Piecewise Direct Standardization Research Articles

Temperature correction of near-infrared spectra of raw milk

Accurate milk composition analysis is crucial for improving product quality, economic efficiency, and animal health in the dairy industry. Near-infrared (NIR) spectroscopy can quantify milk composition quickly and nondestructively. However, external factors, such as temperature fluctuations, can alter the molecular vibrations and hydrogen bonding in milk, altering the NIR spectra and leading to errors in predicting key constituents such as fat, protein, and lactose. This study compares the effectiveness of Piecewise Direct Standardization (PDS), Continuous PDS (CPDS), External Parameter Orthogonalization (EPO), and Dynamic Orthogonal Projection (DOP in correcting the impact of temperature-induced variations on predictions in milk long-wave NIR spectra (LW-NIR, 1000–1700 nm).A total of 270 raw milk samples were analyzed, collecting both reflectance and transmittance spectra at five different temperatures (20 °C, 25 °C, 30 °C, 35 °C, and 40 °C). The experimental setup ensured precise temperature control and accurate spectral measurements. PLSR models were calibrated at 30 °C to predict milk fat, protein, and lactose content. The performance of these models was assessed before and after applying the temperature correction methods, with a primary focus on reflectance spectra.Results indicate that EPO and DOP significantly enhance model robustness and prediction accuracy across all temperatures, outperforming PDS and CPDS, especially for lactose prediction. These orthogonalization methods were compared against PLSR models calibrated with spectra from all temperatures. EPO and DOP showed comparable or superior performance, highlighting their effectiveness without requiring extensive temperature-specific calibration data. These findings suggest that orthogonalization methods are particularly suitable for in-line milk quality measurements under farm conditions where temperature control is challenging. This study highlights the potential of advanced chemometric techniques to improve real-time, on-farm milk composition analysis, facilitating better farm management and enhanced dairy product quality.

Broadening the scope of food quality control: A calibration transfer strategy for minimizing external influences on spectral analysis

Calibration transfer (CT) is an effective tool to address spectral inconsistencies and the decline in model prediction capabilities caused by various influences. This study introduced a modified semi-supervised parameter-free calibration enhancement (MSS-PFCE) strategy to enable calibration models extensively applicable across varying temperatures, instruments and orientations. Investigations conducted on three datasets of watermelon juice, corn, and apples were utilized to validate the efficacy of MSS-PFCE. The results showed that MSS-PFCE decreased the average RMSEP for slave spectrum predictions by 96.51%, 75.96%, and 23.04%, respectively. MSS-PFCE significantly outperformed the original SS-PFCE approach and three classical standardization methods (direct standardization (DS), piecewise direct standardization (PDS) and slope and bias correction (SBC)). Furthermore, MSS-PFCE required no standards and needed only 5%–10% of slave samples for CT, maintaining robust reliability across varying sample sizes and cost thresholds (cth). The conclusions were further examined in three additional datasets with these variations. Notably, MSS-PFCE exhibited high accuracy, fitting stability, low sample dependency, and versatile transferability, positioning it as a promising candidate for widespread implementation in visible/near-infrared (Vis/NIR) spectroscopy. This study has significant potential to enhance the applicability of quality analysis, broaden the scope of food quality control, and promote the sound development of the food industry.

Enhancing cross‐scale Raman in‐line monitoring capability of cell culture process in large‐scale manufacturing

AbstractThis study introduces an approach to enhance the Raman calibration model cross‐scale prediction capabilities in cell cultures. Our investigation centers on the improvement of Raman calibration models along with the scaling‐up of mammalian cell culture processes. Initially, we observed that integrating data from a 50 L run into the original dataset at lab‐scale was an effective strategy for improving prediction accuracy on 1000 L run. Further investigation indicated that this improvement could be attributed to the similarity between the spectra of 50 L with 1000 L. Subsequent investigation unveiled that the spectral variations primarily stemmed from differences between the instruments. This was verified through a direct comparison of two Raman analyzers. Then two pairwise spectral transformation methods, direct standardization (DS) and piecewise DS, both exhibited superior performance in predicting. This research underscores the importance of Raman spectral transfer method to alleviate instrument‐to‐instrument variations in cross‐scale monitoring of cell culture processes.

