Near-infrared Spectrometer Research Articles

Quantitative determination of zearalenone in wheat by the CSA-NIR technique combined with chemometrics algorithms

In the current study, a colorimetric sensor array combined with near-infrared (NIR) spectroscopy was used to quantitatively analyze zearalenone in wheat. The portable NIR spectrometer was used to scan the porphyrin reaction points of the wheat colorimetric sensor and collect spectral data. Subsequently, based on all the NIR spectral data, the two models and three feature selection algorithms are compared, and the best performance model and the best feature variable input are selected. Concurrently, the Kernel-based Extreme Learning Machine (KELM) model optimized by the two parameter optimization algorithms was compared, and the best parameter optimization algorithm was selected. Among all evaluation models, the KELM model optimized by the Competitive Adaptive Reweighted Sampling algorithm combined with the rime optimization algorithm has the best prediction effect. The predicted RP2 is 0.9900, and the root mean square error of prediction (RMSEP) is 18.4610 μg∙kg-1.

Quantification of API content in pharmaceutical tablets within milliseconds by time-stretch near-infrared transmission spectroscopy

We explored the feasibility of high-speed and high-accuracy quantification of active pharmaceutical ingredient (API) content in tablet products by near-infrared (NIR) spectroscopy to improve the reliability of pharmaceuticals. For this purpose, we employed a high-power NIR time-stretch transmission spectrometer recently developed by us. By using this transmission spectrometer with a multivariate calibration model, we demonstrated the ability to quantify API content with a short measurement time of 3.9 ms per tablet for model pharmaceuticals. For the model tablet, the quantification ability of our spectrometer was comparable to that achieved by a commonly used Fourier-transform NIR (FT-NIR) spectrometer with a measurement time of several seconds. We also confirmed that the effect of irradiating tablets with the NIR pulses used in our spectrometer was negligible.

Relationship among intramuscular fat, crude protein, and moisture in porcine longissimus thoracis muscle and their prediction by a handheld fiber-optic near-infrared spectrometer

The handheld fiber-optic near-infrared (NIR) spectrometer with special probe, which is widely used for Wagyu beef carcass in all Japan, was determined to predict the chemical composition in pork. Since intramuscular fat (IMF) is related to eating quality and the relationships among chemical compositions were examined. The intact longissimus dorsi muscles collected from meat markets in Japan (N = 914) were scanned at three sites in the same cut, and analyzed chemically. The data were used for calibration (N = 553 out of 605), prediction (N = 300) and repeatability (N = 9). One-point increase in IMF resulted in linear decreases in moisture and crude protein at approximate rate of 0.7- and 0.3- points, respectively (N = 905). The spectrometer had high repeatability, and the optical values had interaction between the individual pork and the measurement site. The coefficients of determination in the prediction were 0.81, 0.91 and 0.66 for moisture, IMF and crude protein, respectively. The agreements between chemical and optical methods was strong for IMF (intraclass correlation coefficients 0.92) and moisture (0.81), and moderate for crude protein (0.64). These results showed that the handheld fiber-optic NIR spectrometer can quickly evaluate chemical composition for intact pork.

Light-driven incubation of Fusarium species and near-infrared spectroscopy for an early in vitro identification of Fusarium circinatum

This study explores the application of near-infrared (NIR) spectroscopy coupled with multivariate techniques for the rapid and accurate identification of four Fusarium species, with emphasis on the detection of Fusarium circinatum, the causative agent of “Pitch canker” disease in forests, cultured in vitro under distinct light conditions. The impact of two different incubation conditions, near-ultraviolet (NUV) and warm light, on the spectral characteristics of cultures was used as a strategy to improve the early fungal detection using spectroscopy. Spectral data were acquired using a portable NIR spectrometer at 48, 72, and 96 h post-cultivation from various zones of mycelial growth. The results showed distinct spectral profiles among Fusarium species, with notable variations depending on incubation light conditions and growth zones. NUV light conditions significantly improved species differentiation, especially in the central and middle zones of mycelial growth at 72 h post-cultivation (hpc). Partial least squares − discriminant analysis (PLS-DA) model under NUV light conditions provided the best identification strategy, achieving correct classification rates over 97% for all four species from 72 hpc and 82.5% of correct classification of F. circinatum. These findings demonstrate the effectiveness of the NIRS methodology supported with multivariate techniques and combined with optimization of light conditions and mycelial growth zone of cultures, for the early and rapid detection of Fusarium species in culture media, with potential implications for plant pathology diagnostics and disease management strategies.

