Squared Error Of Prediction Research Articles

Rapid detection of pork gelatin in ice cream samples by using non-destructive FT-NIR spectroscopy and Partial least squares-discriminant analysis

This study aimed at developing a fast and low-cost detection method to discriminate between ice cream samples containing pork or non-pork gelatin by using Fourier Transform Near Infrared (FT-NIR) spectroscopy and Partial Least Squares Discriminant Analysis (PLS-DA). Forty two samples of ice cream were used, among which twenty three samples were adulterated with different levels i.e. 1%, 5%, 10%, and 20 % of pork gelatin (Non-Halal). Whereas, the remaining nineteen samples containing only cow gelatin (Halal) were used as a control. All the ice cream samples were measured with the FT-NIR spectrophotometer in the reflection mode. Spectra were collected in the wavenumber range from 10000 to 4000 cm−1 (1000 to 2500 nm). The results show that the PLS-DA model with Unit Vector Normalization (UVN) spectral transformations for 1% pork gelatin adulteration is the optimal one which was based on a compromise between the lowest value of root mean square error of cross validation (RMSECV) for the calibration set. The lowest value of root mean square error of prediction (RMSEP) for the test set, the least number of factors and the percentage of correctly classified samples, the Halal and Non-Halal, for both calibration and test sets. This newly developed method is fast, involves simple sample preparation and is low cost.

Estimation of soluble solids content and fruit temperature in 'Rocha' pear using Vis-NIR spectroscopy and the SpectraNet–32 deep learning architecture

Spectra-based methods are becoming increasingly important in Precision Agriculture as they offer non-destructive, quick tools for measuring the quality of produce. This study introduces a novel approach for estimating the soluble solids content (SSC) of ‘Rocha’ pears using the SpectraNet–32 deep learning architecture, which operates on 1D fruit spectra in the visible to near-infrared region (Vis-NIRS). This method was also able to estimate fruit temperatures, which improved the SSC prediction performance. The dataset consisted of 3300 spectra from 1650 ‘Rocha’ pears collected from local markets over several weeks during the 2010 and 2011 seasons, which had varying edaphoclimatic conditions. Two types of partial least squares (PLS) feature selection methods, under various configurations, were applied to the input spectra to identify the most significant wavelengths for training SpectraNet–32. The model’s robustness was also compared to a similar state-of-the-art deep learning architecture, DeepSpectra, as well as four other classical machine learning algorithms: PLS, multiple linear regression (MLR), support vector machine (SVM), and multi-layer perceptron (MLP). In total, 23 different experimental method configurations were assessed, with 150 neural networks each. SpectraNet–32 consistently outperformed other methods in several metrics. On average, it was 6.1% better than PLS in terms of the root mean square error of prediction (RMSEP, 1.08 vs. 1.15%), 7.7% better in prediction gain (PG, 1.67 vs. 1.55), 3.6% better in the coefficient of determination (R2, 0.58 vs. 0.56) and 5.8% better in the coefficient of variation (CV%, 8.35 vs. 8.86).

Spectroscopic studies on thermal degradation and quantitative prediction on acid value of edible oil during frying by Raman spectroscopy

The health risks posed by harmful substances resulting from the thermal degradation of frying oils are of great concern. Characteristic peak intensity ratios (PIRs) screened from Raman spectra were used to characterize the thermal degradation. High correlation coefficients between PIRs and acid values (AVs) of 0.972 (linear fitting), 0.984 (logarithmic function fitting), and 0.954 (linear fitting) for fried soybean oil, canola oil, and palm oil, were obtained at the PIRs of I1267/I1749, I1267/I1659, and I1267/I1749, respectively. The highly correlated PIRs common to the three oils were determined by Pearson’s correlation coefficient combined with heat maps. To accommodate both linear and nonlinear features, a global model for predicting AVs of multi-varieties frying oils was constructed using a least-squares support vector machine algorithm, and the results performed well with a root mean square error of prediction of 0.016 and a ratio of prediction to deviation of 11.351. The whole results demonstrate that Raman spectroscopy could characterize the thermal degradation and has excellent quantitative analysis ability for food control based on AV in frying oils, thus providing a new approach to quality control of frying oils.