In-situ prediction of soil organic carbon contents in wheat-rice rotation fields via visible near-infrared spectroscopy

Visible near-infrared (VNIR) spectroscopy is a reliable method for estimating soil properties. However, its effectiveness in accurately predicting soil organic carbon (SOC) contents, particularly in wheat-rice rotation fields, remains uncertain. In this study, we collected 202 samples from wheat-rice fields (0–20 ​cm) in southeastern China and measured in-situ spectra of the vertical surface of the soil cores and the laboratory spectra of the dried and sieved soil samples. Our study focused on evaluating three algorithms - external parameter orthogonalization (EPO), direct standardization (DS), and piecewise direct standardization (PDS) - to address the influence of external factors, particularly soil moisture. To carry out our analysis, the dataset was divided into calibration (141 samples) and validation (61 samples) sets via the Kennard-Stone algorithm. A subset of the corresponding in-situ and laboratory spectra in the calibration set (transfer set) was used to derive the transfer matrix for EPO, DS, and PDS, enabling the conversion of in-situ spectra to laboratory spectra by characterizing their differences. Four machine learning models, including cubist, partial least squares regression (PLSR), random forest (RF), and memory-based learning (MBL), were used to predict the SOC, particulate organic carbon (POC), and mineral-associated organic carbon (MAOC) contents based on the laboratory, in-situ, and corrected in-situ spectra. The results revealed that the laboratory spectra outperformed the non-corrected in-situ spectra, with coefficients of determination (R2) of 0.91, 0.75, and 0.80 for SOC, POC, and MAOC, respectively. Among the models, MBL and PLSR exhibited the highest average R2 at 0.85–0.86. EPO marginally improved the prediction accuracy (R2 increased from 0.85 to 0.87 for SOC, 0.64 to 0.69 for POC, and 0.75 to 0.82 for MAOC). These promising prediction accuracies underscore the potential of VNIR spectra for in-situ predictions in wheat-rice fields in Southeast China, offering insights for predicting SOC contents via in-situ spectroscopy.

Calibration transfer between NIR instruments using optimally predictive calibration subsets.

In this study, a new approach for the selection of informative standardization samples from the original calibration set for the transfer of a calibration model between NIR instruments is proposed and evaluated. First, a calibration model is developed, after variable selection by the Final Complexity Adapted Models (FCAM) method, using the significance of the PLS regression coefficients (FCAM-SIG) as selection criterion. Then, the resulting model is used for the selection of the best fitting subset of calibration samples with optimally predictive ability, called the optimally predictive calibration subset (OPCS). Next, the standardization samples are selected from the OPCS. The spectra on the slave instruments are transferred to corresponding spectra on the master instrument by the widely used Piecewise Direct Standardization (PDS) method. Thereafter, for the test set on the slave instrument, a 3D response surface plot is drawn for the root mean squared error of prediction (RMSEP) as a function of the number of OPCS samples and window sizes used for the PDS method. Finally, the smallest set of calibration samples, in combination with the optimal window size, providing the optimal RMSEP, is selected as standardization set. The proposed OPCS approach for the selection of standardization samples is tested on two real-life NIR data sets providing 13 X-y combinations to model. The results show that the obtained numbers of OPCS-based standardization samples are statistically significantly lower than those obtained with the widely used representative sample selection method of Kennard and Stone, while the predictive performances are similar.

Comparison of qualitative and quantitative performance of two portable near-infrared spectrometers for intact Rehmanniae Radix and calibration transfer

As a Chinese herbal medicine with high medical value, Rehmanniae Radix (RR) has a wide variety of geographical origins leading to distinctly diverse quality, and moisture content during storage affects the critical active ingredient content. In this work, two portable near-infrared (NIR) spectrometers, DLP NIRscan Nano (DLP) and VIAVI MicroNIR 1700 (M1700) were used for in-situ spectral acquisition from intact RR. The partial least squares-discriminant analysis (PLS-DA) was employed for three geographical sources (Shandong, Shanxi, Henan). After multiple pre-processing and wavelength selection, the M1700-based PLS-DA model, accuracy (Acc), sensitivity (Sen), and specificity (Spe), achieved 100 % accuracy. In contrast, model predictions using the low-cost instrument (DLP) was not satisfactory. The partial least squares regression (PLSR) was applied to predict the moisture content of RR. The best correlation coefficients in the prediction set (R2p), Root Mean Square Error of Prediction (RMSEP), and residual prediction deviation (RPD) values (0.98, 0.98, 4.98) were obtained by DLP and were also employed for comparison with the M1700 model (0.99, 0.70, 7.00). Therefore, to further improve the model prediction effect of the low-cost DLP, we employed the improved principal component analysis (IPCA), direct standardization (DS), and piecewise direct standardization (PDS) calibration transfer techniques. Unequivocally, IPCA optimized the origin identification model (Acc, Sen, and Spe were all 1.00), the moisture content prediction model RPD was increased by 23 %, and its RMSEP was reduced by 18 %, leading to the improvement in prediction accuracy of the DLP model. This study provides a portable and low-cost detection method for the in-situ evaluation of the quality of RR quality and a feasible solution for the NIR techniques to be used in the rapid and accurate in-situ analysis of RR.