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.

SDS-assisted solar evaporation on floating carbon-based hybrid porous evaporator

Solar evaporation systems represent a green and sustainable strategy for obtaining fresh water. However, traditional evaporation processes depend on the heating of bulk water. Recently, floating solar absorbers have demonstrated excellent evaporation efficiency via localized heating at the device–water interface. In this work, a floating carbon-based hybrid porous evaporator was prepared through simple and inexpensive phase conversion methods, effectively improving the water evaporation efficiency two-fold compared to pure water. The evaporators and evaporation process were characterized by mercury porosimeter, scanning electron microscope, near-infrared spectrometer, infrared thermography, and differential scanning calorimetry. Furthermore, by introducing sodium dodecyl sulfate to regulate the surface hydrophobicity and hydrogen bond structure of water at the device–water interface, the evaporation rate was further improved to 1.27 kg·m−2·h−1 (three times that of pure water) at the optimal sodium dodecyl sulfate concentration of 0.3–1 mmol·L−1. The system also demonstrated excellent practical performance and durability in the evaporation of seawater, salt solutions, and under natural sunlight conditions. This work creates a new avenue for the evaporation applications of hydrophobic carbon-based materials and provides a strategy to regulate solar evaporation systems from the perspective of bulk water by introduction of a surfactant.

Classification of Fritillaria using a portable near-infrared spectrometer and fuzzy generalized singular value decomposition

Fritillaria is a popular Chinese medicinal crop known for its medicinal value. However, the chemical composition and medicinal value of Fritillaria can vary significantly depending on the variety and origin. Therefore, there is a need for a more efficient and accurate method to identify Fritillaria of different varieties and origins. This study employed a portable near-infrared (NIR) spectrometer to collect NIR spectral data on six kinds of Fritillaria and classify them by using different feature extraction methods. In order to circumvent the limitations of Linear Discriminant Analysis (LDA) in small-sample size problem and improve the classification accuracy, Fuzzy Generalized Singular Value Decomposition (FGSVD) was proposed for feature extraction from NIR spectra. The original NIR data were first pre-processed by the Savitzky-Golay (SG) filtering, and then their dimensionality was reduced by Principal Component Analysis (PCA). After that, Generalized Singular Value Decomposition (GSVD) and FGSVD were performed for feature extraction, respectively. In the end, the spectral data were classified into six categories using the k-Nearest Neighbour (KNN) classifier and Extreme Learning Machines (ELM). The results of the study showed that FGSVD had the highest classification accuracy when using the KNN classifier and was able to achieve 100 % classification accuracy. At the same time, GSVD and LDA were able to achieve 97.5 % and 92.5 % classification accuracy respectively. The classification accuracy obtained by FGSVD was also higher than GSVD and LDA when ELM was used. The highest classification accuracies obtained by FGSVD, GSVD and LDA were 96.9 %, 94.2 % and 92.3 % respectively. Thus, the KNN classifier outperformed ELM in classification. Consequently, the portable near-infrared spectrometer coupled with PCA+FGSVD is a novel strategy for rapid and non-destructive classification of Fritillaria.

Noninvasive Temperature Measurements in Tissue-Simulating Phantoms Using a Solid-State Near-Infrared Sensor.