Meta-Regression to Develop Predictive Equations for Urinary Nitrogen Excretion of Lactating Dairy Cows.

Dairy cows' urinary nitrogen (N) excretion (UN; g/d) represents a significant environmental concern due to their contribution to nitrate leaching, nitrous oxide (a potent greenhouse gas), and ammonia emissions (contributor to N deposition). The first objective of the current study was to determine the adequacy of existing models to predict UN from total mixed ration (TMR)-fed and fresh forage (FF)-fed cows. Next, we aimed to develop equations to predict UN based on animal factors [milk urea nitrogen (MUN; mg/dL) and body weight (BW, kg)] and to explore how these equations are improved when dietary factors, such as diet type, dry matter intake (DMI), or dietary characteristics [neutral detergent fiber (NDF) and crude protein (CP) content], are considered. A dataset was obtained from 51 published experiments composed of 174 treatment means. The whole dataset was used to evaluate the mean and linear biases of three existing equations including diet type as an interaction term; all models had significant linear and mean biases and two of the three models had poor predictive capabilities as indicated by their large relative prediction error (RPE; root mean square error of prediction as a percent of the observed mean). Next, the complete data set was split into training and test sets, which were used to develop and to evaluate new models, respectively. The first model included MUN and BW, and there was a significant interaction between diet type and the coefficients. This model had the worst 1:1 agreement [Lin's concordance correlation coefficient (CCC) = 0.50] and largest RPE (24.7%). Models that included both animal and dietary factors performed the best, and when included in the model, the effect of diet type was no longer significant (p > 0.10). These models all had very good agreement (CCC ≥ 0.86) and relatively low RPE (≤13.1%). This meta-analysis developed precise and accurate equations to predict UN from dairy cows in both confined and pasture-based systems.

Data fusion strategy for rapid prediction of moisture content during drying of black tea based on micro-NIR spectroscopy and machine vision

Drying is an important process in black tea processing, meanwhile, the moisture content is an important factor in determining the drying quality. However, at present, there is a lack of effective real-time detection methods for the moisture content of black tea during the drying. Therefore, we explored the analysis of spectral data and image color and texture feature data based on micro-near-infrared spectroscopy(micro-NIRS) and machine vision data fusion technology, and analyzed the spectral data and image color and texture feature data based on micro-NIR spectroscopy and machine vision data fusion technology, a quantitative prediction model for the drying moisture content of black tea was developed by LS-SVM. The results showed that the prediction accuracy of the prediction model established based on the middle -level data fusion achieved the best results and the correlation coefficient (Rp) and root mean square error of prediction (RMSEP) of the prediction set were 0. 9696 and 0.0016, respectively, and the relative deviation (RPD) was 4.0846. This study shows that data fusion based on the fusion of spectral and image technologies has a strong predictive capability for the drying process of black tea, and has some guiding significance for controlling the drying quality of black tea.

A new hybrid multivariate grey model based on genetic algorithms optimization and its application in forecasting oil products demand

PurposeConventional statistical forecasting methods typically need a large sample size or the use of overly confident hypotheses, like the Gaussian distribution of the input data. Unfortunately, these input data are frequently scarce or do no not follow a normal distribution law. A grey forecasting model can be developed and used to predict energy consumption for at least four data points or ambiguous data based on grey theory. The standard grey model, however, may occasionally result in significant forecasting errors.Design/methodology/approachIn order to reduce these errors, this paper proposes a hybrid multivariate grey model (namely Grey Modeling (1,N)) optimized by Genetic Algorithms with sequential selection forecasting mechanism, abbreviated as Sequential-GMGA(1,N). A real case of Cameroon's oil products consumption is considered to demonstrate the effectiveness of the proposed forecasting model.FindingsThe results show the superiority of Sequential-GMGA(1,4) when compared with the results of competing grey models reported in the literature, with a mean absolute percentage error as low as 0.02%.Originality/valueWithout changing the model's basic structure, the suggested framework completely extracts the evolution law of multivariate time series. Regardless of data patterns, Sequential-GMGA(1,4) actively enhances all model parameters over the course of each predicted timeframe. Consequently, Sequential-GMGA(1,4) improves forecast accuracy by resolving the discrepancy between the model's least sum of squares of prediction errors and the parameterization approach based on grey derivative.