Exploring mid‐infrared spectral transfer functions for the prediction of multiple soil properties using a global dataset

AbstractInfrared spectroscopy is increasingly being adopted as a technology for soil analysis. However, laboratories worldwide are equipped with different infrared spectrometers, leading to variations that hinder the global application of soil spectroscopy. This study evaluates the transferability of soil spectra from a global dataset collected using four mid‐infrared spectrometers. To evaluate the efficacy of five spectral transfer functions (direct standardization, piecewise direct standardization, spectral space transformation [SST], principal components‐canonical correlation analysis [PC‐CCA], and domain‐invariant partial least square [DIPLS] regression), two datasets were used: dataset A (n = 224; standardized samples) was scanned using one primary spectrometer and three secondary spectrometers; dataset B (n = 1904; legacy samples) was scanned only using the primary spectrometer. The first set of chemometrics models was developed using dataset A to compare the performance of different spectrometers. The second set of models was developed using dataset B to evaluate the effectiveness of spectral transfer functions. Both models were developed using partial least squares regression. Spectral transfer functions developed using dataset A indicate that the PC‐CCA method was the best in converging spectra collected from four instruments into a similar space projected using Uniform Manifold Approximation and Projection. Spectral transfer did not result in consistent improvement in the prediction of soil properties compared to the direct use of spectra collected from different spectrometers. These findings carry significant implications for the utilization of legacy models, enabling laboratories to concentrate on acquiring new samples and spectral measurements using established protocols without the need for spectral transfer.

Standardization method, testing scenario, and accuracy of the infrared prediction model affect the standardization accuracy of milk mid-infrared spectra

The widespread use of milk mid-infrared (MIR) spectroscopy for phenotype prediction has urged the application of prediction models across regions and countries. Spectra standardization is the most effective way to reduce the variability in the spectral signal provided by different instruments and labs. This study aimed to develop different standardization models for MIR spectra collected by multiple instruments, across 2 provinces of China, and investigate whether the standardization method (piecewise direct standardization, PDS, and direct standardization, DS), testing scenario (standardization of spectra collected on the same day or after 7 mo), infrared prediction model accuracy (high or low), and instrument (6 instruments from 2 brands) affect the performance of the standardization model. The results showed that the determination coefficient (R2) between absorbance values at each wavenumber provided by the primary and the secondary instruments increased from less than 0.90 to nearly 1.00 after standardization. Both PDS and DS successfully reduced spectra variation among instruments, and performed significantly better than non-standardization (P < 0.05). However, DS was more prone to overfitting than PDS. Standardization accuracy was higher when tested using spectra collected on the same time compared with those collected 7 mo after (P < 0.05), but great improvement in model transferability was obtained for both scenarios compared with the non-standardized spectra. The less accurate infrared prediction model (for C8:0 and C10:0 content) benefited the most (P < 0.05) from spectra standardization compared with the more accurate model (for total fat and protein content). For spectra collected after 7 mo from standardization, after PDS the RMSE between predictions obtained by different machines decreased on average by 86 and 94% compared with the values before standardization, for C8:0 and C10:0 respectively. The secondary instrument had no significant effect on the R2 between predictions (P > 0.05). The variation in the spectral signal provided by different instruments was successfully reduced by standardization across 2 provinces in China. This study lays the foundations for developing a national MIR spectra database to provide consistent predictions across provinces to be used in dairy farm management and breeding programs in China. Besides, this provides opportunities for data exchange and cooperation at international levels.

Quantitative analysis of the illegal addition of Atenolol in Panax notoginseng based on NIR-MIR spectral data fusion and calibration transfer.

