MSC), and non-preprocessing methods for the obtained near-infrared spectra on the performance of calibration models were compared. The calibration models were established by modified partial least squares (MPLS) regression. The results showed that the calibration model developed from the successive preprocessing of MSC and first-order derivation (1-D) achieved the optimal performance. The correlation coefficients of the calibration and validation subset were 0.974 and 0.949, respectively, and the standard errors of the calibration and cross validation were 4.249% and 4.256%, respectively. External validation was performed on 60 samples. The correlation coefficient between the measured and predicted values of the calibration model was 0.973 and the prediction model’s relative percent deviation was 4.317. This indicated that the mathematical model of near-infrared spectroscopy predicted the water content in corn stover silage with high accuracy. The study showed that the near-infrared spectroscopy technology can be used for rapid and non-destructive testing across a wide range of water contents in the corn stover silage. Keywords: near-infrared spectroscopy, water, non-destructive measurement, corn stover silage DOI: 10.25165/j.ijabe.20191206.4914 Citation: Zhang M Q, Zhao C, Shao Q J, Yang Z D, Zhang X F, Xu X F, et al. Determination of water content in corn stover silage using near-infrared spectroscopy. Int J Agric & Biol Eng, 2019; 12(6): 143–148.

Effects of pre-processing methods on Landsat OLI-8 land cover classification using OBIA and random forests classifier

The application of Landsat satellite imagery in land cover classification is affected by atmospheric and topographic errors, which have led to the development of different correction methods. In this study, moderate resolution atmospheric transmission (MODTRAN) and dark object subtraction (DOS) atmospheric corrections, and cosine topographic correction were evaluated individually and combined in a heterogeneous landscape in Zambia. These pre-processing methods were tested using a combination of object-based image analysis (OBIA) and Random Forests (RF) non-parametric classifier (hereafter referred to as OBIA-RF). This assessment aimed at understanding the combined effects of different pre-processing methods and the OBIA-RF classification method on the accuracy of Landsat operational land (OLI-8) imagery with different spatial resolutions. Here, we used pansharpened and standard Landsat OLI-8 images with 15 and 30 m spatial resolutions, respectively. The results showed that non pre-processed images reached a classification accuracy of 68% for pansharpened and 66% for standard Landsat OLI-8. Classification accuracy improved to 93% (pansharpened) and 86% (standard) when combined MODTRAN and cosine topographic correction pre-processing were applied. The results highlight the importance of pansharpening, as well as atmospheric and topographic corrections for Landsat OLI-8 imagery, when used as input in OBIA classification with the RF classifier.

Hyperspectral imaging as an effective tool for prediction the moisture content and textural characteristics of roasted pistachio kernels

The objective of this study was to develop calibration models for prediction of moisture content and textural characteristics (fracture force, hardness, apparent modulus of elasticity and compressive energy) of pistachio kernels roasted in different conditions (temperatures 90, 120 and 150 °C; times 20, 35 and 50 min and air velocities 0.5, 1.5 and 2.5 m/s) using Vis/NIR hyperspectral imaging and multivariate analysis. The effects of different pre-processing methods and spectral treatments such as normalization [multiplicative scatter correction (MSC), standard normal variate transformation (SNV)], smoothing (median filter, Savitzky–Golay and Wavelet) and differentiation (first derivative, D1 and second derivative, D2) on the obtained data were investigated. The prediction models were developed by partial least square regression (PLSR) and artificial neural network (ANN). The results indicated that ANN models have higher potential to predict moisture content and textural characteristics of roasted pistachio kernels comparing to PLSR models. High correlation was observed between reflectance data and fracture force (R2 = 0.957 and RMSEP = 3.386) using MSC, Savitzky–Golay and D1, compressive energy (R2 = 0.907 and RMSEP = 15.757) using the combination of MSC, Wavelet and D1, moisture content (R2 = 0.907 and RMSEP = 0.179) and apparent modulus of elasticity (R2 = 0.921 and RMSEP = 2.366) employing combination of SNV, Wavelet and D1, respectively. Moreover, Vis–NIR data correlated well with hardness (R2 = 0.876 and RMSEP = 5.216) using SNV, Wavelet and D2. These results showed the capability of Vis/NIR hyperspectral imaging and the central role of multivariate analysis in developing accurate models for prediction of moisture content and textural properties of roasted pistachio kernels.

Predicting the moisture content and textural characteristics of roasted pistachio kernels using Vis/NIR reflectance spectroscopy and PLSR analysis

The objective of this study is to develop calibration models in order to predict the moisture content and textural characteristics (including fracture force, hardness, apparent modulus of elasticity, and compressive energy) of pistachio kernels roasted at different temperatures (90, 120 and 150 °C), times (20, 35 and 50 min), and air velocities (0.5, 1.5 and 2.5 m/s) by using visible/near infrared spectroscopy and PLSR. The effects of different pre-processing methods and spectra treatments such as normalization, multiplicative scatter correction (MSC), standard normal variate transformation, median filter, Savitzky–Golay, wavelet, and differentiation (first derivative (D1) and second derivative (D2)) were analyzed. High correlation between Vis/NIR measurements with fracture force and apparent modulus of elasticity were obtained with the combination of SNV, wavelet, and D1. NIR measurements correlated well with hardness and compressive energy. Meanwhile, moisture content had correlation with SNV, median filter, D1; SNV, Savitzky–Golay, D1 and MSC, median filter, D1 respectively.