An extreme learning machine optimized by differential evolution and artificial bee colony for predicting the concentration of whole blood with Fourier Transform Raman spectroscopy

Raman spectroscopy, with its advantages of non-contact nature, rapid detection, and minimum water interference, is promising for non-invasive blood detection or diagnosis in clinic applications. However, there is a critical issue that how to accurately analyze blood composition by Raman spectroscopy. In this study, we apply extreme learning machine (ELM) algorithm and a multivariate calibration regression model to analyze the results from Raman spectroscopy and determine the component’s concentrations in blood samples, including glucose, cholesterol, and triglyceride. Self-adaption differential evolution artificial bee colony (SADEABC) algorithm was further applied to increase the data’s accuracy and robustness. The obtained data for coefficient of determination, root mean square error of calibration, root mean square error of prediction, and relative percent deviation, were 0.9822, 0.3993, 0.3827, and 6.6679 for glucose, 0.9786, 0.2104, 0.2088 and 5.9533 for cholesterol, and 0.9921, 0.2744, 0.3433 and 10.5075 for triglyceride, respectively. Results demonstrated that the model based on SADEABC-ELM show much better prediction data than those models based on the ELM and ABC-ELM.

Determination of fatty acid of wheat by near-infrared spectroscopy with combined feature selection based on CARS and NSGA-III

In this study, an innovative method was attempt to use the multi-optimization objective algorithm to select the characteristic wavelengths of wheat near infrared spectra and realize the high-precision analysis of fatty acid in wheat. First, near-infrared (NIR) spectra of wheat samples obtained were collected by a NIRQuest 512 and pre-treated appropriately. Secondly, the competitive adaptive reweighted sampling (CARS) algorithm was used as a rough selection method to eliminate redundant feature variables in the original spectra. Then, the remaining variables were selected by nondominated sorting genetic algorithm-III (NSGA-III), and support vector machine (SVM) models based on optimized features were established to detect fatty acid of wheat with high accuracy. The results obtained showed that the CARS method can effectively screen out the characteristic wavelengths that are closely related to the measured properties of the samples. NSGA-III algorithm can be used to further compress the number of selected feature wavelengths and build a high-performance prediction model. Comparison of different SVM models, the SVM model built on the characteristics obtained by the CARS with the NSGA-III algorithm has the best performance in the case of Case2, and there are only 6 characteristic variables involved in the model establishment. The root mean square error of prediction (RMSEP) was 1.2518 mg/100 g, and the correlation coefficient of prediction (RP) was 0.9897. The results reveal that CARS combined with NSGA-III multi-optimization target algorithm can achieve efficient mining of the spectral characteristics.

Application of MIA-QSAR in Designing New Protein P38 MAP Kinase Compounds Using a Genetic Algorithm

Multivariate image analysis quantitative structure-activity relationship (MIA-QSAR) study aims to obtain information from a descriptor set, which are image pixels of two-dimensional molecule structures. In the QSAR study of protein P38 mitogen-activated protein (MAP) kinase compounds, the genetic algorithm application for pixel selection and image processing is investigated. There is a quantitative relationship between the structure and the pIC50 based on the information obtained. (The pIC50 is the negative logarithm of the half-maximal inhibitory concentration ( IC50 ), so pIC50 = −log IC50 .) Protein P38 MAP kinase inhibitors are used in the treatment of malignant tumors. The development of a model to predict the pIC50 of these compounds was performed in this study. To accomplish this, the molecules were first plotted and fixed in the same coordinates in ChemSketch. Then, the images were processed in the MATLAB program. Partial least squares (PLS) model, orthogonal signal correction partial least squares (OSC-PLS) model, and genetic algorithm partial least squares (GA-PLS) model methods are used to generate quantitative models, and pIC50 prediction is performed. The GA-PLS model has the highest predictive power for a series of statistical parameters such as root mean square error of prediction (RMSEP) and relative standard errors of prediction (RSEP). Finally, the molecular junction (docking) was done for predicted molecules in quantitative structure activity relationship (QSAR) with an appropriate receptor and acceptable results were obtained. These results are good and proper for the prediction of compounds with better properties.