The monitoring of body temperature is a recent addition to the plethora of parameters provided by wellness and fitness wearable devices. Current wearable temperature measurements are made at the skin surface, a measurement that is impacted by the ambient environment of the individual. The use of near-infrared spectroscopy provides the potential for a measurement below the epidermal layer of skin, thereby having the potential advantage of being more reflective of physiological conditions. The feasibility of noninvasive temperature measurements is demonstrated by using an in vitro model designed to mimic the near-infrared spectra of skin. A miniaturizable solid-state laser-diode-based near-infrared spectrometer was used to collect diffuse reflectance spectra for a set of seven tissue phantoms composed of different amounts of water, gelatin, and Intralipid. Temperatures were varied between 20-24 °C while collecting these spectra. Two types of partial least squares (PLS) calibration models were developed to evaluate the analytical utility of this approach. In both cases, the collected spectra were used without pre-processing and the number of latent variables was the only optimized parameter. The first approach involved splitting the whole dataset into separate calibration and prediction subsets for which a single optimized PLS model was developed. For this first case, the coefficient of determination (R2) is 0.95 and the standard error of prediction (SEP) is 0.22 °C for temperature predictions. The second strategy used a leave-one-phantom-out methodology that resulted in seven PLS models, each predicting the temperatures for all spectra in the held-out phantom. For this set of phantom-specific predicted temperatures, R2 and SEP values range from 0.67-0.99 and 0.19-0.65 °C, respectively. The stability and reproducibility of the sample-to-spectrometer interface are identified as major sources of spectral variance within and between phantoms. Overall, results from this in vitro study justify the development of future in vivo measurement technologies for applications as wearables for continuous, real-time monitoring of body temperature for both healthy and ill individuals.

Application of Portable Near-Infrared Instrument for Analysis of Spirulina platensis Aqueous Extracts

Spirulina platensis microalga has become recognized as a promising source of highly nutritious food components to feed the growing global population. Because of its high protein content, abundance of essential amino acids, and excellent digestion, it is employed in human nutrition and there is growing interest in analyzing bioactive compound present in Spirulina platensis microalga. In this work, a portable near-infrared (NIR) spectrometer was used for the monitoring of physicochemical properties (extraction yield (EY), total polyphenols concentration (TPC), total proteins concentration (TP), antioxidant activity measured by (i) the DPPH method (DPPH) and (ii) FRAP method (FRAP)) of Spirulina platensis aqueous extracts. The ultrasound-assisted aqueous extraction (ultrasonic bath with an ultrasound frequency of 35 kHz) of bioactive molecules from Spirulina platensis was performed throughout 30 independent experiments. NIR spectra were recorded in the wavelength range of 900–1700 nm. Raw NIR spectra were subjected to the physicochemical properties applying Principal Component Analysis (PCA), partial least square (PLS), and artificial neural network (ANN) modeling. Results show that ANN models developed for the prediction of TPC and DPPH can be utilized for extraction process control (RER > 10), while the other three models can be employed for screening (RER > 4). Generally, the obtained results indicate significant potential for using portable NIR spectroscopy for the analysis of Spirulina platensis aqueous extracts.

Deep learning model based on molecular spectra to determine chlorpyrifos residues in corn oil

This study presents a novel molecular spectroscopy depth fusion strategy for rapid detection of residual chlorpyrifos in corn oil. Raman and Fourier transform near-infrared (FT-NIR) spectrometers were employed to collect contaminated corn oil sample spectra. The multi-spectral fusion enhances spectral features, improving data reliability and outcomes. The research employed low and mid-level fusion strategies alongside a one-dimensional convolutional neural network (1D-CNN) for modeling. The mid-level data fusion model outperformed the low-level model, achieving a relative percent deviation (RPD) of 11.6517 and a prediction coefficient of determination (RP2) of 0.9874. The results indicate that the mid-level fusion strategy is suitable for multivariate model calibration of Raman and FT-NIR, providing a rapid detection method for pesticide residues in edible oils. This study offers a method reference for fusion strategies in molecular spectroscopy and expands the application scope of deep learning in spectroscopy.

Deployment strategy of multiple miniaturized near-infrared spectrometers based on spectral transfer for characterizing soil organic matter and nitrogen

Developing timely, convenient, and low-cost methods for high-frequency characterization of soil nutrients is necessary for implementing precise soil nutrient management. With the current availability of numerous calibration models of laboratory benchtop near-infrared (NIR) spectrometers for rapid soil nutrient characterization and the appearance of low-cost, convenient miniaturized NIR spectrometers, this study proposes an efficient deployment strategy to address model failure due to inter-device variation based on spectral transfer. The strategy involves using Direct Standardization (DS) to migrate the spectra from multiple miniaturized NIR spectrometers with a laboratory benchtop NIR spectrometer and then directly applying the existing calibration models of the laboratory benchtop instrument to the transferred spectra for soil nutrient analysis. The results indicated that the DS method successfully transferred the spectra of miniaturized devices to be consistent with the spectra of the laboratory benchtop instrument. The soil organic matter (SOM) predictions using the transferred spectra and the calibration models of the laboratory benchtop instrument were even more accurate than those using the respective models developed for each miniaturized devices, with root mean square error (RMSE) of 0.177 %, 0.177 %, and 0.150 %, respectively, while the performances of total nitrogen (TN) predictions were comparable to those using the respective models, with RMSE of 0.013 %, 0.012 %, and 0.010 %, respectively. Bland-Altman plots demonstrated good consistency between the strategy proposed in this study and the strategy of developing respective models for each miniaturized device, with no difference in predictions for the independent validation set compared to the laboratory benchtop instrument. This study proved the feasibility of deployment strategy of multiple miniaturized NIR spectrometers based on spectral transfer, offering a new solution for high-frequency on-site soil nutrient characterization.