To address the issue of the common illegal addition of Atenolol in Panax notoginseng, we propose an approach that realizes multivariate calibration transfer between different particle sizes based on near-infrared (NIR) and mid-infrared (MIR) spectral data fusion. To achieve high prediction accuracy, we construct three data fusion schemes (full-spectrum fusion, feature-level fusion, and decision-level fusion) that combine NIR and MIR spectral data. Among three data fusion schemes, the feature-level fusion based on the UVE-SPA-PLS model for 120-mesh spectral data achieves optimal prediction accuracy. Here, a Piecewise Direct Standardization (PDS) algorithm has been applied to calibration transfer from 100-mesh and 80-mesh to 120-mesh to reduce the influence of particle size and improve the robustness of the model. The correlation coefficient (R2) of 100-mesh, and 80-mesh prediction sets can reach 0.9861 and 0.9823, respectively. The corresponding root mean square error (RMSE) are 0.1545 and 0.2045, respectively. This research provides a method for illegal additions in precious herbs and reduces the effect of particle size on spectral modeling, enabling high-precision quantitative detection. In addition, it has important application prospects in reducing experimental losses of precious medicinal materials and ensuring the safe use of Chinese and Western medicines, which provides an alternative method for non-destructive testing.

Predicting soil organic carbon content using simulated insitu spectra and moisture correction algorithms in southern Xinjiang, China

Soil organic carbon (SOC) is an essential component of the terrestrial carbon pool, and changes in SOC are critical to ecosystem stability and agricultural production. In-situ field spectroscopy, such as visible and near-infrared (vis-NIR) spectroscopy, has proven to be an ideal tool to achieve rapid and efficient detection of SOC. However, soil moisture interference is one of the main challenges for the measurement of SOC using in-situ spectroscopy. Great progress has been made in using external parameter orthogonalization (EPO), direct standardization (DS) and piecewise direct standardization (PDS) to remove the influence of moisture on using vis-NIR spectroscopy to predict SOC. However, most current studies were conducted based on a certain moisture, which makes it difficult to provide a comprehensive guide for SOC detection using in situ spectroscopy. In this study, 135 surface (0–20 cm) soil samples were collected from the Aksu region of Xinjiang, northwestern China. The soil samples were wetted to a saturated moisture content state after manual removal of salts. The spectra data of 11 different moisture levels during natural air-drying of the wet soil samples were measured to analyze and compare the performance of three algorithms, EPO, DS and PDS, in removing the effect of moisture and improving the accuracy of SOC prediction. The results show that PDS has a relatively poor ability to remove the effect of moisture among the three moisture correction algorithms. When the moisture content of the soil exceeds 48%, EPO, DS and PDS cannot effectively remove the disturbance of moisture. The EPO algorithm was the most effective in removing moisture effects when the soil moisture content (SMC) was 25–48%. Using EPO, the predicted R2 and RPIQ of SOC increased by >0.19 and 0.87, respectively. The DS algorithm was the best method to remove the moisture effect on soil vis-NIR spectra when the SMC was 6–25%, and the R2 and RPIQ predictions of SOC after removing the effect of moisture by DS increased by >0.09 and 0.87, respectively. However, when the moisture content is <6%, the influence of soil moisture on the prediction accuracy of SOC spectra is negligible, and SOC can be predicted with high accuracy using in-situ spectra without the introduction of moisture correction algorithms. An appropriate moisture correction algorithm should be selected to remove moisture interference according to the SMC condition.

Calibration transfer via filter learning

BackgroundCalibration transfer is an essential activity in analytical chemistry in order to avoid a complete recalibration. Currently, the most popular calibration transfer methods, such as piecewise direct standardization and dynamic orthogonal projection, require a certain amount of standard or reference samples to guarantee their effectiveness. To achieve higher efficiency, it is desirable to perform the transfer with as few reference samples as possible. ResultsTo this end, we propose a new calibration transfer method by using a calibration database from a master instrument (source domain) and only one spectrum with known properties from a slave instrument (target domain). We first generate a counterpart of this spectrum in the source domain by a multivariate Gaussian kernel. Then, we train a filter to make the response function of the slave instrument equivalent to that of the master instrument. To avoid the need for labels from the target domain, we also propose an unsupervised way to implement our method. Compared with several state-of-the-art methods, the results on one simulated dataset and two real-world datasets demonstrate the effectiveness of our method. SignificanceTraditionally, the demand for certain amounts of reference samples during calibration transfer is cumbersome. Our approach, which requires only one reference sample, makes the transfer process simple and fast. In addition, we provide an alternative for performing unsupervised calibration transfer. As such, the proposed method is a promising tool for calibration transfer.