Nonlocal, local and global preserving stacked autoencoder based fault detection method for nonlinear process monitoring

In recent years, the application of deep learning methods has improved the ability of nonlinear feature extraction in industrial processes. However, most of the deep learning methods cannot consider the manifold structure-related information (i.e., nonlocal, local and global manifold structure) of the data. To extract the vital structure-related features, a novel local, nonlocal and global preserving stacked autoencoder (NLGPSAE) for nonlinear process monitoring is proposed. NLGPSAE has an ability to extract crucial structure-related features by introducing a new regularized objective function with local, nonlocal and global structural information. For the preservation of local structure, NLGPSAE can preserve the original neighbor data points to be neighbor data points in the reconstructed space; for the preservation of nonlocal structures, NLGPSAE projects the nonlocal data points to be far apart in the reconstructed space; for the preservation of the global structure, the distance relationship between the original data points and the center of the data points is preserved in the reconstructed space. Two statistics Hotelling's T-squared (T2) and squared prediction error (SPE) based on features extracted by NLGPSAE are established for fault detection. The effectiveness of the proposed algorithm is verified in a complex numerical process and Tennessee Eastman process.

Rapid Detection of Tea Polyphenols in Fresh Tea Leaves Based on Fusion of Visible/Short-Wave and Long-Wave near Infrared Spectroscopy and Its Device Development

Tea polyphenols are considered as an important indicator of tea quality. Rapid detection of tea polyphenol content plays a valuable role for tea breeding and quality inspection during tea production. In this work, a portable rapid non-destructive detection device of tea polyphenols in fresh tea leaves was developed, which integrated the fusion technology of visible/short-wave (400–1050 nm) and long-wave (1000–1650 nm) near-infrared spectroscopy (Vis/NIR). Experimental results indicated that the spectra within the overlapping region (1000–1050 nm) were assembled by applying the spectral data fusing method. Followed by spectral data preprocessing with the Savitzky–Golay smoothing (SG) method, least squares support vector regression (LS–SVR) models were established for detecting the tea polyphenol content of fresh tea leaves. Based on the fused Vis/NIR spectra (dual-band), the correlation coefficient of calibration (RC), root mean square error of calibration (RMSEC), correlation coefficient of prediction (RP), root mean square error of prediction (RMSEP), and residual predictive deviation (RPD) reached 0.976, 0.679%, 0.893, 0.897%, and 2.230, respectively, which were better than the visible/short-wave or long-wave near infrared spectral data (single-band). The sensitive spectral wavebands of tea polyphenols extracted using the random frog (RF) algorithm were distributed in 402–448 nm, 555–600 nm, 810–1042 nm, 1056–1103 nm, 1219–1323 nm, 1406–1416 nm, and 1499–1511 nm. This demonstrated that the prediction of tea polyphenol content using fused spectral data combined with the LS–SVR model depended on various functional groups such as auxochromes, chromogenic groups, and hydrogen-containing groups. The proposed device is capable of non-destructive detection of tea polyphenol content in fresh tea leaves, which can provide effective technical support for tea breeding and tea leaf quality control.

CH4, C2H6, and CO2 Multi-Gas Sensing Based on Portable Mid-Infrared Spectroscopy and PCA-BP Algorithm.