Seasonal variation of antioxidant bioactive compounds in southern highbush blueberry leaves and non-destructive quality prediction in situ by a portable near-infrared spectrometer

Blueberry leaves (BBL) are a natural source with strong antioxidant activity, but bioactive compounds and their seasonal variation remain vague. Here, two major classes of compounds including four caffeoylquinic acids and eight flavonoids were identified in two southern highbush cultivars (“Lanmei” #1 and “Jewel”) grown in China. Major bioactive compounds were discovered using an online HPLC post-column derivatization system and determined as neochlorogenic acid (NeoCA), chlorogenic acid (CA), rutin, hyperoside, and isoquercitrin. CA contributed the most to the BBL antioxidant activity. “Lanmei” showed significant advantages in terms of rutin content and antioxidant activity over “Jewel” (P < 0.05). The highest CA content (CAC) of juvenile “Jewel” leaves reached 17.9%. July was the optimum harvest time for both cultivars after fruiting stage. Total phenolic content (TPC) and Trolox equivalent antioxidant capacity (TEAC) of fresh BBL were accurately predicted by a portable near-infrared (NIR) device in a rapid, low-cost, and non-destructive way in situ.

Rapid assessment of vanilla (Vanilla planifolia) quality parameters using portable near-infrared spectroscopy combined with random forest

The determination of moisture and vanillin content significantly influences the quality of vanilla. Currently, conventional chemical methods employed for assessing these parameters are time-consuming, involve complex sample preparation, are expensive, and environmentally unfriendly due to the use of chemical solutions. Portable Near-Infrared (NIR) spectroscopy emerges as a promising alternative, characterized by smaller dimensions and lower costs. This study investigates the performance of two portable NIR spectrometers with distinct wavelengths at 740–1070 nm and 1350–2550 nm, in conjunction with Random Forest (RF) and Partial Least Square (PLS) regression, and preprocessing techniques including min-max normalization, 1st derivative, standard normal variate (SNV), multiplicative scatter correction (MSC), 1st derivative + SNV, and 1st derivative + MSC for predicting moisture and vanillin content. At the wavelength range of 1350–2550 nm, RF coupled with 1st derivative produced the best moisture content prediction model with an R2 of 0.971, and RF paired with 1st derivative+SNV yielded the best vanillin content prediction with an R2 of 0.983. This work highlights that the integration of portable NIR and RF allows for rapid and non-destructive detection of moisture and vanillin content. This methodology provides a novel regression method for predicting vanilla qualities.

Determination of butylated hydroxytoluene in edible oil using near-infrared spectroscopy combined with multivariate analysis

Edible oil is a fundamental component of human daily diet and has a wide impact on global agriculture and economy. The issue of additives in edible oil has always been a concern for its quality and safety, as excessive use of additives can be harmful to human health. This study suggests a quantitative detection technique for determining the concentration of butylated hydroxytoluene (BHT) in edible oil using near-infrared spectroscopy (NIRS) technology. Firstly, the spectral characteristics of edible oil samples with different concentrations of BHT are characterized using a near-infrared spectrometer. Then, particle swarm optimization (PSO), butterfly optimization algorithm (BOA), and fox optimizer (FOX) are employed to optimize the preprocessed spectral wavelengths. Finally, a detection model based on the optimized wavelengths is established using backpropagation neural network (BP-ANN) to achieve quantitative detection of BHT content in edible oil. The results show that the model based on the feature wavelengths optimized by the FOX algorithm has the best detection performance. This model takes 7 features as inputs, with a root mean square error of prediction (RMSEP) of 1.6116 g·kg−1 and a prediction determination coefficient (RP) of 0.9900 on the prediction set. The results demonstrate that near-infrared spectroscopy technology can accurately predict the BHT content in edible oil.