Transfer of near infrared calibration for gasoline octane number based on screening consistent wavelengths combined with direct standardization algorithm

In order to share multivariate calibration models of gasoline research octane number between different near infrared spectrometers, a novel calibration transfer method, namely combination of screening consistent wavelengths and direct standardization (SWCSS-DS) was proposed. Firstly, screening wavelengths with consistent and stable signals (SWCSS) between instruments was used to select the wavelengths with best stability, and then direct standardization (DS) further corrected the systematic errors that still exist after the SWCSS was implemented. The spectra of 120 standard gasoline samples collected on two near infrared spectrometers of the same type were investigated in detail to verify the validity of the new algorithm. Compared results of other transfer methods such as SWCSS, Slope/Bias (S/B), direct standardisation (DS), and piecewise direct standardization (PDS), the root mean squared error for prediction (RMSEP) of SWCSS-DS algorithm for target samples was decreased from 5.75 to 0.295, and the Akaike information criterion value decreased from 1516 to 640, which were better than those of the SWCSS, S/B, DS and PDS algorithms. Therefore, the joint algorithm of SWCSS-DS has not only improved the universality of the master model, but also reduced the dimension of the spectral matrix and calibration equation, that would provide a more efficient model transfer strategy for the practical applications.

Efficient Near-Infrared Spectrum Detection in Nondestructive Wood Testing via Transfer Network Redesign.

This study systematically developed a deep transfer network for near-infrared spectrum detection using convolutional neural network modules as key components. Through meticulous evaluation, specific modules and structures suitable for constructing the near-infrared spectrum detection model were identified, ensuring its effectiveness. This study extensively analyzed the basic network components and explored three unsupervised domain adaptation structures, highlighting their applications in the nondestructive testing of wood. Additionally, five transfer networks were strategically redesigned to substantially enhance their performance. The experimental results showed that the Conditional Domain Adversarial Network and Globalized Loss Optimization Transfer network outperformed the Direct Standardization, Piecewise Direct Standardization, and Spectral Space Transformation models. The coefficients of determination for the Conditional Domain Adversarial Network and Globalized Loss Optimization Transfer network are 82.11% and 83.59%, respectively, with root mean square error prediction values of 12.237 and 11.582, respectively. These achievements represent considerable advancements toward the practical implementation of an efficient and reliable near-infrared spectrum detection system using a deep transfer network.

Spectral Data Processing for Field-Scale Soil Organic Carbon Monitoring

Carbon sequestration in soils under agricultural use can contribute to climate change mitigation. Spatial–temporal soil organic carbon (SOC) monitoring requires more efficient data acquisition. This study aims to evaluate the potential of spectral on-the-go proximal measurements to serve these needs. The study was conducted as a long-term field experiment. SOC values ranged between 14 and 25 g kg−1 due to different fertilization treatments. Partial least squares regression models were built based on the spectral laboratory and field data collected with two spectrometers (site-specific and on-the-go). Correction of the field data based on the laboratory data was done by testing linear transformation, piecewise direct standardization, and external parameter orthogonalization (EPO). Different preprocessing methods were applied to extract the best possible information content from the sensor signal. The models were then thoroughly interpreted concerning spectral wavelength importance using regression coefficients and variable importance in projection scores. The detailed wavelength importance analysis disclosed the challenge of using soil spectroscopy for SOC monitoring. The use of different spectrometers under varying soil conditions revealed shifts in wavelength importance. Still, our findings on the use of on-the-go spectroscopy for spatial–temporal SOC monitoring are promising.

Is It Possible to Measure the Quality of Sugarcane in Real-Time during Harvesting Using Onboard NIR Spectroscopy?