A multi-gas sensing system was developed based on the detection principle of the non-dispersive infrared (NDIR) method, which used a broad-spectra light source, a tunable Fabry-Pérot (FP) filter detector, and a flexible low-loss infrared waveguide as an absorption cell. CH4, C2H6, and CO2 gases were detected by the system. The concentration of CO2 could be detected directly, and the concentrations of CH4 and C2H6 were detected using a PCA-BP neural network algorithm because of the interference of CH4 and C2H6. The detection limits were achieved to be 2.59 ppm, 926 ppb, and 114 ppb for CH4, C2H6, and CO2 with an averaging time of 429 s, 462 s, and 297 s, respectively. The root mean square error of prediction (RMSEP) of CH4 and C2H6 were 10.97 ppm and 2.00 ppm, respectively. The proposed system and method take full advantage of the multi-component gas measurement capability of the mid-infrared broadband source and achieve a compromise between performance and system cost.

Rapid detection of protein content in rice based on Raman and near-infrared spectroscopy fusion strategy combined with characteristic wavelength selection

Protein content is an essential index for evaluating rice quality. This work discussed the feasibility of rapid detection of protein content in rice using spectral data fusion technology. An improved binary particle swarm optimization algorithm (IBPSO) was proposed to select the characteristic wavelength of Raman and near-infrared spectroscopy fusion data, which improved the detection accuracy of the partial least squares correction model. The determination coefficient of prediction, root mean square error of prediction, and mean relative error of prediction of the protein content detection model established by IBPSO were 0.903, 0.235%, and 2.768%, respectively, which were better than the modeling performance of the other four algorithms. The research shows that IBPSO can efficiently acquire high correlation modeling wavelength variables through the guiding optimization of binary bits with a value of '1′. The combination of IBPSO and spectral data fusion strategy can realize the rapid detection of protein content in rice, which provides theoretical support for developing related online detection equipment.

Non-destructive prediction of colour and water-related properties of frozen/thawed beef meat by Raman spectroscopy coupled multivariate calibration

Freeze-thaw accelerated the colour deterioration of beef with the increase of colour b* and the decrease of colour a* values (P < 0.05). The maximum exudate loss reached 22 % after the seventh freeze–thaw. A strong correlation between the transversal relaxation time T21 and thawing loss may mean that T21 water contributed to the exudate loss during freeze–thaw. Afterwards, competitive adaptive reweighted sampling-partial least square (CARS-PLS) has the best prediction in thawing loss of frozen/thawed beef with correlation coefficients of prediction (Rp) of 0.971, and root mean square error of prediction (RMSEP) of 1.436. Besides, Uninformative variable elimination-partial least squares (UVE-PLS) showed good prediction effects on colour values (Rp = 0.932 – 0.994) and water content (Rp = 0.928, RMSEP = 0.582) of frozen/thawed beef. Therefore, this work demonstrated that Raman spectroscopy coupled with multivariate calibration has a good ability for non-destructive prediction in colour and water-related properties of frozen/thawed beef.

Simultaneous quantitation of free fatty acid in rice by synergetic data fusion of colorimetric sensor arrays, NIR, and MIR spectroscopy

This study evaluated the feasibility of colorimetric sensor array (CSA), near-infrared (NIR) and mid-infrared (MIR) spectroscopy for quantitation of free fatty acids in rice using data fusion. Purposely, different data sets of low-level (CSA-NIRLL, CSA-MIRLL, and NIR-MIRLL) and mid-level (CSA-NIRML, CSA-MIRML, and NIR-MIRML) fusion were adopted to enhance the statistical parameters. The model performance was evaluated using coefficient of determination for prediction, (R2p), root mean square error of prediction (RMSEP) and residual predictive deviation (RPD). Synergetic low-level and mid-level fusion model yielded 0.7707 ≤ R2p ≤ 0.8275, 14.4 ≤ RMSEP ≤ 16.3 and 2.19 ≤ RPD ≤ 2.48; and 0.7788 ≤ R2p ≤ 0.8571, 12.4 ≤ RMSEP ≤ 16.8 and 2.12 ≤ RPD ≤ 2.88, respectively. The CSA-NIRML model delivered an optimal performance for prediction of free fatty acid. The integration of CSA, NIR and MIR was feasible and could improve the prediction accuracy of free fatty acids in rice.