A Dataset for Estimating Participant Inspiration in Meetings toward AI-Based Meeting Support System to Improve Worker Wellbeing

Various meetings are carried out in intellectual production activities and workers have to spend much time to create ideas. In creative meetings, it is sometime difficult for the meeting moderators and facilitators to efficiently conduct the meetings because the participants are required to come up with new ideas one after another and some participants hesitate to express unconventional ideas. Therefore, we propose to develop an AI-based meeting support system that estimates participants’ inspiration and helps to generate comfortable meeting environments for improvement of worker wellbeing. Participants’ inspiration is assumed to be estimated based on their speech and micro behaviors including smiles and nods. In this paper, a dataset we collected for the development of the proposed system is reported. The dataset consists of participants’ brain blood flows measured near-infrared spectrometers, micro behavior annotated from video recording, and inspiration the participants reported with buttons. The data for 1020 min was collected by conducting simulation meetings. In future work, we plan to train an LSTM (long short-term memory) based neural network model to realize the proposed system.

Sensor for Rapid In-Field Classification of Cannabis Samples Based on Near-Infrared Spectroscopy.

A rugged handheld sensor for rapid in-field classification of cannabis samples based on their THC content using ultra-compact near-infrared spectrometer technology is presented. The device is designed for use by the Austrian authorities to discriminate between legal and illegal cannabis samples directly at the place of intervention. Hence, the sensor allows direct measurement through commonly encountered transparent plastic packaging made from polypropylene or polyethylene without any sample preparation. The measurement time is below 20 s. Measured spectral data are evaluated using partial least squares discriminant analysis directly on the device's hardware, eliminating the need for internet connectivity for cloud computing. The classification result is visually indicated directly on the sensor via a colored LED. Validation of the sensor is performed on an independent data set acquired by non-expert users after a short introduction. Despite the challenging setting, the achieved classification accuracy is higher than 80%. Therefore, the handheld sensor has the potential to reduce the number of unnecessarily confiscated legal cannabis samples, which would lead to significant monetary savings for the authorities.

Measurement errors and implications for preprocessing in miniaturised near-infrared spectrometers: Classification of sweet and bitter almonds as a case of study

Near-infrared (NIR) spectroscopy is a well-established analytical technique that has been used in many applications over the years. Due to the advancements in the semiconductor industry, NIR instruments have evolved from benchtop instruments to miniaturised portable devices. The miniaturised NIR instruments have gained more interest in recent years because of the fast and robust measurements they provide with almost no sample pretreatments.However, due to the very different configurations and characteristics of these instruments, they need a dedicated optimization of the measurement conditions, which is crucial for obtaining reliable results. To comprehensively grasp the capabilities and potentials offered by these sensors, it is imperative to examine errors that can affect the raw data, which is a facet frequently overlooked. In this study, measurement error covariance and correlation matrices were calculated and then visually inspected to gain insight into the error structures associated with the devices, and to find the optimal preprocessing technique that may result in the improvement of the models built.This strategy was applied to the classification of sweet and bitter almonds, which were measured with the three portable low-cost NIR devices (SCiO, FlameNIR+ and NeoSpectra Micro Development Kit) after removing the shelled, since their classification is of utmost importance for the almond industry. The results showed that bitter almonds can be classified from sweet almonds using any of the instruments after selecting the optimal preprocessing, obtained through inspection of covariance and correlation matrices. Measurements obtained with FlameNIR + device provided the best classification models with an accuracy of 98 %. The chosen strategy provides new insight into the performance characterization of the fast-growing miniaturised NIR instruments.

Near-Infrared Spectroscopy Combined with Fuzzy Improved Direct Linear Discriminant Analysis for Nondestructive Discrimination of Chrysanthemum Tea Varieties.