In-field quality prediction in agricultural products is mainly based on near-infrared spectroscopy (NIR). However, initiatives applied to sugarcane quality are only observed under laboratory-controlled conditions. This study proposed a framework for NIR spectroscopy sensing to measure sugarcane quality during a real harvest operation. A platform was built to support the system composed of the NIR sensor and external lighting on the elevator of a sugarcane harvester. Real-time data were acquired in commercial fields. Georeferenced samples were collected for calibration, validation, and adjustment of the multivariate models by partial least squares (PLS) regression. In addition, subsamples of defibrated cane were NIR-acquired for the development of calibration transfer models by piecewise direct standardization (PDS). The method allowed the adjustment of the spectra collected in real time to predict the quality properties of soluble solids content (Brix), apparent sucrose in juice (Pol), fiber, cane Pol, and total recoverable sugar (TRS). The results of the relative mean square error of prediction (RRMSEP) were from 1.80 to 2.14%, and the ratio of interquartile performance (RPIQ) was from 1.79 to 2.46. The PLS-PDS models were applied to data acquired in real-time, allowing estimation of quality properties and identification of the existence of spatial variability in quality. The results showed that it is possible to monitor the spatial variability of quality properties in sugarcane in the field. Future studies with a broader range of quality attribute values and the evaluation of different configurations for sensing devices, calibration methods, and data processing are needed. The findings of this research will enable a valuable spatial information layer for the sugarcane industry, whether for agronomic decision-making, industrial operational planning, or financial management between sugar mills and suppliers.

Enhancing standardization through score-augmented projection-based calibration transfer

Reconstructing statistical models for novel instrumentation entails substantial time and financial investments. To obviate the necessity for such model reconstruction, standardization techniques are widely employed. In this context, we introduce a pioneering standardization method termed Score-Augmented Projection-Based Standardization (SA-PBS). Central to SA-PBS is the extraction of spectral sub-spaces containing interferents common to both the primary and secondary instruments. This extraction employs orthogonal projections as the foundational principle. Execution of the standardization procedure involves the judicious selection of a subset from the primary instrument's recorded dataset, facilitated by the Convex hull tool. This technique ensures the inclusion of independent and information-rich samples from the calibration dataset. Crucially, a subset of samples from the secondary instrument is also incorporated to ensure comprehensive coverage of interferents.Validation of the efficacy of the proposed SA-PBS method is conducted through quantitative analyses of target analytes across diverse scenarios, utilizing the Partial Least Squares method. Comparative assessments are performed against alternative standardization approaches, namely Direct Standardization (DS), Piecewise Direct Standardization (PDS), and Transfer Component Analysis (TCA).

Verification of the active pharmaceutical ingredient in tablets using a low-cost near-infrared spectrometer

The present study investigated the possibilities and limitations of using a low-cost NIR spectrometer for the verification of the presence of the declared active pharmaceutical ingredients (APIs) in tablet formulations, especially for medicine screening studies in low-resource settings. Spectra from 950 to 1650 nm were recorded for 170 pharmaceutical products representing 41 different APIs, API combinations or placebos. Most of the products, including 20 falsified medicines, had been collected in medicine quality studies in African countries. After exploratory principal component analysis, models were built using data-driven soft independent modelling of class analogy (DD-SIMCA), a one-class classifier algorithm, for tablet products of penicillin V, sulfamethoxazole/trimethoprim, ciprofloxacin, furosemide, metronidazole, metformin, hydrochlorothiazide, and doxycycline. Spectra of amoxicillin and amoxicillin/clavulanic acid tablets were combined into a single model. Models were tested using Procrustes cross-validation and by projection of spectra of tablets containing the same or different APIs. Tablets containing no or different APIs could be identified with 100 % specificity in all models. A separation of the spectra of amoxicillin and amoxicillin/clavulanic acid tablets was achieved by partial least squares discriminant analysis. 15 out of 19 external validation products (79 %) representing different brands of the same APIs were correctly identified as members of the target class; three of the four rejected samples showed an API mass percentage of the total tablet weight that was out of the range covered in the respective calibration set. Therefore, in future investigations larger and more representative spectral libraries are required for model building. Falsified medicines containing no API, incorrect APIs, or grossly incorrect amounts of the declared APIs could be readily identified.Variation between different NIR-S-G1 spectroscopic devices led to a loss of accuracy if spectra recorded with different devices were pooled. Therefore, piecewise direct standardization was applied for calibration transfer.The investigated method is a promising tool for medicine screening studies in low-resource settings.