Application of iterative distance correlation and PLS for wavelength interval selection in near infrared spectroscopy

Wavelength selection is a fundamental and critical step in near infrared spectral analysis, which can improve the prediction performance and enhance the interpretability of the model. Motivated by the appealing properties of the distance correlation, a novel wavelength interval selection algorithm, named iterative distance correlation combined with PLS regression (IDC-PLS), is developed. To obtain all the possible wavelength intervals, our method mainly consists of two steps. First, an effective iterative procedure based on distance correlation is used to screen wavelength interval variables. Then, build a series of PLS models by recursive using all the wavelength intervals but one interval until the optimal wavelength intervals obtain, which correspond the lowest root mean square error of prediction. The IDC-PLS integrates the advantages of distance correlation with PLS method, which is an efficient strategy to enhance the performance of PLS in wavelengths selection. The performance of IDC-PLS was tested on three real NIR datasets. The results demonstrate that IDC-PLS can improve prediction performance and efficiently select strongly correlated wavelength intervals related to the response. The proposed method may be a good wavelength interval selection strategy due to its simplicity and efficiency.

Hyperspectral Imaging and Chemometrics for Authentication of Extra Virgin Olive Oil: A Comparative Approach with FTIR, UV-VIS, Raman, and GC-MS.

Limited information on monitoring adulteration in extra virgin olive oil (EVOO) by hyperspectral imaging (HSI) exists. This work presents a comparative study of chemometrics for the authentication and quantification of adulteration in EVOO with cheaper edible oils using GC-MS, HSI, FTIR, Raman and UV-Vis spectroscopies. The adulteration mixtures were prepared by separately blending safflower oil, corn oil, soybean oil, canola oil, sunflower oil, and sesame oil with authentic EVOO in different concentrations (0-20%, m/m). Partial least squares-discriminant analysis (PLS-DA) and PLS regression models were then built for the classification and quantification of adulteration in olive oil, respectively. HSI, FTIR, UV-Vis, Raman, and GC-MS combined with PLS-DA achieved correct classification accuracies of 100%, 99.8%, 99.6%, 96.6%, and 93.7%, respectively, in the discrimination of authentic and adulterated olive oil. The overall PLS regression model using HSI data was the best in predicting the concentration of adulterants in olive oil with a low root mean square error of prediction (RMSEP) of 1.1%, high R2pred (0.97), and high residual predictive deviation (RPD) of 6.0. The findings suggest the potential of HSI technology as a fast and non-destructive technique to control fraud in the olive oil industry.

Improved dynamic kernelPCAbased on local preserving projections and its application for electric submersible pump fault diagnosis

AbstractDynamic kernel principal component analysis (DKPCA) has been frequently implemented for nonlinear and dynamic process monitoring of complex industrial processes. However, traditional DKPCA focuses only on the global structural analysis of data sets and strongly neglects the local information, which is equally essential for process detection and identification. In this paper, an improved DKPCA, referred to as the local DKPCA (LDKPCA), is proposed based on local preserving projections (LPP) for nonlinear dynamic process fault diagnosis. The method combines the advantages of LPP and DKPCA by utilizing the local structure feature to maintain the geometric structure of the data in a unified framework. To achieve a highly comprehensive feature extraction, the local characteristics are fused in DKPCA to produce an optimization objective. The neighbouring points of the new objective function projection in the feature space are still maintained in proximity, and the variance information is retained simultaneously. For the purpose of fault detection, two statistics, known as theT2and squared prediction error (SPE) statistics, are constructed, based on the LDKPCA model, and used to monitor the latent variable space and the residual space, respectively. In addition, the sensitivity analysis is brought in for fault identification of the two statistics. Based on the experimental analysis using the shaft breakage data of an offshore oilfield electric submersible pump (ESP), the proposed method outperforms the conventional DKPCA in terms of fault monitoring performance. The experimental results demonstrate the potential of the method in nonlinear dynamic process fault diagnosis.