Identification of Wine According to Grape Variety Using Near-Infrared Spectroscopy Based on Radial Basis Function Neural Networks and Least-Squares Support Vector Machines

This paper describes how near-infrared (NIR) spectroscopy combined with radial basis function neural networks (RBFNN) and least-squares support vector machines (LS-SVMs) based on principal component analysis (PCA) can be used to classify wines from grape varieties. The effects of different preprocessing methods (standard normal variate (SNV) and multiplicative scattering correction (MSC)) on classification results were also compared. The results show that the use of NIR preprocessing spectral data with optimum RBFNN parameters produced a very high level of correct classification rate, 90.16–98.36%. For RBF LS-SVM, identification rates were from 91.80 to 98.36%. The results demonstrate that, combined with chemometrics with appropriate spectral data pretreatment, NIR spectroscopy has potential to rapidly and nondestructively differentiate wine according to grape variety. The results of this study are helpful to develop a more rapid and nondestructive detection method of wine.

English

English

FT-Raman Spectroscopy and PLS Regression for Quantitative Determination of Captopril in Tablet Powder; Effect of Different Preprocessing Methods

Aims: This study was performed to develop a fast and simple method for the quantitative analysis of Captopril in tablet powder by FT-Raman Spectroscopy and PLS regression. The effect of different preprocessing methods on multivariate calibration was studied. Methodology: Four different preprocessing methods, namely mean center (MC), autoscale (AS), normalization (N1) and orthogonal signal correction (OSC) were applied to reduce the impact of sources of variability, such as instrument drift and sampling variability, correct for path length variation and increase the signal to noise ratio. PLS regression models were fitted and their predictive performance was evaluated by the root mean square error of prediction (RMSEP) and number of latent variables (LVs). Research Article American Chemical Science Journal, 4(1): 24-37, 2014 25 Place and Duration of Study: School of Pharmacy, University of Maryland, between July to November 2012. Results: N1-AS combination (in this order) was found to give best results as it decreased the RMSEP by 15 % (from 0.92 to 0.77) with same number of latent variable used in the model (2 LVs). Other preprocessing methods have not yielded good results for this application. The results obtained by the proposed method were compared with those of the reported HPLC method. No significant difference has been observed regarding both accuracy and precision. Conclusion: FT-Raman Spectroscopy with PLS regression can be used as a reliable alternative for HPLC method, as it is faster and does not require sample pretreatment procedures.

Vis/NIR spectroscopy and chemometrics for the prediction of soluble solids content and acidity (pH) of kiwifruit

Visible and near infrared spectroscopic (Vis/NIRS) techniques have shown promise as rapid and non-destructive tools to evaluate the various internal quality attributes of fruits and vegetables. The objective of this study was to develop a calibration model for prediction of soluble solids content and acidity (pH) of kiwifruit by using visible and near infrared spectroscopy and chemometrics. The transmission spectra of kiwifruit were obtained in the wavelength range from 400 to 1000 nm. The effects of different pre-processing methods and spectra treatments, such as standard normal variate transformation (SNV), multiplicative scatter correction (MSC), and median filter and first derivative (D 1 ) were analysed. The prediction models were developed by principal component analysis (PCA) and partial least square regression (PLS). The correlation coefficient for soluble solids content and pH were 0.93, 0.943 and root mean square error of prediction (RMSEP) was 0.259Brix and 0.076, respectively. These results were achieved when SNV was utilised in conjunction with median filter and first derivative. This showed the capability of Vis/NIRS and the important role of chemometrics in developing accurate models for the prediction of kiwifruit internal quality characteristics.

Identification of the breast edge using areas enclosed by iso-intensity contours

The segmentation of a mammogram into background and breast is a crucial first step in the computer aided diagnosis of mammograms that has the advantage of simplifying further processing of the image (by eliminating the background) and also provides a reference for the alignment of views when two views are being compared. A novel method of segmenting the breast from the background by analysing the area enclosed by iso-intensity contours is presented. Results are evaluated by comparison with manual borders drawn by three radiologists for a set of 25 mammograms. The effect of different pre-processing methods, on the accuracy of automated borders, is investigated. The best methods yielded average root-mean-square differences between the manual and automated iso-intensity borders of 3.0 ± 0.3 mm for the image set containing clear breast edges and 4.8 ± 0.5 mm for the image set containing indistinct breast edges compared to 5.1 ± 0.8 and 7.9 ± 0.9 mm for the two data sets with no pre-processing. Results are also compared to those obtained from global thresholding.