Study on the rapid measurement of carbon content in marine sediments based on the model transfer of hyperspectral imaging camera and spectrometer

Laboratory spectrometer and hyperspectral imaging camera are two instruments for obtaining spectral information of substances. Both instruments have advantages in practical applications. In this paper, a total of 164 sediment samples were collected from two locations in the marine intertidal zone of Qingdao Aoshan Bay. The total carbon content (TC) concentration in marine sediments was obtained by chemical method. The spectral data of sediments were obtained by the spectrometer and the hyperspectral data were obtained by a hyperspectral imaging camera. With a spectrometer as the main instrument and a hyperspectral imaging camera as the slave instrument, the rapid measurement of carbon content in marine sediments was realized through the model transfer. Two model transfer algorithms were used: piecewise direct standardization, deviation model updating, and slope/bias correction method (PDS-DMP-S/B), and piecewise direct standardization, model updating, and slope/bias correction method (PDS-MP-S/B). Different modeling results were obtained by changing the proportion of the calibration set and test set and adding preprocessing. Compared with the single model transfer algorithm, PDS-MP-S/B and PDS-DMP-S/B were more effective. Standard normal variable transform (SNV) preprocessing had little effect on the modeling results in the model transfer between the spectrometer and hyperspectral imaging camera. After the data normalization of spectral data, all models were improved. When the ratio of the calibration set to the test set was 3:1, the PDS-DMP-S/B algorithm was used for the model transfer, the RP2 value of the modeling result was 0.693, the RMSEP value was 2.332, and the RPD value was 1.615, which achieved a relatively ideal modeling result. This study provides a new and fast method for predicting the carbon content in marine sediments.

Application of stable consistency wavelength in optimizing gasoline RON near‐infrared analysis model transfer

AbstractThe purpose of model transfer is to solve the problem that multivariate calibration models cannot be shared among different near‐infrared spectrometers. Taking gasoline as the research object, the transfer analysis of its octane number model was carried out. The gasoline samples collected by two near‐infrared spectrometers of the same type were used as the research object. The screening wavelengths with consistent and stable signals (SWCSS) combined with competitive adaptive reweighted sampling (CARS), uninformative variable elimination (UVE), and successive projections algorithm (SPA) were used to reduce the adverse effects of invalid wavelengths in the SWCSS method; therefore, the analysis ability of the master model to the slave samples was improved. Partial least squares regression (PLSR) models based on SWCSS‐UVE, SWCSS‐CARS, and SWCSS‐SPA algorithms were established, and comparison was made between their analytical capabilities for slave samples and those of SWCSS, direct standardization (DS) algorithm , piecewise direct standardization (PDS) algorithm, and slope/bias (S/B) algorithm. The results shown that the SWCSS‐UVE and SWCSS‐CARS methods can be used to establish models from the 231 and 6 wavelengths selected from the consistent wavelengths, respectively. The root mean square error of prediction (RMSEP) of the gasoline octane number (RON) content of the direct analysis of the spectrum measured by the slave machine was reduced from 5.7490 to 0.3226 and 0.3250, respectively, which was better than the single SWCSS and DS, PDS, and SWCSS‐SPA methods, and was close to the model transfer accuracy of the S/B algorithm. The transfer accuracy of SWCSS‐UVE and SWCSS‐CARS was not much different, but the wavelength variable involved in the model transfer of the latter was much smaller than that of the former, and the AIC value of SWCSS‐CARS was −59.59, which was much smaller than the akaike information criterion (AIC) value of SWCSS‐UVE 398.42.

Comparison of Transfer Learning and Established Calibration Transfer Methods for Metal Oxide Semiconductor Gas Sensors

Although metal oxide semiconductors are a promising candidate for accurate indoor air quality assessments, multiple drawbacks of the gas sensors prevent their widespread use. Examples include poor selectivity, instability over time, and sensor poisoning. Complex calibration methods and advanced operation modes can solve some of those drawbacks. However, this leads to long calibration times, which are unsuitable for mass production. In recent years, multiple attempts to solve calibration transfer have been made with the help of direct standardization, orthogonal signal correction, and many more methods. Besides those, a new promising approach is transfer learning from deep learning. This article will compare different calibration transfer methods, including direct standardization, piecewise direct standardization, transfer learning for deep learning models, and global model building. The machine learning methods to calibrate the initial models for calibration transfer are feature extraction, selection, and regression (established methods) and a custom convolutional neural network TCOCNN. It is shown that transfer learning can outperform the other calibration transfer methods regarding the root mean squared error, especially if the initial model is built with multiple sensors. It was possible to reduce the number of calibration samples by up to 99.3% (from 10 days to approximately 2 h) and still achieve an RMSE for acetone of around 18 ppb (15 ppb with extended individual calibration) if six different sensors were used for building the initial model. Furthermore, it was shown that the other calibration transfer methods (direct standardization and piecewise direct standardization) also work reasonably well for both machine learning approaches, primarily when multiple sensors are used for the initial model.