Machine learning-assisted laser-induced breakdown spectroscopy for monitoring molten salt compositions of small modular reactor fuel under varying laser focus positions

Next-generation advanced nuclear reactors based on molten salts are interested to apply machine learning (ML) technology to minimize human error and realize effective autonomous operation. Owing to harsh environments with limited access to molten salts, laser-induced breakdown spectroscopy (LIBS) has been investigated as a possible option for remote online monitoring. However, the height of molten salts is easily fluctuated by vibration. In addition, the level of molten salts could change during normal operation through the insertion of a controlling structure. While these uncertainties should be considered, their effects have not been studied yet. In this study, LIBS has been actively coupled with ML to automate the online monitoring of difficult-to-access molten salt systems. To practically apply a prediction model with ML, we intentionally defocus the measurement by manipulating the sample position. This study investigates the focusing and defocusing spectra of Sr and Mo as fission products for constructing the two prediction models using partial least squares and artificial neural network methods. For each method, the prediction models trained with focusing spectra only or focusing and defocusing spectra simultaneously are constructed and compared to each other. While the prediction model using only focusing spectra resulted in a root mean square error of prediction (RMSEP) of 0.1943–0.2175 wt%, a prediction model using both spectra led to approximately 10 times enhanced RMSEP (0.0210–0.0316 wt%). This study implies that not only focusing data but also defocusing data are needed to construct the prediction model while considering its practical usage in a real system, especially in the complex processes of the nuclear industry.

Estimation of carcass chemical composition in beef-on-dairy cattle using dual-energy X-ray absorptiometry (DXA) scans of cold half-carcass or 11th rib cut

Abstract The aim of the present study was to estimate the chemical composition (water, lipid, protein, mineral, and energy contents) of carcasses measured postmortem using dual-energy X-ray absorptiometry (DXA) scans of cold half-carcass or 11th rib cut. One hundred and twenty beef-on-dairy (dam: Swiss Brown, sire: Angus, Limousin, or Simmental) bulls (n = 66), heifers (n = 42), and steers (n = 12) were included in the study. The reference carcass composition measured after grinding, homogenization, and chemical analyses was estimated from DXA variables using simple or multiple linear regressions with model training on 70% (n = 84) and validation on 30% (n = 36) of the observations. In the validation step, the estimates of water and protein masses from the half-carcass (R2 = 0.998 and 0.997; root mean square error of prediction [RMSEP], 1.0 and 0.5 kg, respectively) and 11th rib DXA scans (R2 = 0.997 and 0.996; RMSEP, 1.5 and 0.5 kg, respectively) were precise. Lipid mass was estimated precisely from the half-carcass DXA scan (R2 = 0.990; RMSEP = 1.0 kg) with a slightly lower precision from the 11th rib DXA scan (R2 = 0.968; RMSEP = 1.7 kg). Mineral mass was estimated from half-carcass (R² = 0.975 and RMSEP = 0.3 kg) and 11th rib DXA scans (R2 = 0.947 and RMSEP = 0.4 kg). For the energy content, the R2 values ranged from 0.989 (11th rib DXA scan) to 0.996 (half-carcass DXA scan), and the RMSEP ranged from 36 (half-carcass) to 55 MJ (11th rib). The proportions of water, lipids, and energy in the carcasses were also precisely estimated (R2 ≥ 0.882) using either the half-carcass (RMSEP ≤ 1.0%) or 11th rib-cut DXA scans (RMSEP ≤ 1.3%). Precision was lower for the protein and mineral proportions (R2 ≤ 0.794, RMSEP ≤ 0.5%). The cattle category (sex and breed of sire) effect was observed only in some estimative models for proportions from the 11th rib cut. In conclusion, DXA imaging of either a cold half-carcass or 11th rib cut is a precise method for estimating the chemical composition of carcasses from beef-on-dairy cattle.