The quality of chrysanthemum tea has a great connection with its variety. Different types of chrysanthemum tea have very different efficacies and functions. Moreover, the discrimination of chrysanthemum tea varieties is a significant issue in the tea industry. Therefore, to correctly and non-destructively categorize chrysanthemum tea samples, this study attempted to design a novel feature extraction method based on the fuzzy set theory and improved direct linear discriminant analysis (IDLDA), called fuzzy IDLDA (FIDLDA), for extracting the discriminant features from the near-infrared (NIR) spectral data of chrysanthemum tea. To start with, a portable NIR spectrometer was used to collect NIR data for five varieties of chrysanthemum tea, totaling 400 samples. Secondly, the raw NIR spectra were processed by four different pretreatment methods to reduce noise and redundant data. Thirdly, NIR data dimensionality reduction was performed by principal component analysis (PCA). Fourthly, feature extraction from the NIR spectra was performed by linear discriminant analysis (LDA), IDLDA, and FIDLDA. Finally, the K-nearest neighbor (KNN) algorithm was applied to evaluate the classification accuracy of the discrimination system. The experimental results show that the discrimination accuracies of LDA, IDLDA, and FIDLDA could reach 87.2%, 94.4%, and 99.2%, respectively. Therefore, the combination of near-infrared spectroscopy and FIDLDA has great application potential and prospects in the field of nondestructive discrimination of chrysanthemum tea varieties.

Predicting grass proportion in fresh alfalfa: Grass mixtures using a hand‐held near‐infrared spectrometer

AbstractTechnological advancements have made hand‐held near infrared (NIR) spectrometers more affordable and more accurate, creating interest in on‐farm application for forage management. The objective of this study was to evaluate the ability of a hand‐held NIR spectrometer to predict grass percentage within fresh alfalfa (Medicago sativa L.):grass mixtures. Forage samples were collected at a range of maturities and varieties during the 2021 and 2022 growing seasons from multiple locations in New York. Fresh forage samples were chopped, and pure species were combined into known proportions on a dry matter basis, resulting in 534 samples. Analysis was carried out on NIR spectra collected from a hand‐held NeoSpectra spectrometer using stationary and sliding scanning techniques. Development of calibration models was completed using partial least squares regression with cross validation. The best performing calibration model using absorbance was from the sliding scanning technique with preprocessing consisting of mean‐centering (R2 = 0.89, root mean square error of prediction [RMSEP] = 13.7%, and ratio of prediction to deviation = 2.53). A total of 84% of the samples were correctly classified when the grass component was lower than 40%. For samples with the grass component above 40%, a total of 94% of the samples were correctly classified. Correct sample classification is critical considering that the extension recommendation in New York is to reseed alfalfa fields when the grass component exceeds 40% of the sward on a botanical composition basis. This research demonstrates that NIR technology has potential to provide the agricultural industry with rapid, non‐destructive, and affordable information to allow farmers and consultants to predict grass proportion within alfalfa:grass fresh forage mixtures in real time.

Portable near infrared (NIR) spectrometer coupled with machine learning to classify milk with subclinical mastitis

Milk is one of the traditional foods in the human diet. However, subclinical mastitis infection in cows could compromise the nutritional composition of milk as well as the consumer safety. In this study, we investigated the possibility of implementing near infrared spectroscopy (NIRS), using a portable spectrometer, as a screening method to detect milk contaminated with subclinical mastitis. The spectra was acquired from a highly complex milk sample set (two seasons: winter and summer; two years: 2021 and 2022; from five geographical locations within Brazil: Goiás, Pará, Paraíba, São Paulo, and Santa Catarina; different feeding systems.) were analyzed using Principal Component Analysis (PCA) and Partial Least Squares Discriminant Analysis (PLS-DA), as well as machine learning models like Random Forest (RF) and Support Vector Machine (SVM). PCA revealed that the clustering of mastitis milk and non-mastitis milk samples was associated with variations in lactose content. This observation was also noted in PLS-DA, which achieved accuracy values of 78%, compared to the 62% achieved by RF and SVM in detecting mastitis milk. However, the sensitivity (recall) for detecting mastitis samples was higher for RF (78%), and SVM notably excelled in detecting non-mastitis milk (81%). Furthermore, it was demonstrated that the removal of outliers using Isolation Forest enhances the performance of RF and SVM models based on NIR spectra, with increases of up to 25% in the precision. In conclusion, the portable NIR spectrometer could potentially serve as a screening method in the dairy industry to detect mastitis milk samples.